ALBERT

All Library Books, journals and Electronic Records Telegrafenberg

X
feed icon rss

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
Filter
  • Articles  (13,069)
  • Articles: DFG German National Licenses  (13,069)
  • Chemical Engineering  (11,634)
  • Industrial Chemistry and Chemical Engineering  (1,133)
  • neural networks  (165)
  • Escherichia coli  (136)
  • Animals
  • Process Engineering, Biotechnology, Nutrition Technology  (12,905)
  • Computer Science  (164)
Collection
  • Articles  (13,069)
Source
Keywords
Publisher
Years
Topic
  • 1
    Electronic Resource
    Electronic Resource
    The Causal and Explanatory Role of Information Stored in Connectionist Networks (2000)
    Springer
    Minds and machines 10 (2000), S. 361-380 
    Details
    ISSN: 1572-8641
    Keywords: connectionism ; mental representation ; neural networks ; causation ; explanation philosophy of mind
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Philosophy
    Notes: Abstract In this paper I defend the propriety of explaining the behavior of distributed connectionist networks by appeal to selected data stored therein. In particular, I argue that if there is a problem with such explanations, it is a consequence of the fact that information storage in networks is superpositional, and not because it is distributed. I then develop a “proto-account” of causation for networks, based on an account of Andy Clark's, that shows even superpositionality does not undermine information-based explanation. Finally, I argue that the resulting explanations are genuinely informative and not vacuous.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1026545231550
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 2
    Electronic Resource
    Electronic Resource
    Obstacle Avoidance Using the Human Operator Experience for a Mobile Robot (2000)
    Springer
    Journal of intelligent and robotic systems 27 (2000), S. 305-319 
    Details
    ISSN: 1573-0409
    Keywords: control ; fuzzy logic ; neural networks ; robotics
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract In this paper, a neuro-fuzzy technique has been used to steer a mobile robot. The neuro-fuzzy approach provides a good way to capture the information given by a human. In this manner, it has been possible to obtain the rules and membership functions automatically whereas a fuzzy approach needs to make a prior definition of the rules and membership functions. In order to apply the neuro-fuzzy strategy, two mobile robots have been developed. However, in this paper only the smallest one has been considered. Similar results are obtained for the biggest one. The results of the approach are satisfactory, avoiding the obstacles when the mobile robot is steered to the target.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008104122177
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 3
    Electronic Resource
    Electronic Resource
    Adaptive Retrieval Agents: Internalizing Local Context and Scaling up to the Web (2000)
    Springer
    Machine learning 39 (2000), S. 203-242 
    Details
    ISSN: 0885-6125
    Keywords: InfoSpiders ; distributed information retrieval ; evolutionary algorithms ; local selection ; internalization ; reinforcement learning ; neural networks ; relevance feedback ; linkage topology ; scalability ; selective query expansion ; adaptive on-line Web agents
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract This paper discusses a novel distributed adaptive algorithm and representation used to construct populations of adaptive Web agents. These InfoSpiders browse networked information environments on-line in search of pages relevant to the user, by traversing hyperlinks in an autonomous and intelligent fashion. Each agent adapts to the spatial and temporal regularities of its local context thanks to a combination of machine learning techniques inspired by ecological models: evolutionary adaptation with local selection, reinforcement learning and selective query expansion by internalization of environmental signals, and optional relevance feedback. We evaluate the feasibility and performance of these methods in three domains: a general class of artificial graph environments, a controlled subset of the Web, and (preliminarly) the full Web. Our results suggest that InfoSpiders could take advantage of the starting points provided by search engines, based on global word statistics, and then use linkage topology to guide their search on-line. We show how this approach can complement the current state of the art, especially with respect to the scalability challenge.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1007653114902
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 4
    Electronic Resource
    Electronic Resource
    Approximation by radial bases and neural networks (2000)
    Springer
    Numerical algorithms 25 (2000), S. 241-262 
    Details
    ISSN: 1572-9265
    Keywords: approximation ; radial basis functions ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract In this paper, we study approximation by radial basis functions including Gaussian, multiquadric, and thin plate spline functions, and derive order of approximation under certain conditions. Moreover, neural networks are also constructed by wavelet recovery formula and wavelet frames.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1016685729545
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 5
    Electronic Resource
    Electronic Resource
    Recognition of Handwritten ZIP Codes in a Real—World Non-Standard-Letter Sorting System (2000)
    Springer
    Applied intelligence 12 (2000), S. 95-115 
    Details
    ISSN: 1573-7497
    Keywords: postal automation ; address reading ; neural networks ; handprinted digit recognition
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract In this article, we describe the OCR and image processing algorithms used to read destination addresses from non-standard letters (flats) by Siemens postal automation system currently in use by the Deutsche Post AG1. We first describe the sorting machine, its OCR hardware and the sequence of image processing and pattern recognition algorithms needed to solve the difficult task of reading mail addresses, especially handwritten ones. The article concentrates mainly on the two classifiers used to recognize handprinted digits. One of them is a complex time delayed neural network (TDNN) used to classify scaled digit-features. The other classifier extracts the structure of each digit and matches it to a number of prototypes. Different digits represented by the same graph are then discriminated by classifiying some of the features of the digit-graph with small neural networks. We also describe some approaches for the segmentation of the digits in the ZIP code, so that the resulting parts can be processed and evaluated by the classifiers.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008316121543
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 6
    Electronic Resource
    Electronic Resource
    Fuzzy Neural Network Models for Classification (2000)
    Springer
    Applied intelligence 12 (2000), S. 207-215 
    Details
    ISSN: 1573-7497
    Keywords: fuzzy logic ; neural networks ; decision systems ; classification
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract In this paper, we combine neural networks with fuzzy logic techniques. We propose a fuzzy-neural network model for pattern recognition. The model consists of three layers. The first layer is an input layer. The second layer maps input features to the corresponding fuzzy membership values, and the third layer implements the inference engine. The learning process consists of two phases. During the first phase weights between the last two layers are updated using the gradient descent procedure, and during the second phase membership functions are updated or tuned. As an illustration the model is used to classify samples from a multispectral satellite image, a data set representing fruits, and Iris data set.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008367007808
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 7
    Electronic Resource
    Electronic Resource
    Neural Networks and Structured Knowledge: Rule Extraction and Applications (2000)
    Springer
    Applied intelligence 12 (2000), S. 7-13 
    Details
    ISSN: 1573-7497
    Keywords: neural networks ; rule extraction ; knowledge representation ; structured knowledge ; connectionism ; hybrid systems
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract As the second part of a special issue on “Neural Networks and Structured Knowledge,” the contributions collected here concentrate on the extraction of knowledge, particularly in the form of rules, from neural networks, and on applications relying on the representation and processing of structured knowledge by neural networks. The transformation of the low-level internal representation in a neural network into higher-level knowledge or information that can be interpreted more easily by humans and integrated with symbol-oriented mechanisms is the subject of the first group of papers. The second group of papers uses specific applications as starting point, and describes approaches based on neural networks for the knowledge representation required to solve crucial tasks in the respective application. The companion first part of the special issue [1] contains papers dealing with representation and reasoning issues on the basis of neural networks.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008344602888
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 8
    Electronic Resource
    Electronic Resource
    On-line Algorithm for Blind Signal Extraction of Arbitrarily Distributed, but Temporally Correlated Sources Using Second Order Statistics (2000)
    Springer
    Neural processing letters 12 (2000), S. 91-98 
    Details
    ISSN: 1573-773X
    Keywords: adaptive learning algorithms ; blind signal processing ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Most of the algorithms for blind separation/extraction and independent component analysis (ICA) can not separate mixtures of sources with extremely low kurtosis or colored Gaussian sources. Moreover, to separate mixtures of super- and sub-Gaussian signals, it is necessary to use adaptive (time-variable) or switching nonlinearities which are controlled via computationally intensive measures, such as estimation of the sign of kurtosis of extracted signals. In this paper, we develop a very simple neural network model and an efficient on-line adaptive algorithm that sequentially extract temporally correlated sources with arbitrary distributions, including colored Gaussian sources and sources with extremely low values (or even zero) of kurtosis. The validity and performance of the algorithm have been confirmed by extensive computer simulation experiments.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009616029367
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 9
    Electronic Resource
    Electronic Resource
    Using a Neural Network to Approximate an Ensemble of Classifiers (2000)
    Springer
    Neural processing letters 12 (2000), S. 225-237 
    Details
    ISSN: 1573-773X
    Keywords: approximator ; bagging ; boosting ; ensemble of classifiers ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Several methods (e.g., Bagging, Boosting) of constructing and combining an ensemble of classifiers have recently been shown capable of improving accuracy of a class of commonly used classifiers (e.g., decision trees, neural networks). The accuracy gain achieved, however, is at the expense of a higher requirement for storage and computation. This storage and computation overhead can decrease the utility of these methods when applied to real-world situations. In this Letter, we propose a learning approach which allows a single neural network to approximate a given ensemble of classifiers. Experiments on a large number of real-world data sets show that this approach can substantially save storage and computation while still maintaining accuracy similar to that of the entire ensemble.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1026530200837
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 10
    Electronic Resource
    Electronic Resource
    Building Adaptive Basis Functions with a Continuous Self-OrganizingMap (2000)
    Springer
    Neural processing letters 11 (2000), S. 59-78 
    Details
    ISSN: 1573-773X
    Keywords: basis functions ; continuous function approximation ; competitive learning ; interpolation ; neural networks ; on-line learning ; self-organizing map
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract This paper introduces CSOM, a continuous version of the Self-Organizing Map(SOM). The CSOM network generates maps similar to those created with theoriginal SOM algorithm but, due to the continuous nature of the mapping,CSOM outperforms the SOM on function approximation tasks. CSOM integratesself-organization and smooth prediction into a single process. This is adeparture from previous work that required two training phases, one toself-organize a map using the SOM algorithm, and another to learn a smoothapproximation of a function. System performance is illustrated with threeexamples.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009622004201
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 11
    Electronic Resource
    Electronic Resource
    Evolving Multilayer Perceptrons (2000)
    Springer
    Neural processing letters 12 (2000), S. 115-128 
    Details
    ISSN: 1573-773X
    Keywords: evolutionary algorithms ; generalization ; learning ; neural networks ; optimization
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract This paper proposes a new version of a method (G-Prop, genetic backpropagation) that attempts to solve the problem of finding appropriate initial weights and learning parameters for a single hidden layer Multilayer Perceptron (MLP) by combining an evolutionary algorithm (EA) and backpropagation (BP). The EA selects the MLP initial weights, the learning rate and changes the number of neurons in the hidden layer through the application of specific genetic operators, one of which is BP training. The EA works on the initial weights and structure of the MLP, which is then trained using QuickProp; thus G-Prop combines the advantages of the global search performed by the EA over the MLP parameter space and the local search of the BP algorithm. The application of the G-Prop algorithm to several real-world and benchmark problems shows that MLPs evolved using G-Prop are smaller and achieve a higher level of generalization than other perceptron training algorithms, such as QuickPropagation or RPROP, and other evolutive algorithms. It also shows some improvement over previous versions of the algorithm.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009684907680
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 12
    Electronic Resource
    Electronic Resource
    Automated Cellular Modeling and Prediction on a Large Scale (2000)
    Springer
    Artificial intelligence review 14 (2000), S. 485-502 
    Details
    ISSN: 1573-7462
    Keywords: churn prediction ; neural networks ; decision trees
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract We describe CHAMP (CHurn Analysis, Modeling, andPrediction), an automated system for modeling cellularsubscriber churn that is predicting which customerswill discontinue cellular phone service. We describevarious issues related to developing and deployingthis system including automating data access from aremote data warehouse, preprocessing, featureselection, model validation, and optimization toreflect business tradeoffs. Using data from GTE'sdata warehouse for cellular phone customers, CHAMP iscapable of developing churn models customized byregion for over one hundred GTE cellular phone marketstotaling over 5 million customers. Every month churnfactors are identified for each geographic region andmodels are updated to generate churn scores predictingwho is likely to churn in the short term. Learningmethods such as decision trees and genetic algorithmsare used for feature selection and a cascade neuralnetwork is used for predicting churn scores. Inaddition to producing churn scores, CHAMP alsoproduces qualitative results in the form of rules andcomparison of market trends that are disseminatedthrough a web based interface.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1006643109702
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 13
    Electronic Resource
    Electronic Resource
    Intelligent Data Analysis for Protein Disorder Prediction (2000)
    Springer
    Artificial intelligence review 14 (2000), S. 447-484 
    Details
    ISSN: 1573-7462
    Keywords: data mining ; neural networks ; protein structure ; protein disorder prediction ; protein databases
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Although an ordered 3D structure is generally considered to be anecessary pre-condition for protein functionality, there are disorderedcounter examples found to have biological activity. The objectives ofour data mining project are: (1) to generalize from the limitedset of counter examples and then apply this knowledge to large databases of amino acid sequence in order to estimate commonness ofdisordered protein regions in nature, and (2) to determine whether thereare different types of protein disorder. For general disorderestimation, a neural network based predictor was designed and tested ondata built from several public domain data banks through a nontrivialsearch, statistical analysis and data dimensionality reduction. Inaddition, predictors for identification of family-specific disorder weredeveloped by extracting knowledge from databases generated throughmultiple sequence alignments of a known disordered sequence to otherhighly related proteins. Family-specific predictors were also integratedto test quality of general protein disorder identification from suchhybrid prediction systems. Out-of-sample cross validation performance ofseveral predictors was computed first, followed by tests on an unrelateddatabase of proteins with long disordered regions, and the applicationof few selected predictors to two large protein data banks:Nrl_3D, currently containing more than 10,000 protein fragmentsof known 3D structure, and Swiss Protein, having almost 60,000 proteinsequences. The obtained results provide evidence that long disorderedregions are common in nature, with an estimate that 11% of allthe residues in the Swiss Protein data bank belong to disordered regionsof length 40 or greater. The hypothesis that different protein disordertypes exist is supported by high specificity/low sensitivity resultsof two family-specific predictors, by hybrid systems outperforminggeneral models on a two-family test, and by existence of significantgaps in Swiss Protein vs. Nrl_3D disorder frequency estimates forboth families. These findings prompt the need for a revision in thecurrent understanding of protein structure and function, as well as forthe developing of improved disorder predictors that should haveimportant uses in biotechnology applications.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1006678623815
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 14
    Electronic Resource
    Electronic Resource
    Neural Nets Trained by Genetic Algorithms for Collision Avoidance (2000)
    Springer
    Applied intelligence 13 (2000), S. 205-213 
    Details
    ISSN: 1573-7497
    Keywords: air traffic control ; collision avoidance ; neural networks ; genetic algorithms
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract As air traffic keeps increasing, many research programs focus on collision avoidance techniques. For short or medium term avoidance, new headings have to be computed almost on the spot, and feed forward neural nets are susceptible to find solutions in a much shorter amount of time than classical avoidance algorithms (A *, stochastic optimization, etc.) In this article, we show that a neural network can be built with unsupervised learning to compute nearly optimal trajectories to solve two aircraft conflicts with the highest reliability, while computing headings in a few milliseconds.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1026507809196
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 15
    Electronic Resource
    Electronic Resource
    A Novel Self-Creating Neural Network for Learning Vector Quantization (2000)
    Springer
    Neural processing letters 11 (2000), S. 139-151 
    Details
    ISSN: 1573-773X
    Keywords: competitive learning ; neural networks ; local minimum ; self-creating network ; stability-and-plasticity dilemma ; vector quantization
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract This paper presents a novel self-creating neural network scheme which employs two resource counters to record network learning activity. The proposed scheme not only achieves the biologically plausible learning property, but it also harmonizes equi-error and equi-probable criteria. The training process is smooth and incremental: it not only avoids the stability-and-plasticity dilemma, but also overcomes the dead-node problem and the deficiency of local minimum. Comparison studies on learning vector quantization involving stationary and non-stationary, structured and non-structured inputs demonstrate that the proposed scheme outperforms other competitive networks in terms of quantization error, learning speed, and codeword search efficiency.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009626513932
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 16
    Electronic Resource
    Electronic Resource
    A Comparison between the Tikhonov and the Bayesian Approaches to Calculate Regularisation Matrices (2000)
    Springer
    Neural processing letters 11 (2000), S. 185-195 
    Details
    ISSN: 1573-773X
    Keywords: Bayesian inference ; ill-posed problems ; neural networks ; RBF ; regularization techniques ; smoothing functions
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Regularisation is a well-known technique for working with ill-posed and ill-conditioned problems that have been explored in a variety of different areas, including Bayesian inference, functional analysis, optimisation, numerical analysis and connectionist systems. In this paper we present the equivalence between the Bayesian approach to the regularisation theory and the Tikhonov regularisation into the function approximation theory framework, when radial basis functions networks are employed. This equivalence can be used to avoid expensive calculations when regularisation techniques are employed.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009607425536
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 17
    Electronic Resource
    Electronic Resource
    Neural Net Based Hybrid Modeling of the Methanol Synthesis Process (2000)
    Springer
    Neural processing letters 11 (2000), S. 219-228 
    Details
    ISSN: 1573-773X
    Keywords: hybrid modeling ; genetic algorithms ; feature selection ; methanol synthesis ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract A Hybrid modeling approach, combining an analytical model with a radial basis function neural network is introduced in this paper. The modeling procedure is combined with genetic algorithm based feature selection designed to select informative variables from the set of available measurements. By only using informative inputs, the model's generalization ability can be enhanced. The approach proposed is applied to modeling of the liquid–phase methanol synthesis. It is shown that a hybrid modeling approach exploiting available a priori knowledge and experimental data can considerably outperform a purely analytical approach.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009615710515
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 18
    Electronic Resource
    Electronic Resource
    Transfusion Cost Containment for Abdominal Surgery with Neural Networks (2000)
    Springer
    Neural processing letters 11 (2000), S. 229-238 
    Details
    ISSN: 1573-773X
    Keywords: neural networks ; abdominal surgery ; AAA ; transfusion ; cost ; MSBOS
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Typing and crossmatching blood is a significant cost for most hospitals, regardless of whether the blood is actually transfused. Many hospitals have implemented a Maximum Surgical Blood Order Schedule, MSBOS, to control over-ordering of blood units for surgery. The research presented in this article examines the use of neural networks for predicting the quantity of blood required by individual patients undergoing abdominal surgery (e.g. splenectomy). A comparison is made between the neural network predictions at a particular hospital versus the current MSBOS methodology for ordering surgical blood, by using the crossmatch to transfusion ratio. Results from the neural network transfusion predictions for the abdominal aortic aneurysm (AAA) surgery imply that neural networks can significantly improve the transfusion efficiency of hospitals. However, further examination of neural network capabilities for predicting the transfusion needs of patients undergoing other types of abdominal surgeries indicates that for operations other than the AAA, neural networks tend to under-predict the transfusion requirements of ten percent of the patients. Even if not used to limit over-ordering of blood for surgical transfusions, neural networks may be used as an intelligent decision support system to evaluate the current efficiency of hospital transfusion practices and to indicate beneficial changes to current MSBOS values.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009667711423
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 19
    Electronic Resource
    Electronic Resource
    A Minimax Method for Learning Functional Networks (2000)
    Springer
    Neural processing letters 11 (2000), S. 39-49 
    Details
    ISSN: 1573-773X
    Keywords: functional equations ; functional networks ; learning ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract In this paper, a minimax method for learning functional networks is presented. The idea of the method is to minimize themaximum absolute error between predicted and observed values. In addition, the invertible functions appearing in the modelare assumed to be linear convex combinations of invertible functions. This guarantees the invertibilityof the resulting approximations. The learning method leads to a linear programming problem and then: (a) the solution isobtained in a finite number of iterations, and (b) the global optimum is attained. The method is illustrated withseveral examples of applications, including the Hénon and Lozi series. The results show that the method outperforms standard least squares direct methods.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009628031942
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 20
    Electronic Resource
    Electronic Resource
    Neural Network Agents for Learning Semantic Text Classification (2000)
    Springer
    Information retrieval 3 (2000), S. 87-103 
    Details
    ISSN: 1573-7659
    Keywords: neural networks ; news agent ; recurrent plausibility network ; text classification ; machine learning
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract The research project AgNeT develops Agents for Neural Text routing in the internet. Unrestricted potentially faulty text messages arrive at a certain delivery point (e.g. email address or world wide web address). These text messages are scanned and then distributed to one of several expert agents according to a certain task criterium. Possible specific scenarios within this framework include the learning of the routing of publication titles or news titles. In this paper we describe extensive experiments for semantic text routing based on classified library titles and newswire titles. This task is challenging since incoming messages may contain constructions which have not been anticipated. Therefore, the contributions of this research are in learning and generalizing neural architectures for the robust interpretation of potentially noisy unrestricted messages. Neural networks were developed and examined for this topic since they support robustness and learning in noisy unrestricted real-world texts. We describe and compare different sets of experiments. The first set of experiments tests a recurrent neural network for the task of library title classification. Then we describe a larger more difficult newswire classification task from information retrieval. The comparison of the examined models demonstrates that techniques from information retrieval integrated into recurrent plausibility networks performed well even under noise and for different corpora.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009942513170
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 21
    Electronic Resource
    Electronic Resource
    A Population Density Approach That Facilitates Large-Scale Modeling of Neural Networks: Analysis and an Application to Orientation Tuning (2000)
    Springer
    Journal of computational neuroscience 8 (2000), S. 19-50 
    Details
    ISSN: 1573-6873
    Keywords: neural networks ; modeling ; population density ; orientation tuning ; visual cortex
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Medicine , Physics
    Notes: Abstract We explore a computationally efficient method of simulating realistic networks of neurons introduced by Knight, Manin, and Sirovich (1996) in which integrate-and-fire neurons are grouped into large populations of similar neurons. For each population, we form a probability density that represents the distribution of neurons over all possible states. The populations are coupled via stochastic synapses in which the conductance of a neuron is modulated according to the firing rates of its presynaptic populations. The evolution equation for each of these probability densities is a partial differential-integral equation, which we solve numerically. Results obtained for several example networks are tested against conventional computations for groups of individual neurons. We apply this approach to modeling orientation tuning in the visual cortex. Our population density model is based on the recurrent feedback model of a hypercolumn in cat visual cortex of Somers et al. (1995). We simulate the response to oriented flashed bars. As in the Somers model, a weak orientation bias provided by feed-forward lateral geniculate input is transformed by intracortical circuitry into sharper orientation tuning that is independent of stimulus contrast. The population density approach appears to be a viable method for simulating large neural networks. Its computational efficiency overcomes some of the restrictions imposed by computation time in individual neuron simulations, allowing one to build more complex networks and to explore parameter space more easily. The method produces smooth rate functions with one pass of the stimulus and does not require signal averaging. At the same time, this model captures the dynamics of single-neuron activity that are missed in simple firing-rate models.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008912914816
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 22
    Electronic Resource
    Electronic Resource
    Application of bromodeoxyuridine (BrdU)-labelled Escherichia coli strains in studies on their adherence to human endothelial cells (2000)
    Springer
    World journal of microbiology and biotechnology 16 (2000), S. 85-86 
    Details
    ISSN: 1573-0972
    Keywords: Bacterial adherence ; bromodeoxyuridine (BrdU) ; Escherichia coli ; fimbria ; immunomax technique
    Source: Springer Online Journal Archives 1860-2000
    Topics: Biology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: Abstract Fimbriated and fimbria-less strains of Escherichia coli were isolated from urine of pyelonephritis patients, labelled with bromodeoxyuridine and their adhesion to human umbillical vein endothelial cells was studied employing ELISA and immunocytochemistry. No significant differences were noted in adhesion of the two types of strains.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008930315300
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 23
    Electronic Resource
    Electronic Resource
    Representation and Classification of Breath Sounds Recorded in an Intensive Care Setting Using Neural Networks (2000)
    Springer
    Journal of clinical monitoring and computing 16 (2000), S. 95-105 
    Details
    ISSN: 1573-2614
    Keywords: Breath sounds ; respiratory sounds ; intensive care unit ; spectral analysis ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Medicine
    Notes: Abstract Objective.Develop and test methods for representing and classifying breath sounds in an intensive care setting. Methods.Breath sounds were recorded over the bronchial regions of the chest. The breath sounds were represented by their averaged power spectral density, summed into feature vectors across the frequency spectrum from 0 to 800 Hertz. The sounds were segmented by individual breath and each breath was divided into inspiratory and expiratory segments. Sounds were classified as normal or abnormal. Different back-propagation neural network configurations were evaluated. The number of input features, hidden units, and hidden layers were varied.Results.2127 individual breath sounds from the ICU patients and 321breaths from training tapes were obtained. Best overall classification rate for the ICU breath sounds was 73% with 62% sensitivity and 85% specificity. Best overall classification rate for the training tapes was 91% with 87%sensitivity and 95% specificity. Conclusions.Long term monitoring of lung sounds is not feasible unless several barriers can be overcome. Several choices in signal representation and neural network design greatly improved the classification rates of breath sounds. The analysis of transmitted sounds from the trachea to the lung is suggested as an area for future study.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009934112185
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 24
    Electronic Resource
    Electronic Resource
    Non-parametric smoothing of the location model in mixed variable discrimination (2000)
    Springer
    Statistics and computing 10 (2000), S. 289-297 
    Details
    ISSN: 1573-1375
    Keywords: leave-one-out error rates ; linear discriminant functions ; logistic discrimination ; mixed integer programming classification ; neural networks ; pseudo-likelihood ; tree-based classifiers
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mathematics
    Notes: Abstract The location model is a familiar basis for discriminant analysis of mixtures of categorical and continuous variables. Its usual implementation involves second-order smoothing, using multivariate regression for the continuous variables and log-linear models for the categorical variables. In spite of the smoothing, these procedures still require many parameters to be estimated and this in turn restricts the categorical variables to a small number if implementation is to be feasible. In this paper we propose non-parametric smoothing procedures for both parts of the model. The number of parameters to be estimated is dramatically reduced and the range of applicability thereby greatly increased. The methods are illustrated on several data sets, and the performances are compared with a range of other popular discrimination techniques. The proposed method compares very favourably with all its competitors.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008973308264
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 25
    Electronic Resource
    Electronic Resource
    Clinical significance of Verocytotoxin-producing Escherichia coli O157 (2000)
    Springer
    World journal of microbiology and biotechnology 16 (2000), S. 719-724 
    Details
    ISSN: 1573-0972
    Keywords: Escherichia coli ; haemolytic uraemic syndrome ; haemorrhagic colitis ; pathogenicity ; Verocytotoxin ; VTEC
    Source: Springer Online Journal Archives 1860-2000
    Topics: Biology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: Abstract In 1977, Konowalchuk and colleagues (Konowalchuk, J., Speirs, J.I. & Stavric, S. 1977 Infection and Immunity 18, 775–779) were the first to describe Verocytotoxin-producing strains of Escherichia coli or VTEC. The surveillance of infection caused by VTEC demonstrated strains of E. coli belonging to serogroup O157 as the main cause of human infection capable of causing haemorrhagic colitis (HC) and haemolytic uraemic syndrome (HUS). Infection with O157 VTEC results in a range of disease manifestations including abdominal cramps, vomiting and fever. This frequently leads to cases with bloody diarrhoea and HC, and approximately 10% of patients develop HUS. The symptoms of disease caused by VTEC O157 have been well documented and the pathogenic mechanisms expressed by VTEC have been the focus of considerable attention. However, the role of putative pathogenic mechanisms in the pathogenesis of disease is not fully understood. The aim of this review is to consider the clinical aspects of infection with strains of VT-producing E. coli O157 in terms of the putative pathogenic mechanisms expressed by these bacteria.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008928822352
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 26
    Electronic Resource
    Electronic Resource
    Predicting Aflatoxin Contamination in Peanuts: A Genetic Algorithm/Neural Network Approach (2000)
    Springer
    Applied intelligence 12 (2000), S. 183-192 
    Details
    ISSN: 1573-7497
    Keywords: genetic algorithm/neural network hybrid ; genetic algorithms ; neural networks ; genetic learning ; aflatoxin prediction
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Aflatoxin contamination in peanut crops is a problem of significant health and financial importance. Predicting aflatoxin levels prior to crop harvest is useful for minimizing the impact of a contaminated crop and is the goal of our research. Backpropagation neural networks have been used to model problems of this type, however development of networks poses the complex problem of setting values for architectural features and backpropagation parameters. Genetic algorithms have been used in other studies to determine parameters for backpropagation neural networks. This paper describes the development of a genetic algorithm/backpropagation neural network hybrid (GA/BPN) in which a genetic algorithm is used to find architectures and backpropagation parameter values simultaneously for a backpropagation neural network that predicts aflatoxin contamination levels in peanuts based on environmental data. Learning rate, momentum, and number of hidden nodes are the parameters that are set by the genetic algorithm. A three-layer feed-forward network with logistic activation functions is used. Inputs to the network are soil temperature, drought duration, crop age, and accumulated heat units. The project showed that the GA/BPN approach automatically finds highly fit parameter sets for backpropagation neural networks for the aflatoxin problem.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008310906900
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 27
    Electronic Resource
    Electronic Resource
    Variable Hidden Layer Sizing in Elman Recurrent Neuro-Evolution (2000)
    Springer
    Applied intelligence 12 (2000), S. 193-205 
    Details
    ISSN: 1573-7497
    Keywords: Elman recurrent networks ; neural networks ; hidden layer ; genetic algorithm
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract The relationship between the size of the hidden layer in a neural network and performance in a particular domain is currently an open research issue. Often, the number of neurons in the hidden layer is chosen empirically and subsequently fixed for the training of the network. Fixing the size of the hidden layer limits an inherent strength of neural networks—the ability to generalize experiences from one situation to another, to adapt to new situations, and to overcome the “brittleness” often associated with traditional artificial intelligence techniques. This paper proposes an evolutionary algorithm to search for network sizes along with weights and connections between neurons. This research builds upon the neuro-evolution tool SANE, developed by David Moriarty. SANE evolves neurons and networks simultaneously, and is modified in this work in several ways, including varying the hidden layer size, and evolving Elman recurrent neural networks for non-Markovian tasks. These modifications allow the evolution of better performing and more consistent networks, and do so more efficiently and faster. SANE, modified with variable network sizing, learns to play modified casino blackjack and develops a successful card counting strategy. The contributions of this research are up to 8.3% performance increases over fixed hidden layer size models while reducing hidden layer processing time by almost 10%, and a faster, more autonomous approach to the scaling of neuro-evolutionary techniques to solving larger and more difficult problems.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008315023738
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 28
    Electronic Resource
    Electronic Resource
    Real-time Collision-free Path Planning of Robot Manipulators using Neural Network Approaches (2000)
    Springer
    Autonomous robots 9 (2000), S. 27-39 
    Details
    ISSN: 1573-7527
    Keywords: path planning ; real-time planning ; obstacle clearance ; robot manipulators ; nonstationary environment ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract In this paper, a novel neural network approach to real-time collision-free path planning of robot manipulators in a nonstationary environment is proposed, which is based on a biologically inspired neural network model for dynamic trajectory generation of a point mobile robot. The state space of the proposed neural network is the joint space of the robot manipulators, where the dynamics of each neuron is characterized by a shunting equation or an additive equation. The real-time robot path is planned through the varying neural activity landscape that represents the dynamic environment. The proposed model for robot path planning with safety consideration is capable of planning a real-time “comfortable” path without suffering from the “too close” nor “too far” problems. The model algorithm is computationally efficient. The computational complexity is linearly dependent on the neural network size. The effectiveness and efficiency are demonstrated through simulation studies.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008920117364
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 29
    Electronic Resource
    Electronic Resource
    A Gesture Based Interface for Human-Robot Interaction (2000)
    Springer
    Autonomous robots 9 (2000), S. 151-173 
    Details
    ISSN: 1573-7527
    Keywords: gestures ; human robot interaction ; mobile robot navigation ; service robots ; visual template matching ; hidden markov models ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract Service robotics is currently a highly active research area in robotics, with enormous societal potential. Since service robots directly interact with people, finding “natural” and easy-to-use user interfaces is of fundamental importance. While past work has predominately focussed on issues such as navigation and manipulation, relatively few robotic systems are equipped with flexible user interfaces that permit controlling the robot by “natural” means. This paper describes a gesture interface for the control of a mobile robot equipped with a manipulator. The interface uses a camera to track a person and recognize gestures involving arm motion. A fast, adaptive tracking algorithm enables the robot to track and follow a person reliably through office environments with changing lighting conditions. Two alternative methods for gesture recognition are compared: a template based approach and a neural network approach. Both are combined with the Viterbi algorithm for the recognition of gestures defined through arm motion (in addition to static arm poses). Results are reported in the context of an interactive clean-up task, where a person guides the robot to specific locations that need to be cleaned and instructs the robot to pick up trash.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008918401478
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 30
    Electronic Resource
    Electronic Resource
    Identifying Objects in Procedural Programs Using Clustering Neural Networks (2000)
    Springer
    Automated software engineering 7 (2000), S. 239-261 
    Details
    ISSN: 1573-7535
    Keywords: clustering ; objects ; abstract data types ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract This paper presents a general approach for the identification of objects in procedural programs. The approach is based on neural architectures that perform an unsupervised learning of clusters. We describe two such neural architectures, explain how to use them in identifying objects in software systems and briefly describe a prototype tool, which implements the clustering algorithms. With the aid of several examples, we explain how our approach can identify abstract data types as well as groups of routines which reference a common set of data. The clustering results are compared to the results of many other object identification techniques. Finally, several case studies were performed on existing programs to evaluate the object identification approach. Results concerning two representative programs and their generated clusters are discussed.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008718105516
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 31
    Electronic Resource
    Electronic Resource
    Why not Artificial Consciousness or Thought? (1999)
    Springer
    Minds and machines 9 (1999), S. 3-28 
    Details
    ISSN: 1572-8641
    Keywords: physical symbols ; formal programs ; neural networks ; designation ; interpretation ; representation ; semantics ; intensional meaning ; extensional meaning ; causal capacities ; emergence ; levels
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Philosophy
    Notes: Abstract The purpose of this article is to show why consciousness and thought are not manifested in digital computers. Analyzing the rationale for claiming that the formal manipulation of physical symbols in Turing machines would emulate human thought, the article attempts to show why this proved false. This is because the reinterpretation of ‘designation’ and ‘meaning’ to accommodate physical symbol manipulation eliminated their crucial functions in human discourse. Words have denotations and intensional meanings because the brain transforms the physical stimuli received from the microworld into a qualitative, macroscopic representation for consciousness. Lacking this capacity as programmed machines, computers have no representations for their symbols to designate and mean. Unlike human beings in which consciousness and thought, with their inherent content, have emerged because of their organic natures, serial processing computers or parallel distributed processing systems, as programmed electrical machines, lack these causal capacities.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008374714117
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 32
    Electronic Resource
    Electronic Resource
    Introduction: from legal theories to neural networks and fuzzy reasoning (1999)
    Springer
    Artificial intelligence and law 7 (1999), S. 115-128 
    Details
    ISSN: 1572-8382
    Keywords: analogy ; fuzzy logic ; learning ; legal formalism ; neural networks ; vagueness
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Law
    Notes: Abstract Computational approaches to the law have frequently been characterized as being formalistic implementations of the syllogistic model of legal cognition: using insufficient or contradictory data, making analogies, learning through examples and experiences, applying vague and imprecise standards. We argue that, on the contrary, studies on neural networks and fuzzy reasoning show how AI & law research can go beyond syllogism, and, in doing that, can provide substantial contributions to the law.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008371600675
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 33
    Electronic Resource
    Electronic Resource
    Out of their minds: legal theory in neural networks (1999)
    Springer
    Artificial intelligence and law 7 (1999), S. 129-151 
    Details
    ISSN: 1572-8382
    Keywords: connectionism ; legal philosophy ; legal theory ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Law
    Notes: Abstract This paper examines the use of connectionism (neural networks) in modelling legal reasoning. I discuss how the implementations of neural networks have failed to account for legal theoretical perspectives on adjudication. I criticise the use of neural networks in law, not because connectionism is inherently unsuitable in law, but rather because it has been done so poorly to date. The paper reviews a number of legal theories which provide a grounding for the use of neural networks in law. It then examines some implementations undertaken in law and criticises their legal theoretical naïvete. It then presents a lessons from the implementations which researchers must bear in mind if they wish to build neural networks which are justified by legal theories.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008301122056
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 34
    Electronic Resource
    Electronic Resource
    Object Recognition and Selective Handling by a Robot (1999)
    Springer
    Journal of intelligent and robotic systems 25 (1999), S. 121-132 
    Details
    ISSN: 1573-0409
    Keywords: invariant object recognition ; pattern recognition ; neural networks ; flexible manufacturing
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract A small flexible production cell has been built around a selectively compliant articulated robot arm. Moving on a conveyor belt, boxes marked with different labels are presented to the robot in a random order. Using a camera and a vision card, the labels on the boxes are recognized. Each one of the labels can be rotated, translated or scaled. Three different invariant feature extraction methods (signature, invariant moments of Hu and Zernike) are compared. A neural net is used to classify the labels. The task of the SCARA robot is to pick up the moving boxes and to sort them according to their labels.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008088209663
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 35
    Electronic Resource
    Electronic Resource
    Learning Complex Tasks Using a Stepwise Approach (1999)
    Springer
    Journal of intelligent and robotic systems 24 (1999), S. 43-68 
    Details
    ISSN: 1573-0409
    Keywords: learning robots ; system organization ; optimization ; physical equation ; look-ut table ; neural networks ; fuzzy controllers
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract This paper explores a stepwise learning approach based on a system's decomposition into functional subsystems. Two case studies are examined: a visually guided robot that learns to track a maneuvering object, and a robot that learns to use the information from a force sensor in order to put a peg into a hole. These two applications show the features and advantages of the proposed approach: i) the subsystems naturally arise as functional components of the hardware and software; ii) these subsystems are building blocks of the robot behavior and can be combined in several ways for performing various tasks; iii) this decomposition makes it easier to check the performances and detect the cause of a malfunction; iv) only those subsystems for which a satisfactory solution is not available need to be learned; v) the strategy proposed for coordinating the optimization of all subsystems ensures an improvement at the task-level; vi) the overall system's behavior is significantly improved by the stepwise learning approach.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008058131402
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 36
    Electronic Resource
    Electronic Resource
    Stable Neuro-Adaptive Control for Robots with the Upper Bound Estimation on the Neural Approximation Errors (1999)
    Springer
    Journal of intelligent and robotic systems 26 (1999), S. 91-100 
    Details
    ISSN: 1573-0409
    Keywords: robots ; neural networks ; adaptiveness ; stability ; approximation
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract An indirect adaptive control approach is developed in this paper for robots with unknown nonlinear dynamics using neural networks (NNs). A key property of the proposed approach is that the actual joint angle values in the control law are replaced by the desired joint angles, angle velocities and accelerators, and the bound on the NN reconstruction errors is assumed to be unknown. Main theoretical results for designing such a neuro-controller are given, and the control performance of the proposed controller is verified with simulation studies.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008195720685
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 37
    Electronic Resource
    Electronic Resource
    Genetic Tuning of PID Controllers Using a Neural Network Model: A Seesaw Example (1999)
    Springer
    Journal of intelligent and robotic systems 25 (1999), S. 43-59 
    Details
    ISSN: 1573-0409
    Keywords: PID control ; GAs ; neural networks ; multivariable systems
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract When genetic algorithms (GAs) are applied for PID parameter tuning, since the PID parameters are adjusted almost randomly, it is possible that the plant will be damaged due to abrupt changes in PID parameters. To solve this problem, a neural network will be used to model the plant and the genetic tuning procedure will be performed on the neural network instead of the plant. After determining the PID parameters in this off-line manner, these gains are then applied to the plant for on-line control. Moreover, considering that the neural network model may not be accurate enough, a method is also proposed for on-line fine-tuning of PID parameters. To show the validity of the proposed method, a seesaw system that has one input and two outputs will be used for experimental evaluation
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008077610571
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 38
    Electronic Resource
    Electronic Resource
    An Introduction to Variational Methods for Graphical Models (1999)
    Springer
    Machine learning 37 (1999), S. 183-233 
    Details
    ISSN: 0885-6125
    Keywords: graphical models ; Bayesian networks ; belief networks ; probabilistic inference ; approximate inference ; variational methods ; mean field methods ; hidden Markov models ; Boltzmann machines ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract This paper presents a tutorial introduction to the use of variational methods for inference and learning in graphical models (Bayesian networks and Markov random fields). We present a number of examples of graphical models, including the QMR-DT database, the sigmoid belief network, the Boltzmann machine, and several variants of hidden Markov models, in which it is infeasible to run exact inference algorithms. We then introduce variational methods, which exploit laws of large numbers to transform the original graphical model into a simplified graphical model in which inference is efficient. Inference in the simpified model provides bounds on probabilities of interest in the original model. We describe a general framework for generating variational transformations based on convex duality. Finally we return to the examples and demonstrate how variational algorithms can be formulated in each case.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1007665907178
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 39
    Electronic Resource
    Electronic Resource
    On the Sample Complexity for Nonoverlapping Neural Networks (1999)
    Springer
    Machine learning 37 (1999), S. 131-141 
    Details
    ISSN: 0885-6125
    Keywords: neural networks ; read-once formulas ; threshold gates ; sigmoidal gates ; PAC learning ; Vapnik-Chervonenkis dimension
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract A neural network is said to be nonoverlapping if there is at most one edge outgoing from each node. We investigate the number of examples that a learning algorithm needs when using nonoverlapping neural networks as hypotheses. We derive bounds for this sample complexity in terms of the Vapnik-Chervonenkis dimension. In particular, we consider networks consisting of threshold, sigmoidal and linear gates. We show that the class of nonoverlapping threshold networks and the class of nonoverlapping sigmoidal networks on n inputs both have Vapnik-Chervonenkis dimension Ω(nlog n). This bound is asymptotically tight for the class of nonoverlapping threshold networks. We also present an upper bound for this class where the constants involved are considerably smaller than in a previous calculation. Finally, we argue that the Vapnik-Chervonenkis dimension of nonoverlapping threshold or sigmoidal networks cannot become larger by allowing the nodes to compute linear functions. This sheds some light on a recent result that exhibited neural networks with quadratic Vapnik-Chervonenkis dimension.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1007609822199
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 40
    Electronic Resource
    Electronic Resource
    Neural Networks and Structured Knowledge: Knowledge Representation and Reasoning (1999)
    Springer
    Applied intelligence 11 (1999), S. 5-13 
    Details
    ISSN: 1573-7497
    Keywords: neural networks ; knowledge representation ; structured knowledge reasoning ; connectionism ; symbol processing ; hybrid systems
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract This collection of articles is the first of two parts of a special issue on “Neural Networks and Structured Knowledge.” The contributions to the first part shed some light on the issues of knowledge representation and reasoning with neural networks. Their scope ranges from formal models for mapping discrete structures like graphs or logical formulae onto different types of neural networks, to the construction of practical systems for various types of reasoning. In the second part to follow, the emphasis will be on the extraction of knowledge from neural networks, and on applications of neural networks and structured knowledge to practical tasks.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008327412259
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 41
    Electronic Resource
    Electronic Resource
    Comparing Structures Using a Hopfield-Style Neural Network (1999)
    Springer
    Applied intelligence 11 (1999), S. 15-30 
    Details
    ISSN: 1573-7497
    Keywords: neural networks ; structured objects ; machine learning ; classification ; similarity ; nearest neighbor
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Labeled graphs are an appropriate and popular representation of structured objects in many domains. If the labels describe the properties of real world objects and their relations, finding the best match between two graphs turns out to be the weakly defined, NP-complete task of establishing a mapping between them that maps similar parts onto each other preserving as much as possible of their overall structural correspondence. In this paper, former approaches of structural matching and constraint relaxation by spreading activation in neural networks and the method of solving optimization tasks using Hopfield-style nets are combined. The approximate matching task is reformulated as the minimization of a quadratic energy function. The design of the approach enables the user to change the parameters and the dynamics of the net so that knowledge about matching preferences is included easily and transparently. In the last section, some examples demonstrate the successful application of this approach in classification and learning in the domain of organic chemistry.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008320413168
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 42
    Electronic Resource
    Electronic Resource
    Exploiting Hierarchy in Text Categorization (1999)
    Springer
    Information retrieval 1 (1999), S. 193-216 
    Details
    ISSN: 1573-7659
    Keywords: information retrieval ; text mining ; topic spotting ; text categorization ; knowledge management ; problem decomposition ; machine learning ; neural networks ; probabilistic models ; hierarchical models ; performance evaluation
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract With the recent dramatic increase in electronic access to documents, text categorization—the task of assigning topics to a given document—has moved to the center of the information sciences and knowledge management. This article uses the structure that is present in the semantic space of topics in order to improve performance in text categorization: according to their meaning, topics can be grouped together into “meta-topics”, e.g., gold, silver, and copper are all metals. The proposed architecture matches the hierarchical structure of the topic space, as opposed to a flat model that ignores the structure. It accommodates both single and multiple topic assignments for each document. Its probabilistic interpretation allows its predictions to be combined in a principled way with information from other sources. The first level of the architecture predicts the probabilities of the meta-topic groups. This allows the individual models for each topic on the second level to focus on finer discriminations within the group. Evaluating the performance of a two-level implementation on the Reuters-22173 testbed of newswire articles shows the most significant improvement for rare classes.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009983522080
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 43
    Electronic Resource
    Electronic Resource
    Medical Data Mining on the Internet: Research on a Cancer Information System (1999)
    Springer
    Artificial intelligence review 13 (1999), S. 437-466 
    Details
    ISSN: 1573-7462
    Keywords: CancerLit ; concept spaces ; data mining ; Hopfield net ; information retrieval ; Kohonen net ; medical knowledge ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract This paper discusses several data mining algorithms and techniques thatwe have developed at the University of Arizona Artificial Intelligence Lab.We have implemented these algorithms and techniques into severalprototypes, one of which focuses on medical information developed incooperation with the National Cancer Institute (NCI) and the University ofIllinois at Urbana-Champaign. We propose an architecture for medicalknowledge information systems that will permit data mining across severalmedical information sources and discuss a suite of data mining tools that weare developing to assist NCI in improving public access to and use of theirexisting vast cancer information collections.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1006548623067
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 44
    Electronic Resource
    Electronic Resource
    A Hybrid Architecture for Situated Learning of Reactive Sequential Decision Making (1999)
    Springer
    Applied intelligence 11 (1999), S. 109-127 
    Details
    ISSN: 1573-7497
    Keywords: hybrid models ; sequential decision making ; neural networks ; reinforcement learning ; cognitive modeling
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract In developing autonomous agents, one usually emphasizes only (situated) procedural knowledge, ignoring more explicit declarative knowledge. On the other hand, in developing symbolic reasoning models, one usually emphasizes only declarative knowledge, ignoring procedural knowledge. In contrast, we have developed a learning model CLARION, which is a hybrid connectionist model consisting of both localist and distributed representations, based on the two-level approach proposed in [40]. CLARION learns and utilizes both procedural and declarative knowledge, tapping into the synergy of the two types of processes, and enables an agent to learn in situated contexts and generalize resulting knowledge to different scenarios. It unifies connectionist, reinforcement, and symbolic learning in a synergistic way, to perform on-line, bottom-up learning. This summary paper presents one version of the architecture and some results of the experiments.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008332731824
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 45
    Electronic Resource
    Electronic Resource
    A Neural Network Diagnosis Approach for Analog Circuits (1999)
    Springer
    Applied intelligence 11 (1999), S. 169-186 
    Details
    ISSN: 1573-7497
    Keywords: neural networks ; multiple fault diagnosis ; analog circuits
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract This paper presents a neural network system for the diagnosis of analog circuits and shows how the performance of such a system can be affected by the choice of different techniques used by its submodules. In particular we discuss the influence of feature extraction techniques such as Fourier Transforms, Wavelets and Principal Component Analysis. The system uses several different power supplies and as many neural networks “in parallel”. Two different algorithms that can be used to combine the candidate sets produced by each network are also presented. The system is capable of diagnosing multiple faults even if trained on single ones.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008376430315
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 46
    Electronic Resource
    Electronic Resource
    A New Symmetric Probabilistic Encryption Scheme Based on Chaotic Attractors of Neural Networks (1999)
    Springer
    Applied intelligence 10 (1999), S. 71-84 
    Details
    ISSN: 1573-7497
    Keywords: encryption ; chaotic attractors ; neural networks ; symmetric-key
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract A new probabilistic symmetric-key encryption scheme based on chaotic-classified properties of Hopfield neural networks is described. In an overstoraged Hopfield Neural Network (OHNN) the phenomenon of chaotic-attractors is well documented and messages in the attraction domain of an attractor are unpredictably related to each other. By performing permutation operations on the neural synaptic matrix, several interesting chaotic-classified properties of OHNN were found and these were exploited in developing a new cryptography technique. By keeping the permutation operation of the neural synaptic matrix as the secret key, we introduce a new probabilistic encryption scheme for a symmetric-key cryptosystem. Security and encryption efficiency of the new scheme are discussed.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008337631906
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 47
    Electronic Resource
    Electronic Resource
    Fusion Via a Linear Combination of Scores (1999)
    Springer
    Information retrieval 1 (1999), S. 151-173 
    Details
    ISSN: 1573-7659
    Keywords: linear combination ; fusion ; neural networks ; routing ; performance evaluation
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract We present a thorough analysis of the capabilities of the linear combination (LC) model for fusion of information retrieval systems. The LC model combines the results lists of multiple IR systems by scoring each document using a weighted sum of the scores from each of the component systems. We first present both empirical and analytical justification for the hypotheses that such a model should only be used when the systems involved have high performance, a large overlap of relevant documents, and a small overlap of nonrelevant documents. The empirical approach allows us to very accurately predict the performance of a combined system. We also derive a formula for a theoretically optimal weighting scheme for combining 2 systems. We introduce d—the difference between the average score on relevant documents and the average score on nonrelevant documents—as a performance measure which not only allows mathematical reasoning about system performance, but also allows the selection of weights which generalize well to new documents. We describe a number of experiments involving large numbers of different IR systems which support these findings.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009980820262
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 48
    Electronic Resource
    Electronic Resource
    Neural Networks in Non-Euclidean Spaces (1999)
    Springer
    Neural processing letters 10 (1999), S. 201-210 
    Details
    ISSN: 1573-773X
    Keywords: neural networks ; learning ; minimal distance methods ; similarity-based methods ; machine learning ; interpretation of neural functions ; classification
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Multilayer Perceptrons (MLPs) use scalar products to compute weighted activation of neurons providing decision borders using combinations of soft hyperplanes. The weighted fun-in activation function may be replaced by a distance function between the inputs and the weights, offering a natural generalization of the standard MLP model. Non-Euclidean distance functions may also be introduced by normalization of the input vectors into an extended feature space. Both approaches influence the shapes of decision borders dramatically. An illustrative example showing these changes is provided.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1018728407584
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 49
    Electronic Resource
    Electronic Resource
    A New Relaxation Procedure in the Hopfield Network for Solving Optimization Problems (1999)
    Springer
    Neural processing letters 10 (1999), S. 211-222 
    Details
    ISSN: 1573-773X
    Keywords: constraint satisfaction ; Hopfield network ; neural networks ; optimization ; relaxation procedure
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract When solving an optimization problem with a Hopfield network, a solution is obtained after the network is relaxed to an equilibrium state. The relaxation process is an important step in achieving a solution. In this paper, a new procedure for the relaxation process is proposed. In the new procedure, the amplified signal received by a neuron from other neurons is treated as the target value for its activation (output) value. The activation of a neuron is updated directly based on the difference between its current activation and the received target value, without using the updating of the input value as an intermediate step. A relaxation rate is applied to control the updating scale for a smooth relaxation process. The new procedure is evaluated and compared with the original procedure in the Hopfield network through simulations based on 200 randomly generated instances of the 10-city traveling salesman problem. The new procedure reduces the error rate by 34.6% and increases the percentage of valid tours by 194.6% as compared with the original procedure.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1018780424422
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 50
    Electronic Resource
    Electronic Resource
    Performance Analysis of Neural Network Detectors by Importance Sampling Techniques (1999)
    Springer
    Neural processing letters 9 (1999), S. 257-269 
    Details
    ISSN: 1573-773X
    Keywords: detectors ; detection and false alarm probabilities ; importance sampling techniques ; Monte Carlo simulations ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Often, Neural Networks are involved in binary detectors of communication, radar or sonar systems. The design phase of a neural network detector usually requires the application of Monte Carlo trials in order to estimate some performance parameters. The classical Monte Carlo method is suitable to estimate high event probabilities (higher than 0.01), but not suitable to estimate very low event probabilities (say, 10−5 or less). For estimations of very low false alarm probabilities (or error probabilities), a modified Monte Carlo technique, the so-called Importance Sampling (IS) technique, is considered in this paper; some topics are developed, such as optimal and suboptimal IS probability density functions (biasing density functions), control parameters and new algorithms for the minimization of the estimator error. The main novelty of this paper is the application of an efficient IS technique on neural networks, drastically reducing the number of patterns required for testing events of low probability. As a practical application, the IS technique is applied to a neural detector on a radar (or sonar) system.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1018612207016
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 51
    Electronic Resource
    Electronic Resource
    A Neural-Network-Based Approach to Detecting Hyperellipsoidal Shells (1999)
    Springer
    Neural processing letters 9 (1999), S. 279-292 
    Details
    ISSN: 1573-773X
    Keywords: cluster analysis ; neural networks ; shell detection
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract This paper presents a novel class of neural networks which can be trained in an unsupervised manner to detect a mixture of hyperellipsoidal shells and/or segments of hyperellipsoidal shells. This approach is computationally and implementationally simpler than other clustering algorithms that have been suggested for this purpose. Experimental results on several data sets are presented.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1018676508833
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 52
    Electronic Resource
    Electronic Resource
    A Multilayer Perceptrons Model for the Stability of a Bipedal Robot (1999)
    Springer
    Neural processing letters 9 (1999), S. 221-227 
    Details
    ISSN: 1573-773X
    Keywords: dynamical equilibrium ; walking robots ; neural networks ; Levenberg-Marquardt's rules
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract A neural network model is proposed as a means of controlling the dynamical equilibrium of a walking bipedal robot. As a criterion to determine the stability of such a robot in relation with the organization of the sensorimotor system, we have been making use of the ZMP (Zero Momentum Point). Simulations are used to check the convergence of the algorithm. In the generalization phase, it is shown that the neural network has the ability to stabilise the robot for motions which have not previously been learned. An extended model is proposed, which seeks to closely inspect the physiology of the cerebellar cortex.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1018631315677
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 53
    Electronic Resource
    Electronic Resource
    Kinetic characterization in batch and continuous culture of Escherichia coli mutants affected in phosphoenolpyruvate metabolism: differences in acetic acid production (1999)
    Springer
    World journal of microbiology and biotechnology 15 (1999), S. 587-592 
    Details
    ISSN: 1573-0972
    Keywords: Acetic acid production ; carbon metabolism ; continuous culture ; Escherichia coli ; metabolic engineering
    Source: Springer Online Journal Archives 1860-2000
    Topics: Biology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: Abstract The growth kinetics of an Escherichia coli wild type strain and two derivative mutants were examined in batch cultures and in glucose-limited chemostats. One mutant (PB12) had an inactive phosphotranferase transport system and the other (PB25) had interrupted pykA and pykF genes that code for the two pyruvate kinase isoenzymes. In both batch and continuous culture, important differences in acetic acid accumulation and other metabolic activities were found. Compared to the wild type strain, we observed a reduction in acetic acid accumulation of 25 and 80% in PB25 and PB12 strains respectively, in batch culture. Continuous culture experiments revealed that compared to the other two strains, PB25 accumulated less acetic acid as a function of dilution rate. In continuous cultures, oxidoreductase metabolic activities were substantially affected in the two mutant strains. These changes in turn were reflected in different levels of biomass and CO2 production, and in oxygen consumption.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008934810150
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 54
    Electronic Resource
    Electronic Resource
    Improved stability and expression of a recombinant shuttle plasmid in Escherichia coli during fedbatch cultivation (1999)
    Springer
    World journal of microbiology and biotechnology 15 (1999), S. 65-71 
    Details
    ISSN: 1573-0972
    Keywords: Escherichia coli ; fedbatch cultivation ; growth rate ; high cell density ; plasmid stability
    Source: Springer Online Journal Archives 1860-2000
    Topics: Biology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: Abstract The effect of higher cell densities on the expression and segregational stability of a recombinant E. coli- B. subtilisshuttle plasmid coding for carboxymethylcellulase (CMCase) activity, was studied in E. coli DH5α. Of the various feeding policies adopted for maximal expression and stability, exponential feeding resulted in the highest biomass of 15g dry cell weight (DCW) l−1 and plasmid stability of 45%. A CMCase activity of 11400 Uml−1 was achieved as compared to 230 Uml−1 during batch cultivation. In the case of other feeding strategies viz., constant feeding, linear feeding or intermittent feeding, the plasmid stability varied between 20% to 60%. Biomass achieved ranged from 5.0 g DCW l−1 to 9.0 g DCW l−1 and enzyme activities were between 2550 Uml−1 and 6000 Uml−1.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008870528336
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 55
    Electronic Resource
    Electronic Resource
    Secretion to the growth medium of an α-amylase by Escherichia coli clones carrying a Bacillus laterosporus gene (1999)
    Springer
    World journal of microbiology and biotechnology 15 (1999), S. 475-480 
    Details
    ISSN: 1573-0972
    Keywords: α-Amylase ; Bacillus laterosporus ; cloning ; Escherichia coli ; secretion
    Source: Springer Online Journal Archives 1860-2000
    Topics: Biology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: Abstract α-Amylase gene from Bacillus laterosporus P3 was cloned and expressed in Escherichia coli HB101 and DH5α. Up to 92% of the cloned gene product was secreted into the medium by the recombinant E. coli. The recombinant crude enzyme showed improved functionality in terms of activity at a wider pH range and at higher temperature, as compared to the crude enzyme from the donor strain. The improved functionality of the cloned enzyme was due to the absence of a contaminating protease which was co-produced in the donor strain. Sub-cloning of the α-amylase gene using the promoter-probe vector, pKT240 in E. coli DH5α indicated the presence of a promoter of B. laterosporus P3 in the cloned fragment.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008996509667
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 56
    Electronic Resource
    Electronic Resource
    Influence of amylose, amylopectin and pullulan on β-glucuronidase activity of starch-degrading Escherichia coli (1999)
    Springer
    World journal of microbiology and biotechnology 15 (1999), S. 497-499 
    Details
    ISSN: 1573-0972
    Keywords: Amylose ; amylopectin ; Escherichia coli ; β-glucuronidase ; pullulan ; starch
    Source: Springer Online Journal Archives 1860-2000
    Topics: Biology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: Abstract Synthesis of β-glucuronidase in starch-degrading Escherichia coli (S1) was induced by amylose, amylopectin and pullulan supplied in mineral medium as the sole carbon source (1%, w/v). The maximum activity occurred after 4 days when cultures reached the stationary phase of growth, but induction was also evident during log-phase. The effects obtained with amylose, amylopectin and pullulan were higher than that obtained with maize starch.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008992405277
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 57
    Electronic Resource
    Electronic Resource
    Learning of Sensor-Based Arm Motions while Executing High-Level Descriptions of Tasks (1999)
    Springer
    Autonomous robots 7 (1999), S. 57-75 
    Details
    ISSN: 1573-7527
    Keywords: sensor-based manipulators ; multi-goal reaching tasks ; reinforcement learning ; neural networks ; differential inverse kinematics
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract Our work focuses on making an autonomous robot manipulator learn suitable collision-free motions from local sensory data while executing high-level descriptions of tasks. The robot arm must reach a sequence of targets where it undertakes some manipulation. The robot manipulator has a sonar sensing skin covering its links to perceive the obstacles in its surroundings. We use reinforcement learning for that purpose, and the neural controller acquires appropriate reaction strategies in acceptable time provided it has some a priori knowledge. This knowledge is specified in two main ways: an appropriate codification of the signals of the neural controller—inputs, outputs and reinforcement—and decomposition of the learning task. The codification facilitates the generalization capabilities of the network as it takes advantage of inherent symmetries and is quite goal-independent. On the other hand, the task of reaching a certain goal position is decomposed into two sequential subtasks: negotiate obstacles and move to goal. Experimental results show that the controller achieves a good performance incrementally in a reasonable time and exhibits high tolerance to failing sensors.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008969830273
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 58
    Electronic Resource
    Electronic Resource
    Robust Backstepping Control of Robotic Systems Using Neural Networks (1998)
    Springer
    Journal of intelligent and robotic systems 23 (1998), S. 105-128 
    Details
    ISSN: 1573-0409
    Keywords: neural networks ; robust control ; back stepping control ; adaptive control
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract Neural network (NN) controllers for the robust back stepping control of robotic systems in both continuous and discrete-time are presented. Control action is employed to achieve tracking performance for unknown nonlinear system. Tuning methods are derived for the NN based on delta rule. Novel weight tuning algorithms for the NN are obtained that are similar to ε-modification in the case of continuous-time adaptive control. Uniform ultimate boundedness of the tracking error and the weight estimates are presented without using the persistency of excitation (PE) condition. Certainty equivalence is not used and regression matrix is not computed. No learning phase is needed for the NN and initialization of the network weights is straightforward. Simulation results justify the theoretical conclusions.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008052206600
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 59
    Electronic Resource
    Electronic Resource
    A Neural Approach for the Control of Piezoelectric Micromanipulation Robots (1998)
    Springer
    Journal of intelligent and robotic systems 22 (1998), S. 351-374 
    Details
    ISSN: 1573-0409
    Keywords: micromanipulation station ; autonomous robots ; microrobots ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract Micromanipulation has become an issue of primary importance in industry and biomedicine, since human manual capabilities are restricted to certain tolerances. The manipulation of biological cells or the assembly of a complete microsystem composed of different microcomponents are examples of the application of piezoelectric-driven microrobots. An automated microrobot-based micromanipulation desktop-station is developed by an interdisciplinary group at the University of Karlsruhe. The process of assembly takes place in the field of view of a light optical microscope. This paper focuses on motion control problems of the microrobots. The ability of an intelligent microsystem to adapt itself to the process requirements is of great importance, especially for assembly robots. The microrobots must be able to operate in a partially defined environment and to ensure reasonable behaviour in unpredicted situations. A neural control concept based on a reference model approach is proposed as a solution. It is shown, that the neural controller is able to learn the desired behaviour. It considerably outperforms an analytically designed linear controller. This is demonstrated both in simulation and in the real environment.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008006308260
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 60
    Electronic Resource
    Electronic Resource
    Self-Localisation in the ‘Senario’ Autonomous Wheelchair (1998)
    Springer
    Journal of intelligent and robotic systems 22 (1998), S. 255-267 
    Details
    ISSN: 1573-0409
    Keywords: localisation ; neural networks ; stochastic diffusion
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract This paper introduces the Focused Stochastic Diffusion Network as a novel method of self-localisation for an autonomous wheelchair in a complex, busy environment. The space of possible positions is explored in parallel by a set of cells searching in a competitive co-operative manner for the most likely position of the wheelchair in its environment. Experimental results from the SENARIO autonomous wheelchair project indicate the technique is practical and robust.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008033229660
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 61
    Electronic Resource
    Electronic Resource
    Use of Autoassociative Neural Networks for Signal Validation (1998)
    Springer
    Journal of intelligent and robotic systems 21 (1998), S. 143-154 
    Details
    ISSN: 1573-0409
    Keywords: neural networks ; sensor calibration ; fault detection and isolation
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract Recently, the use of Autoassociative Neural Networks (AANNs) to perform on-line calibration monitoring of process sensors has been shown to not only be feasible, but practical as well. This paper summarizes the results of applying AANNs to instrument surveillance and calibration monitoring at Florida Power Corporation's Crystal River #3 Nuclear Power Plant and at the Oak Ridge National Laboratory High Flux Isotope Reactor. In both cases sensor drifts are detectable at a nominal level of 0.5% instrument's full scale range. This paper will discuss the selection of a five layer neural network architecture, a robust training paradigm, the input selection criteria, and a retuning algorithm.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1007981322574
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 62
    Electronic Resource
    Electronic Resource
    Synchronization of Multivariate Captors with an Autoadaptive Neural Method (1998)
    Springer
    Journal of intelligent and robotic systems 21 (1998), S. 155-165 
    Details
    ISSN: 1573-0409
    Keywords: neural networks ; synchronization of signals ; time series
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract Before any multivariate analysis scheme (using typicaly simultaneous measurements) it is useful to readjust in time each measurement so that each one refer to the same element of the model. This problem arises frequently in the modelization of an industrial process. It is sometimes possible to propose a dynamic model after a microscopic study of displacements of matter. However such a study is very complex and cannot be conceived by a machine analysis of the data. In this article we present a practical self-adapting methodology which automates the synchronization of captors. This method use a recurrent neural network for the self auto-adaptivity of the synchronization. This network is model and tune automaticaly by an initialization process based on the local stationary phenomena appearing in measurements.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1007937606644
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 63
    Electronic Resource
    Electronic Resource
    Path Planning for Robots by Stochastic Optimization Methods (1998)
    Springer
    Journal of intelligent and robotic systems 22 (1998), S. 117-127 
    Details
    ISSN: 1573-0409
    Keywords: path planning for robots ; stochastic uncertainty ; real-time computation ; B-splines ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract The problem of adaptive trajectory planning for robots under stochastic uncertainty is considered, where new information about the robots and their environment is presented on-line. Solving the problem numerically by means of spline approximation and by applying the method of neural networks, the optimal control can be calculated in real-time. Some numerical results are presented.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1007976516339
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 64
    Electronic Resource
    Electronic Resource
    Prequential and Cross-Validated Regression Estimation (1998)
    Springer
    Machine learning 33 (1998), S. 5-39 
    Details
    ISSN: 0885-6125
    Keywords: regression estimation ; prequential model selection ; cross-validation ; neural networks ; rates of convergence ; mixture regression ; integrated mean-squared error ; time-averaged expected prediction error
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Prequential model selection and delete-one cross-validation are data-driven methodologies for choosing between rival models on the basis of their predictive abilities. For a given set of observations, the predictive ability of a model is measured by the model's accumulated prediction error and by the model's average-out-of-sample prediction error, respectively, for prequential model selection and for cross-validation. In this paper, given i.i.d. observations, we propose nonparametric regression estimators—based on neural networks—that select the number of “hidden units” (or “neurons”) using either prequential model selection or delete-one cross-validation. As our main contributions: (i) we establish rates of convergence for the integrated mean-squared errors in estimating the regression function using “off-line” or “batch” versions of the proposed estimators and (ii) we establish rates of convergence for the time-averaged expected prediction errors in using “on-line” versions of the proposed estimators. We also present computer simulations (i) empirically validating the proposed estimators and (ii) empirically comparing the proposed estimators with certain novel prequential and cross-validated “mixture” regression estimators.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1007577530334
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 65
    Electronic Resource
    Electronic Resource
    Statistical Mechanics of Online Learning of Drifting Concepts: A Variational Approach (1998)
    Springer
    Machine learning 32 (1998), S. 179-201 
    Details
    ISSN: 0885-6125
    Keywords: neural networks ; concept learning ; online algorithms ; variational optimization
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract We review the application of statistical mechanics methods to the study of online learning of a drifting concept in the limit of large systems. The model where a feed-forward network learns from examples generated by a time dependent teacher of the same architecture is analyzed. The best possible generalization ability is determined exactly, through the use of a variational method. The constructive variational method also suggests a learning algorithm. It depends, however, on some unavailable quantities, such as the present performance of the student. The construction of estimators for these quantities permits the implementation of a very effective, highly adaptive algorithm. Several other algorithms are also studied for comparison with the optimal bound and the adaptive algorithm, for different types of time evolution of the rule.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1007428731714
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 66
    Electronic Resource
    Electronic Resource
    Training a Vision Guided Mobile Robot (1998)
    Springer
    Machine learning 31 (1998), S. 201-222 
    Details
    ISSN: 0885-6125
    Keywords: mobile robots ; neural networks ; machine vision ; robot learning
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract This paper presents the design, implementation and evaluation of a trainable vision guided mobile robot. The robot, CORGI, has a CCD camera as its only sensor which it is trained to use for a variety of tasks. The techniques used for train ing and the choice of natural light vision as the primary sensor makes the methodology immediately applicable to tasks such as trash collection or fruit picking. For example, the robot is readily trained to perform a ball finding task which involves avoiding obstacles and aligning with tennis balls. The robot is able to move at speeds up to 0.8 ms-1 while performing this task, and has never had a collision in the trained environment. It can process video and update the actuators at 11 Hz using a single $20 microprocessor to perform all computation. Further results are shown to evaluate the system for generalization across unseen domains, fault tolerance and dynamic environments.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1007405111315
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 67
    Electronic Resource
    Electronic Resource
    Rapid Concept Learning for Mobile Robots (1998)
    Springer
    Machine learning 31 (1998), S. 7-27 
    Details
    ISSN: 0885-6125
    Keywords: robot learning ; concept learning ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Concept learning in robotics is an extremely challenging problem: sensory data is often high-dimensional, and noisy due to specularities and other irregularities. In this paper, we investigate two general strategies to speed up learning, based on spatial decomposition of the sensory representation, and simultaneous learning of multiple classes using a shared structure. We study two concept learning scenarios: a hallway navigation problem, where the robot has to induce features such as “opening” or “wall”. The second task is recycling, where the robot has to learn to recognize objects, such as a “trash can”. We use a common underlying function approximator in both studies in the form of a feedforward neural network, with several hundred input units and multiple output units. Despite the high degree of freedom afforded by such an approximator, we show the two strategies provide sufficient bias to achieve rapid learning. We provide detailed experimental studies on an actual mobile robot called PAVLOV to illustrate the effectiveness of this approach.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1007432422702
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 68
    Electronic Resource
    Electronic Resource
    Color Computer Vision and Artificial Neural Networks for the Detection of Defects in Poultry Eggs (1998)
    Springer
    Artificial intelligence review 12 (1998), S. 163-176 
    Details
    ISSN: 1573-7462
    Keywords: color computer vision ; neural networks ; machine vision ; egg grading ; blood spots ; dirt stains ; cracks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract A blood spot detection neural network was trained, tested, and evaluated entirely on eggs with blood spots and grade A eggs. The neural network could accurately distinguish between grade A eggs and blood spot eggs. However, when eggs with other defects were included in the sample, the accuracy of the neural network was reduced. The accuracy was also reduced when evaluating eggs from other poultry houses. To minimize these sensitivities, eggs with cracks and dirt stains were included in the training data as examples of eggs without blood spots. The training data also combined eggs from different sources. Similar inaccuracies were observed in neural networks for crack detection and dirt stain detection. New neural networks were developed for these defects using the method applied for the blood spot neural network development. The neural network model for blood spot detection had an average accuracy of 92.8%. The neural network model for dirt stained eggs had an average accuracy of 85.0%. The average accuracy of the crack detection neural network was 87.8%. These accuracy levels were sufficient to produce graded samples that would exceed the USDA requirements.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1006509010816
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 69
    Electronic Resource
    Electronic Resource
    A Spurious Equilibria-free Learning Algorithm for the Blind Separation of Non-zoer Skewness Signals (1998)
    Springer
    Neural processing letters 7 (1998), S. 61-68 
    Details
    ISSN: 1573-773X
    Keywords: blind source separation ; higher-order statistics ; neural networks ; unsupervised learning
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract We present a new learning algorithm for the blind separation of independent source signals having non-zero skewness (the 3rd-order cumulant) (the source signals have non-symmetric probability distribution.), from their linear mixtures. It is shown that for a class of source signals whose probability distribution functions is not symmetric, a simple adaptive learning algorithm using quadratic function (f(x)=x2) is very efficient for blind source separation task. It is proved that all stable equilibria of the proposed learning algorithm are desirable solutions. Extensive computer simulation experiments confirmed the validity of the proposed algorithm.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009688827236
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 70
    Electronic Resource
    Electronic Resource
    Extraction of Logical Rules from Neural Networks (1998)
    Springer
    Neural processing letters 7 (1998), S. 211-219 
    Details
    ISSN: 1573-773X
    Keywords: backpropagation ; feature selection ; logical rule extraction ; MLP ; neural networks ; probability density estimation
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Three neural-based methods for extraction of logical rules from data are presented. These methods facilitate conversion of graded response neural networks into networks performing logical functions. MLP2LN method tries to convert a standard MLP into a network performing logical operations (LN). C-MLP2LN is a constructive algorithm creating such MLP networks. Logical interpretation is assured by adding constraints to the cost function, forcing the weights to ±1 or 0. Skeletal networks emerge ensuring that a minimal number of logical rules are found. In both methods rules covering many training examples are generated before more specific rules covering exceptions. The third method, FSM2LN, is based on the probability density estimation. Several examples of performance of these methods are presented.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009670302979
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 71
    Electronic Resource
    Electronic Resource
    Constraints Satisfaction through Recursive Neural Networks with Mixed Penalties: a Case Study (1998)
    Springer
    Neural processing letters 8 (1998), S. 15-26 
    Details
    ISSN: 1573-773X
    Keywords: neural networks ; constraints satisfaction ; assignment problems ; 0/1 linear programming
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract This paper investigates an industrial assignment problem. It is modelized as a constraint satisfaction problem of large size with linear inequalities and binary variables. A new analog neuron-like network is proposed to find out feasible solutions to problems having several thousands of 0/1 variables. The approach developed in this paper is based on mixed-penalty functions: exterior penalty functions together with interior penalty functions. Starting from a near-binary solution satisfying each linear inequality, the network generates trial solutions located outside or inside the feasible set, in order to minimize an energy function which measures the total binary infeasibility of the system. The performances of the network are demonstrated on real data sets.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009660928212
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 72
    Electronic Resource
    Electronic Resource
    Handwritten Digit Recognition by a Mixture of Local Principal Component Analysis (1998)
    Springer
    Neural processing letters 8 (1998), S. 241-252 
    Details
    ISSN: 1573-773X
    Keywords: neural networks ; mixture of principal component analysis ; handwritten digit recognition
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Mixture of local principal component analysis (PCA) has attracted attention due to a number of benefits over global PCA. The performance of a mixture model usually depends on the data partition and local linear fitting. In this paper, we propose a mixture model which has the properties of optimal data partition and robust local fitting. Data partition is realized by a soft competition algorithm called neural 'gas' and robust local linear fitting is approached by a nonlinear extension of PCA learning algorithm. Based on this mixture model, we describe a modular classification scheme for handwritten digit recognition, in which each module or network models the manifold of one of ten digit classes. Experiments demonstrate a very high recognition rate.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009673230776
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 73
    Electronic Resource
    Electronic Resource
    Evolutionary Learning of Modular Neural Networks with Genetic Programming (1998)
    Springer
    Applied intelligence 9 (1998), S. 191-200 
    Details
    ISSN: 1573-7497
    Keywords: neural networks ; evolutionary computation ; modules ; emergence
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Evolutionary design of neural networks has shown a great potential as a powerful optimization tool. However, most evolutionary neural networks have not taken advantage of the fact that they can evolve from modules. This paper presents a hybrid method of modular neural networks and genetic programming as a promising model for evolutionary learning. This paper describes the concepts and methodologies for the evolvable model of modular neural networks, which might not only develop new functionality spontaneously, but also grow and evolve its own structure autonomously. We show the potential of the method by applying an evolved modular network to a visual categorization task with handwritten digits. Sophisticated network architectures as well as functional subsystems emerge from an initial set of randomly-connected networks. Moreover, the evolved neural network has reproduced some of the characteristics of natural visual system, such as the organization of coarse and fine processing of stimuli in separate pathways.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008388118869
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 74
    Electronic Resource
    Electronic Resource
    Automation of an Industrial Fork Lift Truck, Guided by Artificial Vision in Open Environments (1998)
    Springer
    Autonomous robots 5 (1998), S. 215-231 
    Details
    ISSN: 1573-7527
    Keywords: mobile robot ; road following ; multi-sensor integration ; visual feedback ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract Mobile robots capable of moving autonomously in more or less structured environments are being increasingly employed in the automation of certain industrial processes. Along these lines, the authors constructed a platform, on the base of a commercial industrial truck, provided with sufficient autonomy to carry out tasks within an industrial environment (VIA: Autonomous Industrial Vehicle). One of the sensor systems used in the truck is a system of artificial vision which enables it to move on asphalted surfaces both in open environments (roads) and closed ones, seeking the markings which most easily allow it to determine the path marked in the images. The system for following roads is capable of following painted lines, determining the sides of the road by texture analysis or determining the minimum width of the road for the robot to pass, according to the circumstances. A model of the road predicts its situation and enables a decision to be made on whether the information provided by the algorithm is reliable or not. At the same time, a neural network is trained with the results obtained by any of the previous algorithms, in such a way that when the training process converges the network takes over the steering of the truck. The vision system, composed of a CCD colour camera and a “frame grabber” installed in a PCI slot of a Pentium 120 PC, provides a path every 100 ms, which allows the industrial truck to be steered at its maximum speed of 10 m/s.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008826306614
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 75
    Electronic Resource
    Electronic Resource
    Rapid Concept Learning for Mobile Robots (1998)
    Springer
    Autonomous robots 5 (1998), S. 239-251 
    Details
    ISSN: 1573-7527
    Keywords: robot learning ; concept learning ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract Concept learning in robotics is an extremely challenging problem: sensory data is often high dimensional, and noisy due to specularities and other irregularities. In this paper, we investigate two general strategies to speed up learning, based on spatial decomposition of the sensory representation, and simultaneous learning of multiple classes using a shared structure. We study two concept learning scenarios: a hallway navigation problem, where the robot has to induce features such as “opening” or “wall”. The second task is recycling, where the robot has to learn to recognize objects, such as a “trash can”. We use a common underlying function approximator in both studies in the form of a feedforward neural network, with several hundred input units and multiple output units. Despite the high degree of freedom afforded by such an approximator, we show the two strategies provide sufficient bias to achieve rapid learning. We provide detailed experimental studies on an actual mobile robot called PAVLOV to illustrate the effectiveness of this approach.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008850021368
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 76
    Electronic Resource
    Electronic Resource
    Training a Vision Guided Mobile Robot (1998)
    Springer
    Autonomous robots 5 (1998), S. 381-394 
    Details
    ISSN: 1573-7527
    Keywords: mobile robots ; neural networks ; machine vision ; robot learning
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
    Notes: Abstract This paper presents the design, implementation and evaluation of a trainable vision guided mobile robot. The robot, CORGI, has a CCD camera as its only sensor which it is trained to use for a variety of tasks. The techniques used for training and the choice of natural light vision as the primary sensor makes the methodology immediately applicable to tasks such as trash collection or fruit picking. For example, the robot is readily trained to perform a ball finding task which involves avoiding obstacles and aligning with tennis balls. The robot is able to move at speeds up to 0.8 ms-1 while performing this task, and has never had a collision in the trained environment. It can process video and update the actuators at 11 Hz using a single $20 microprocessor to perform all computation. Further results are shown to evaluate the system for generalization across unseen domains, fault tolerance and dynamic environments.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008870625003
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 77
    Electronic Resource
    Electronic Resource
    Optimal Algorithmic Complexity of Fuzzy ART (1998)
    Springer
    Neural processing letters 7 (1998), S. 37-41 
    Details
    ISSN: 1573-773X
    Keywords: adaptive resonance theory ; algorithmic complexity ; fuzzy systems ; neural networks ; unsupervised learning
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract We discuss implementations of the Adaptive Resonance Theory (ART) on a serial machine. The standard formulation of ART, which was inspired by recurrent brain structures, corresponds to a recursive algorithm. This induces an algorithmic complexity of order O(N2)+O(MN) in worst and average case, N being the number of categories, and M the input dimension. It is possible, however, to formulate ART in a non-recursive algorithm such that the complexity is of order O(MN) only.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009632604848
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 78
    Electronic Resource
    Electronic Resource
    Functional Networks (1998)
    Springer
    Neural processing letters 7 (1998), S. 151-159 
    Details
    ISSN: 1573-773X
    Keywords: functional equation ; functional networks ; learning ; neural networks
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract In this letter we present functional networks. Unlike neural networks, in these networks there are no weightsassociated with the links connecting neurons, and the internal neuron functions are not fixed but learnable. These functions are not arbitrary, but subject to strong constraints to satisfy the compatibility conditions imposed by the existence of multiple links going from the last input layer to the same output units. In fact, writing the values of the output units in different forms, by considering these different links, a system of functional equations is obtained. When this system is solved, the numberof degrees of freedom of these initially multidimensional functions is considerably reduced. One example illustrates the process and shows that multidimensional functions can be reduced to functions with a single argument. To learn the resulting functions, a method based on minimizing a least squares error function is used, which, unlike the functions used in neural networks, has a single minimum.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009656525752
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 79
    Electronic Resource
    Electronic Resource
    Automatic Classification of Biological Particles from Electron-microscopy Images Using Conventional and Genetic-algorithm Optimized Learning Vector Quantization (1998)
    Springer
    Neural processing letters 8 (1998), S. 55-65 
    Details
    ISSN: 1573-773X
    Keywords: genetic algorithms ; neural networks ; neural network optimization ; image classification ; image reconstruction
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Automatic classification of transmission electron-microscopy images is an important step in the complex task of determining the structure of biologial macromolecules. The process of 3D reconstruction from a set of such images implies their previous classification into homogeneous image classes. In general, different classes may represent either distinct biochemical specimens or specimens from different directions of an otherwise homogenous specimen. In this paper, a neural network classification algorithm has been applied to a real-data case in which it was known a priori the existence of two differentiated views of the same specimen. Using two labeled sets as a reference, the parameters and architecture of the classifier were optimized using a genetic algorithm. The global automatic process of training and optimization is implemented using the previously described g-lvq (genetic learning vector quantization) [10] algorithm, and compared to a non-optimized version of the algorithm, Kohonen's lvq (learning vector quantization) [7]. Using a part of the sample as training set, the results presented here show an efficient (approximately 90%) average classification rate of unknown samples in two classes. Finally, the implication of this kind of automatic classification of algorithms in the determination of three dimensional structure of biological particles is discused. This paper extends the results already presented in [11], and also improves them.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009617113191
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 80
    Electronic Resource
    Electronic Resource
    Synchronization of Locally Coupled Neural Oscillators (1998)
    Springer
    Neural processing letters 7 (1998), S. 199-210 
    Details
    ISSN: 1573-773X
    Keywords: asymptotic stability ; Fitzhugh-Nagumo model ; local connections ; neural networks ; oscillations ; synchronization
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract A new method of controlling Fitzhugh-Nagumo (F-N) neural oscillators, Fitzhugh [1], with local coupling is presented. It is proved that through the use of an additive closed-loop controlling action that entrains each neural oscillator to a ‘goal’ behavior, necessary and sufficient conditions for the occurrence of synchronization in networks of unidirectionally self-connected neural oscillators are obtained in terms of asymptotic stability. These conditions suggest that rapid global synchronization can be achieved using sufficiently strong local inhibitory connections.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009618318908
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 81
    Electronic Resource
    Electronic Resource
    Extracting Rules from Composite Neural Networks for Medical Diagnostic Problems (1998)
    Springer
    Neural processing letters 8 (1998), S. 253-263 
    Details
    ISSN: 1573-773X
    Keywords: expert system ; genetic algorithms ; medical diagnosis ; neural networks ; rule extraction
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Recently, neural networks have been applied to many medical diagnostic problems because of their appealing properties, robustness, capability of generalization and fault tolerance. Although the predictive accuracy of neural networks may be higher than that of traditional methods (e.g., statistical methods) or human experts, the lack of explanation from a trained neural network leads to the difficulty that users would hesitate to take the advise of a black box on faith alone. This paper presents a class of composite neural networks which are trained in such a way that the values of the network parameters can be utilized to generate If-Then rules on the basis of preselected meaningful coordinates. The concepts and methods presented in the paper are illustrated through one practical example from medical diagnosis.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009681803460
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 82
    Electronic Resource
    Electronic Resource
    Large Neural Network Simulations on Multiple Hardware Platforms (1998)
    Springer
    Journal of computational neuroscience 5 (1998), S. 443-459 
    Details
    ISSN: 1573-6873
    Keywords: computational neuroscience ; neural networks ; neural simulation ; large-scale simulation ; portable software
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Medicine , Physics
    Notes: Abstract To efficiently simulate very large networks of interconnected neurons, particular consideration has to be given to the computer architecture being used. This article presents techniques for implementing simulators for large neural networks on a number of different computer architectures. The neuronal simulation task and the computer architectures of interest are first characterized, and the potential bottlenecks are highlighted. Then we describe the experience gained from adapting an existing simulator, SWIM, to two very different architectures–vector computers and multiprocessor workstations. This work lead to the implementation of a new simulation library, SPLIT, designed to allow efficient simulation of large networks on several architectures. Different computer architectures put different demands on the organization of both data structures and computations. Strict separation of such architecture considerations from the neuronal models and other simulation aspects makes it possible to construct both portable and extendible code.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008893429695
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 83
    Electronic Resource
    Electronic Resource
    Generating controlled reducing environments in aerobic recombinant Escherichia coli fermentations: Effects on cell growth, oxygen uptake, heat shock protein expression, and in vivo CAT activity (1998)
    New York, NY [u.a.] : Wiley-Blackwell
    Biotechnology and Bioengineering 59 (1998), S. 248-259 
    Details
    ISSN: 0006-3592
    Keywords: Escherichia coli ; Chloramphenicol Acetyltransferase (CAT) ; Culture Redox Potential (CRP) ; Dithiothreitol (DTT) ; reducing agents ; molecular chaperones ; proteases ; heat shock ; stress response ; protein folding ; Chemistry ; Biochemistry and Biotechnology
    Source: Wiley InterScience Backfile Collection 1832-2000
    Topics: Biology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: The independent control of culture redox potential (CRP) by the regulated addition of a reducing agent, dithiothreitol (DTT) was demonstrated in aerated recombinant Escherichia coli fermentations. Moderate levels of DTT addition resulted in minimal changes to specific oxygen uptake, growth rate, and dissolved oxygen. Excessive levels of DTT addition were toxic to the cells resulting in cessation of growth. Chloramphenicol acetyltransferase (CAT) activity (nmoles/μg total protein min.) decreased in batch fermentation experiments with respect to increasing levels of DTT addition. To further investigate the mechanisms affecting CAT activity, experiments were performed to assay heat shock protein expression and specific CAT activity (nmoles/μg CAT min.). Expression of such molecular chaperones as GroEL and DnaK were found to increase after addition of DTT. Additionally, sigma factor 32 (σ32) and several proteases were seen to increase dramatically during addition of DTT. Specific CAT activity (nmoles/μg CAT min.) varied greatly as DTT was added, however, a minimum in activity was found at the highest level of DTT addition in E. coli strains RR1 [pBR329] and JM105 [pROEX-CAT]. In conjunction, cellular stress was found to reach a maximum at the same levels of DTT. Although DTT addition has the potential for directly affecting intracellular protein folding, the effects felt from the increased stress within the cell are likely the dominant effector. That the effects of DTT were measured within the cytoplasm of the cell suggests that the periplasmic redox potential was also altered. The changes in specific CAT activity, molecular chaperones, and other heat shock proteins, in the presence of minimal growth rate and oxygen uptake alterations, suggest that the ex vivo control of redox potential provides a new process for affecting the yield and conformation of heterologous proteins in aerated E. coli fermentations. © 1998 John Wiley & Sons, Inc. Biotechnol Bioeng 59: 248-259, 1998.
    Additional Material: 10 Ill.
    Type of Medium: Electronic Resource
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
  • 84
    Electronic Resource
    Electronic Resource
    Retarded growth of an Escherichia coli mutant deficient in spermidine synthase can be unspecifically repaired by addition of various polyamines (1998)
    Springer
    World journal of microbiology and biotechnology 14 (1998), S. 857-863 
    Details
    ISSN: 1573-0972
    Keywords: Escherichia coli ; diamines ; homospermidine synthase ; polyamines ; spermidine deficiency ; spermidine synthase
    Source: Springer Online Journal Archives 1860-2000
    Topics: Biology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: Abstract The Escherichia coli mutant speE deficient in the gene encoding for spermidine synthase has no absolute requirement for spermidine but shows a retarded growth rate. This growth retardation could be unspecifically restored to the respective wild type level by exogenously supplied polyamines such as spermidine, spermine and homospermidine as well as the diamines putrescine and cadaverine. In comparison to the respective wild type, the mutant shows a two-fold increased level of endogenous putrescine but displays a reduced ability to accumulate the diamines putrescine and cadaverine. The ability to accumulate polyamines is not affected. The deleted spermidine synthase gene of the mutant was substituted by heterologous expression of the hss gene from Rhodopseudomonas viridis encoding homospermidine synthase.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008829008065
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 85
    Electronic Resource
    Electronic Resource
    Evolving the Topology and the Weights of Neural Networks Using a Dual Representation (1998)
    Springer
    Applied intelligence 8 (1998), S. 73-84 
    Details
    ISSN: 1573-7497
    Keywords: Evolutionary computation ; genetic algorithms ; neural networks ; genetic programming
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Evolutionary computation is a class of global search techniques based on the learning process of a population of potential solutions to a given problem, that has been successfully applied to a variety of problems. In this paper a new approach to the construction of neural networks based on evolutionary computation is presented. A linear chromosome combined to a graph representation of the network are used by genetic operators, which allow the evolution of the architecture and the weights simultaneously without the need of local weight optimization. This paper describes the approach, the operators and reports results of the application of this technique to several binary classification problems.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008272615525
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 86
    Electronic Resource
    Electronic Resource
    An Accelerated Genetic Algorithm (1998)
    Springer
    Applied intelligence 8 (1998), S. 103-111 
    Details
    ISSN: 1573-7497
    Keywords: genetic algorithm ; neural networks ; Baldwin effect ; optimisation ; history
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract The standard Genetic Algorithm, originally inspired by natural evolution, has displayed its effectiveness in solving a wide variety of complex problems. This paper describes the use of the natural phenomenon known as the Baldwin effect (or cross-generational learning) as an enhancement to the standard Genetic Algorithm. This is implemented by using an artificial neural network to store aspects of the population's history. It also describes a method by which the negative side effects of a large elite sub-population can be counter-balanced by using an ageing coefficient in the fitness calculation.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008227606285
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 87
    Electronic Resource
    Electronic Resource
    Evolving Neuro-Controllers for a Dynamic System Using Structured Genetic Algorithms (1998)
    Springer
    Applied intelligence 8 (1998), S. 113-121 
    Details
    ISSN: 1573-7497
    Keywords: genetic algorithms ; neural networks ; pole-cart system ; neuro-controller ; simulation ; gene activation ; multi-level chromosome
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract This paper describes the application of the Structured Genetic Algorithm (sGA) to design neuro-controllers for an unstable physical system. In particular, the approach uses a single unified genetic process to automatically evolve complete neural nets (both architectures and their weights) for controlling a simulated pole-cart system. Experimental results demonstrate the effectiveness of the sGA-evolved neuro-controllers for the task—to keep the pole upright (within a specified vertical angle) and the cart within the limits of the given track.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008291923124
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 88
    Electronic Resource
    Electronic Resource
    Neural-Fuzzy Models for Multispectral Image Analysis (1998)
    Springer
    Applied intelligence 8 (1998), S. 173-187 
    Details
    ISSN: 1573-7497
    Keywords: neural networks ; fuzzy logic ; classification ; remote sensing
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract In this paper, we consider neural-fuzzy models for multispectral image analysis. We consider both supervised and unsupervised classification. The model for supervised classification consists of six layers. The first three layers map the input variables to fuzzy set membership functions. The last three layers implement the decision rules. The model learns decision rules using a supervised gradient descent procedure. The model for unsupervised classification consists of two layers. The algorithm is similar to competitive learning. However, here, for each input sample, membership functions of output categories are used to update weights. Input vectors are normalized, and Euclidean distance is used as the similarity measure. In this model if the input vector does not satisfy the “similarity criterion,” a new cluster is created; otherwise, the weights corresponding to the winner unit are updated using the fuzzy membership values of the output categories. We have developed software for these models. As an illustration, the models are used to analyze multispectral images.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008200324941
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 89
    Electronic Resource
    Electronic Resource
    Neural Navigation Approach for Intelligent Autonomous Vehicles (IAV) in Partially Structured Environments (1998)
    Springer
    Applied intelligence 8 (1998), S. 219-233 
    Details
    ISSN: 1573-7497
    Keywords: Intelligent Autonomous Vehicles ; navigation ; target localization ; obstacle avoidance ; partially structured environments ; neural networks ; supervised gradient backpropagation learning ; reinforcement trial and error learning
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract The use of Neural Networks (NN) is necessary to bring the behavior of Intelligent Autonomous Vehicles (IAV) near the human one in recognition, learning, decision-making, and action. First, current navigation approaches based on NN are discussed. Indeed, these current approaches remedy insufficiencies of classical approaches related to real-time,autonomy , and intelligence. Second, a neural navigation approach essentially based on pattern classification to acquire target localization and obstacle avoidance behaviors is suggested. This approach must provide vehicles with capability, after supervised Gradient Backpropagation learning, to recognize both six (06) target location and thirty (30) obstacle avoidance situations using NN1 and NN2 classifiers, respectively. Afterwards, the decision-making and action consist of two association stages, carried out by reinforcement Trial and Error learning, and their coordination using a NN3. Then, NN3 allows to decide among five (05) actions (move towards 30°, move towards 60°, move towards 90°, move towards 120°, and move towards 150°). Third, simulation results which display the ability of theneural approach to provide IAV with capability to intelligently navigate in partially structured environments are presented. Finally, a discussion dealing with the suggested approach and how it relates to some other works is given.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008216400353
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 90
    Electronic Resource
    Electronic Resource
    Brief Application Description. Neural Networks Based Forecasting Techniques for Inventory Control Applications (1998)
    Springer
    Data mining and knowledge discovery 2 (1998), S. 97-102 
    Details
    ISSN: 1573-756X
    Keywords: neural networks ; applications of neural networks ; inventory management system ; statistical reasoning ; data mining and knowledge discovery
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract An increasing number of organizations are involved in the development of information systems for effective linkages with their suppliers, customers, and other channel partners involved in transportation, distribution, warehousing and maintenance activities. We use neural network based data mining and knowledge discovery techniques to solve the problems of inventory in a large medical distribution company. The paper describes the use of traditional statistical techniques to evaluate the best neural network type. Based on the neural network model described in this paper, a prototype was conceived with data from a large decentralized organization. The prototype was successful in reducing the total level of inventory by 50% in the organization, while maintaining the same level of probability that a particular customer's demand will be satisfied.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1009769804855
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 91
    Electronic Resource
    Electronic Resource
    High cell density culture of metabolically engineered Escherichia coli for the production of poly(3-hydroxybutyrate) in a defined medium (1998)
    New York, NY [u.a.] : Wiley-Blackwell
    Biotechnology and Bioengineering 58 (1998), S. 325-328 
    Details
    ISSN: 0006-3592
    Keywords: poly(3-hydroxybutyrate) ; Escherichia coli ; filamentation suppression ; defined medium ; high cell density culture ; Chemistry ; Biochemistry and Biotechnology
    Source: Wiley InterScience Backfile Collection 1832-2000
    Topics: Biology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: A recombinant Escherichia coli strain XL1-Blue harboring a stable high-copy-number plasmid pSYL107 containing the Alcaligenes eutrophus polyhydroxyalkanoate biosynthesis genes and the Escherichia coli ftsZ gene was employed for the production of poly(3-hydroxybutyrate) (PHB) by fed-batch culture in a defined medium. Suppression of filamentation by overexpressing the cell division protein FtsZ allowed production of PHB to a high concentration (77 g/L) with high productivity (2 g/L/h) in a defined medium, which was not possible with the recombinant E. coli that underwent filamentation. Further optimization of fed-batch culture condition resulted in PHB concentration of 104 g/L in a defined medium, which was the highest value reported to date by employing recombinant E. coli. © 1998 John Wiley & Sons, Inc. Biotechnol Bioeng 58:325-328, 1998.
    Additional Material: 3 Ill.
    Type of Medium: Electronic Resource
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
  • 92
    Electronic Resource
    Electronic Resource
    The expression of recombinant genes from bacteriophage lambda strong promoters triggers the SOS response in Escherichia coli (1998)
    New York, NY [u.a.] : Wiley-Blackwell
    Biotechnology and Bioengineering 60 (1998), S. 551-559 
    Details
    ISSN: 0006-3592
    Keywords: Escherichia coli ; SOS ; DNA repair ; recombinant proteins ; promoter ; proteolysis ; Chemistry ; Biochemistry and Biotechnology
    Source: Wiley InterScience Backfile Collection 1832-2000
    Topics: Biology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: The production of several non-related heterologous proteins in recombinant Escherichia coli cells promotes a significant transcription of recA and sfiA SOS DNA repair genes. The activation of the SOS system occurs when the expression of plasmid-encoded genes is directed by the strong lambda lytic promoters, but not by IPTG-controlled promoters either at 37 or at 42°C, and it is linked to an extensive degradation of the proteins after their synthesis. The triggering signal for the SOS response could be an important arrest of cell DNA replication observed within the first hour after the induction of recombinant gene expression. The stimulation of this DNA repair system can partially account for the toxicity exhibited by recombinant proteins on actively producing E. coli cells. © 1998 John Wiley & Sons, Inc. Biotechnol Bioeng 60: 551-559, 1998.
    Additional Material: 6 Ill.
    Type of Medium: Electronic Resource
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
  • 93
    Electronic Resource
    Electronic Resource
    Transportation of hazardous wastes (1998)
    New York, NY [u.a.] : Wiley-Blackwell
    Process Safety Progress 17 (1998), S. 61-67 
    Details
    ISSN: 1066-8527
    Keywords: Chemistry ; Chemical Engineering
    Source: Wiley InterScience Backfile Collection 1832-2000
    Topics: Chemistry and Pharmacology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: Risk assessments have been performed to determine the risk associated with the transportation of hazardous wastes through a city. In the course of these assessments, a number of modeling issues arose relating to transportation accident rates, the characterization of incidents, the effect of thermal radiation, the impact of exposure to toxic chemicals, and the threshold for acceptable risk. This paper discusses these issues.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1002/prs.680170112
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 94
    Electronic Resource
    Electronic Resource
    Process safety update (1998)
    New York, NY [u.a.] : Wiley-Blackwell
    Process Safety Progress 17 (1998), S. S3 
    Details
    ISSN: 1066-8527
    Keywords: Chemistry ; Chemical Engineering
    Source: Wiley InterScience Backfile Collection 1832-2000
    Topics: Chemistry and Pharmacology , Process Engineering, Biotechnology, Nutrition Technology
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1002/prs.680170202
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 95
    Electronic Resource
    Electronic Resource
    Burst resistant ribbon wound pressure vessels for ammonia plants (1998)
    New York, NY [u.a.] : Wiley-Blackwell
    Process Safety Progress 17 (1998), S. 98-103 
    Details
    ISSN: 1066-8527
    Keywords: Chemistry ; Chemical Engineering
    Source: Wiley InterScience Backfile Collection 1832-2000
    Topics: Chemistry and Pharmacology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: This paper presents the design of ribbon wound pressure vessels useful for Ammonia, Urea and Methanol plants. The design is to create a thin shell of 1/5 the total wall thickness required, weld it to the end pieces, and wind 4 to 8 mm thick ribbons of 80 mm width at an angle of 15 to 30 degrees on the inner shell, using a prestress. The ribbons are welded at the ends and an even number of layers are wound cross-helically on to the shell. With more than 7000 vessels over the pressure range of 50 to 350 atmospheres in use in the various chemical industries in China over the past 30 years, their safety record has been excellent. Of particular interest has been the application of this technology in the Ammonia and Urea plants, where the design allows fabrication of these vessels at substantial reduction in cost, and early delivery, when compared to the mono wall technology.
    Additional Material: 6 Ill.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1002/prs.680170205
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 96
    Electronic Resource
    Electronic Resource
    Safety surveys - looking at key activities in depth (1998)
    New York, NY [u.a.] : Wiley-Blackwell
    Process Safety Progress 17 (1998), S. 20-22 
    Details
    ISSN: 1066-8527
    Keywords: Chemistry ; Chemical Engineering
    Source: Wiley InterScience Backfile Collection 1832-2000
    Topics: Chemistry and Pharmacology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: Most audits try to look at a representative selection of the plant procedures and equipment. An alternative is a survey, a look in depth at selected procedures (such as those for testing alarms and trips, issuing permits-to-work, controlling modifications, taking samples or testing relief devices) or selected equipment (such as level glasses or equipment for handling LPG). If the procedure or equipment is well-chosen, surveys may make a bigger contribution to safety, per person-hour, than a conventional audit.
    Additional Material: 1 Tab.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1002/prs.680170106
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 97
    Electronic Resource
    Electronic Resource
    Pressure relief system documentation: Equipment based relational database is key to OSHA 1910.119 compliance (1998)
    New York, NY [u.a.] : Wiley-Blackwell
    Process Safety Progress 17 (1998), S. 39-42 
    Details
    ISSN: 1066-8527
    Keywords: Chemistry ; Chemical Engineering
    Source: Wiley InterScience Backfile Collection 1832-2000
    Topics: Chemistry and Pharmacology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: Under OSHA 1910.119, all Process Safety Management (PSM) facilities are required to keep their pressure relief system design information current. This article demonstrates why a pressure relief system design verification effort must be based on an equipment list, rather than a relief device list, in order to ensure that every piece of equipment is adequately protected. The formerly common practice of simply checking the design bases of all existing relief devices is deficient is deficient since this technique does not systematically ensure that every piece of equipment is protected.The “Berwanger Method” is a step by step process for designing or analyzing a pressure relief system to meet OSHA 1910.119 Process Safety Information (PSI) and Process Hazard Analysis (PHA) mandates. The method uses a relational database which tracks the relationships between protected equipment, potential overpressure scenarios, and protective devices.The challenge facing an operating company does not end once the design basis has been “verified” - the design basis information must also be maintained and be readily accessible to avoid costly reinvention of the wheel down the road. The “Berwanger Method” also addresses these maintenance issues.
    Additional Material: 6 Ill.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1002/prs.680170109
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 98
    Electronic Resource
    Electronic Resource
    A detailed reaction study of phosphorus trichloride and water (1998)
    New York, NY [u.a.] : Wiley-Blackwell
    Process Safety Progress 17 (1998), S. 49-60 
    Details
    ISSN: 1066-8527
    Keywords: Chemistry ; Chemical Engineering
    Source: Wiley InterScience Backfile Collection 1832-2000
    Topics: Chemistry and Pharmacology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: This paper reports on a comprehensive literature search and small scale experimental work on the reaction characteristics of phosphorous trichloride and water. More than 30 tests were conducted, including both closed and open test cells. The water to phosphorus trichloride molar ratio was varied from 1 to 25. When in contact, water and phosphorus trichloride will form two liquid layers with a reaction starting at the interface. The impact of variables on reaction rates including the interface surface area, layer depth, and stirring were investigated experimentally. A reaction rate model that fits all the measured data is presented. Case studies illustrating the use of this data for emergency relief systems and vent containment design are presented in reference. [1].
    Additional Material: 10 Ill.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1002/prs.680170111
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 99
    Electronic Resource
    Electronic Resource
    The influence of the geometry of the hot surfaces on the autoignition of vapor/air mixture: Some experimental and theoretical results (1998)
    New York, NY [u.a.] : Wiley-Blackwell
    Process Safety Progress 17 (1998), S. 68-73 
    Details
    ISSN: 1066-8527
    Keywords: Chemistry ; Chemical Engineering
    Source: Wiley InterScience Backfile Collection 1832-2000
    Topics: Chemistry and Pharmacology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: Two major accidents in the 80's: the summit Tunnel Fire, England and Piper Alpha disaster, an offshore platform in the North Sea; and very recently, possible explosion of the Boeing, TWA flight 800 at New York, makes it imperative that further research into the mechonisms of the ignition of flammable vapor/air mixture in contact with hot surfaces needs to be done. There have been a number of studies of ignition by hot surfaces, but in all these studies the ignition sources were wire, sphere or strip, i.e., most of them were flat surfaces. But to the authors' knowledge, other variables which affect the ignition mechanism such as irregular geometrical shapes have not been studied. The purpose of this paper is to examine how the degree of confinement (or, configuration), size and orientation, of the heated surface affects the ignition temperature of the flammable vapors. The results were obtained by experimentnal and by computational fluid dynamics.
    Additional Material: 13 Ill.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1002/prs.680170113
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 100
    Electronic Resource
    Electronic Resource
    Characterization of bacteriophage λ Q - mutant for stable and efficient production of recombinant protein in Escherichia coli system (1998)
    New York, NY [u.a.] : Wiley-Blackwell
    Biotechnology and Bioengineering 57 (1998), S. 529-535 
    Details
    ISSN: 0006-3592
    Keywords: bacteriophage λ ; Q - mutant ; Escherichia coli ; recombinant protein ; Chemistry ; Biochemistry and Biotechnology
    Source: Wiley InterScience Backfile Collection 1832-2000
    Topics: Biology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: We previously demonstrated that the λ system integrated into the host chromosome can overcome the instability encountered in continuous operations of unstable plasmid-based expression vectors. High stability of a cloned gene in a lysogenic state and a high copy number in a lytic state provide cloned-gene stability and overexpression in a two-stage continuous operation. But the expression by the commonly used S- mutant λ was only twice as high as that of the single copy. To increase the expression in the λ system, we constructed a Q- mutant λ vector that can be used in long-term operations such as a two-stage continuous operation. The Q- mutant phage λ is deficient in the synthesis of proteins involved in cell lysis and λ DNA packaging, while the S- mutant is deficient in the synthesis of one of two phage proteins required for lysis of the host cell and liberation of the progeny phage. Therefore, it is expected that the replicated Q- λ DNA containing a cloned gene would not be coated by a phage head and would remain naked for ample expression of the cloned gene and host cells would not lyse easily and consequently would produce larger amounts of cloned-gene products. The β-galactosidase expression per unit cell by the Q- mutant in a lytic state was about 30 times higher than that in a lysogenic state, while the expression by the commonly used S- mutant in a lytic state was twice as high as that in a lysogenic state. The optimal switching time of the Q- mutant from the lysogenic state to the lytic state for the maximum production of β-galactosidase was 5.3 h, which corresponds to an early log phase in the batch operation. ©1998 John Wiley & Sons, Inc. Biotechnol Bioeng 57: 529-535, 1998.
    Additional Material: 6 Ill.
    Type of Medium: Electronic Resource
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...