ALBERT

Description: This installment of Computer's series highlighting the work published in IEEE Computer Society journals comes from IEEE Transactions on Visualization and Computer Graphics. The Web extra at http://youtu.be/E1PVTitj7h0 is a video demonstration of a novel solution to multivariate data visualization that helps users interactively explore data by combining standard presentations, from detailed views to high-level overviews.

Description: The data rearrangement engine (DRE) performs in-memory data restructuring to accelerate irregular, data-intensive applications. An emulation on a field-programmable gate array shows how the DRE could improve speedup, memory bandwidth, and energy consumption on three representative benchmarks.

Description: Advertisement, IEEE.

Description: The goal of cross-domain matching (CDM) is to find correspondences between two sets of objects in different domains in an unsupervised way. CDM has various interesting applications, including photo album summarization where photos are automatically aligned into a designed frame expressed in the Cartesian coordinate system, and temporal alignment which aligns sequences such as videos that are potentially expressed using different features. In this paper, we propose an information-theoretic CDM framework based on squared-loss mutual information (SMI). The proposed approach can directly handle non-linearly related objects/sequences with different dimensions, with the ability that hyper-parameters can be objectively optimized by cross-validation. We apply the proposed method to several real-world problems including image matching, unpaired voice conversion, photo album summarization, cross-feature video and cross-domain video-to-mocap alignment, and Kinect -based action recognition, and experimentally demonstrate that the proposed method is a promising alternative to state-of-the-art CDM methods.

Description: The skeleton of a 2D shape is an important geometric structure in pattern analysis and computer vision. In this paper we study the skeleton of a 2D shape in a two-manifold $mathcal {M}$ , based on a geodesic metric. We present a formal definition of the skeleton $S(Omega )$ for a shape $Omega$ in $mathcal {M}$ and show several properties that make $S(Omega )$ distinct from its Euclidean counterpart in $mathbb {R}^2$ . We further prove that for a shape sequence $lbrace Omega _irbrace$ that converge to a shape $Omega$ in $mathcal {M}$ , the mapping $Omega righta- row overline{S}(Omega )$ is lower semi-continuous. A direct application of this result is that we can use a set $P$ of sample points to approximate the boundary of a 2D shape $Omega$ in $mathcal {M}$ , and the Voronoi diagram of $P$ inside $Omega subset mathcal {M}$ gives a good approximation to the skeleton $S(Omega )$ . Examples of skeleton computation in topography and brain morphometry are illustrated.

Description: A widely used approach for locating points on deformable objects in images is to generate feature response images for each point, and then to fit a shape model to these response images. We demonstrate that Random Forest regression-voting can be used to generate high quality response images quickly. Rather than using a generative or a discriminative model to evaluate each pixel, a regressor is used to cast votes for the optimal position of each point. We show that this leads to fast and accurate shape model matching when applied in the Constrained Local Model framework. We evaluate the technique in detail, and compare it with a range of commonly used alternatives across application areas: the annotation of the joints of the hands in radiographs and the detection of feature points in facial images. We show that our approach outperforms alternative techniques, achieving what we believe to be the most accurate results yet published for hand joint annotation and state-of-the-art performance for facial feature point detection.

Description: We present a novel method to recognise planar structures in a single image and estimate their 3D orientation. This is done by exploiting the relationship between image appearance and 3D structure, using machine learning methods with supervised training data. As such, the method does not require specific features or use geometric cues, such as vanishing points. We employ general feature representations based on spatiograms of gradients and colour, coupled with relevance vector machines for classification and regression. We first show that using hand-labelled training data, we are able to classify pre-segmented regions as being planar or not, and estimate their 3D orientation. We then incorporate the method into a segmentation algorithm to detect multiple planar structures from a previously unseen image.

Description: Multiple view segmentation consists in segmenting objects simultaneously in several views. A key issue in that respect and compared to monocular settings is to ensure propagation of segmentation information between views while minimizing complexity and computational cost. In this work, we first investigate the idea that examining measurements at the projections of a sparse set of 3D points is sufficient to achieve this goal. The proposed algorithm softly assigns each of these 3D samples to the scene background if it projects on the background region in at least one view, or to the foreground if it projects on foreground region in all views. Second, we show how other modalities such as depth may be seamlessly integrated in the model and benefit the segmentation. The paper exposes a detailed set of experiments used to validate the algorithm, showing results comparable with the state of art, with reduced computational complexity. We also discuss the use of different modalities for specific situations, such as dealing with a low number of viewpoints or a scene with color ambiguities between foreground and background.

Description: Text detection in natural scene images is an important prerequisite for many content-based image analysis tasks, while most current research efforts only focus on horizontal or near horizontal scene text. In this paper, first we present a unified distance metric learning framework for adaptive hierarchical clustering, which can simultaneously learn similarity weights (to adaptively combine different feature similarities) and the clustering threshold (to automatically determine the number of clusters). Then, we propose an effective multi-orientation scene text detection system, which constructs text candidates by grouping characters based on this adaptive clustering. Our text candidates construction method consists of several sequential coarse-to-fine grouping steps: morphology-based grouping via single-link clustering, orientation-based grouping via divisive hierarchical clustering, and projection-based grouping also via divisive clustering. The effectiveness of our proposed system is evaluated on several public scene text databases, e.g., ICDAR Robust Reading Competition data sets (2011 and 2013), MSRA-TD500 and NEOCR. Specifically, on the multi-orientation text data set MSRA-TD500, the $f$ measure of our system is $71$ percent, much better than the state-of-the-art performance. We also construct and release a practical challenging multi-orientation scene text data set (USTB-SV1K), which is available at http://prir.ustb.edu.cn/TexStar/MOMV-text-detection/.

Description: Digital circuits are expected to increasingly suffer from more hard faults due to technology scaling. Especially, a single hard fault in ALU (Arithmetic Logic Unit) might lead to a total failure in processors or significantly reduce their performance. To address these increasingly important problems, we propose a novel cost-efficient fault-tolerant mechanism for the ALU, called LIZARD. LIZARD employs two half-word ALUs, instead of a single full-word ALU, to perform computations with concurrent fault detection. When a fault is detected, the two ALUs are partitioned into four quarter-word ALUs. After diagnosing and isolating a faulty quarter-word ALU, LIZARD continues its operation using the remaining ones, which can detect and isolate another fault. Even though LIZARD uses narrow ALUs for computations, it adds negligible performance overhead through exploiting predictability of the results in the arithmetic computations. We also present the architectural modifications when employing LIZARD for scalar as well as superscalar processors. Through comparative evaluation, we demonstrate that LIZARD outperforms other competitive fault-tolerant mechanisms in terms of area, energy consumption, performance and reliability.

Description: Information searches are the most common application within social networks. Normally, the social network is modeled as a network graph, consisting of nodes (In the rest of the paper, unless otherwise specified, we will use the terms “user” and “node” interchangeably.) representing users within the network and edges representing relationships between users. Choosing the appropriate nodes to form an auxiliary structure for supporting the effective query message spreading can reduce the troublesome repeated queries. To accomplish this, a hybrid search (HS) scheme is proposed. If the query message is received by a node belonging the auxiliary structure constructed by dynamic weighted distributed label clustering (DW-DLC), it would be flooded to all neighbors of the visited node; otherwise, it would be forwarded to one neighbor of the visited node. The DW-DLC based auxiliary structure can accelerate the process of obtaining required information within the network. The simulation results show that the HS+DW-DLC scheme can reduce the average searching delay time, even in a required-information-scarce social network. In addition, the proposed scheme can generate a relatively low amount of repeated messages to lower repeatedly asking social network users.

Description: This paper presents a derivation of four radix-2 division algorithms by digit recurrence. Each division algorithm selects a quotient digit from the over-redundant digit set {−2, −1, 0, 1, 2}, and the selection of each quotient digit depends only on the two most-significant digits of the partial remainder in a redundant representation. Two algorithms use a two’s complement representation for the partial remainder and carry-save additions, and the other two algorithms use a binary signed-digit representation for the partial remainder and carry-free additions. Three algorithms are novel. The fourth algorithm has been presented before. Results from the synthesized netlists show that two of our fastest algorithms achieve an improvement of 10 percent in latency per iteration over a standard radix-2 SRT algorithm at the cost of 36 percent more power and 50 percent more area.

Description: We present WaFS, a user-level file system, and a related scheduling algorithm for scientific workflow computation in the cloud. WaFS’s primary design goal is to automatically detect and gather the explicit and implicit data dependencies between workflow jobs, rather than high-performance file access. Using WaFS’s data, a workflow scheduler can either make effective cost-performance tradeoffs or improve storage utilization. Proper resource provisioning and storage utilization on pay-as-you-go clouds can be more cost effective than the uses of resources in traditional HPC systems. WaFS and the scheduler controls the number of concurrent workflow instances at runtime so that the storage is well used, while the total makespan (i.e., turnaround time for a workload) is not severely compromised. We describe the design and implementation of WaFS and the new workflow scheduling algorithm based on our previous work. We present empirical evidence of the acceptable overheads of our prototype WaFS and describe a simulation-based study, using representative workflows, to show the makespan benefits of our WaFS-enabled scheduling algorithm.

Description: Given a database table with records that can be ranked, an interesting problem is to identify selection conditions for the table, which are qualified by an input record and render its ranking as high as possible among the qualifying tuples. In this paper, we study this standing maximization problem, which finds application in object promotion and characterization. After showing the hardness of the problem, we propose greedy methods, which are experimentally shown to achieve high accuracy compared to exhaustive enumeration, while scaling very well to the problem input size. Our contributions include a linear-time algorithm for determining the optimal selection range for an ordinal attribute and techniques for choosing and prioritizing the most promising selection predicates to apply. Experiments on real datasets confirm the effectiveness and efficiency of our techniques.

Description: Some fairly recent research has focused on providing XACML-based solutions for dynamic privacy policy management. In this regard, a number of works have provided enhancements to the performance of XACML policy enforcement point (PEP) component, but very few have focused on enhancing the accuracy of that component. This paper improves the accuracy of an XACML PEP by filling some gaps in the existing works. In particular, dynamically incorporating user access context into the privacy policy decision, and its enforcement. We provide an XACML-based implementation of a dynamic privacy policy management framework and an evaluation of the applicability of our system in comparison to some of the existing approaches.

Description: This paper first introduces pattern aided regression (PXR) models, a new type of regression models designed to represent accurate and interpretable prediction models. This was motivated by two observations: (1) Regression modeling applications often involve complex diverse predictor-response relationships , which occur when the optimal regression models (of given regression model type) fitting two or more distinct logical groups of data are highly different. (2) State-of-the-art regression methods are often unable to adequately model such relationships. This paper defines PXR models using several patterns and local regression models, which respectively serve as logical and behavioral characterizations of distinct predictor-response relationships. The paper also introduces a contrast pattern aided regression (CPXR) method, to build accurate PXR models. In experiments, the PXR models built by CPXR are very accurate in general, often outperforming state-of-the-art regression methods by big margins. Usually using (a) around seven simple patterns and (b) linear local regression models, those PXR models are easy to interpret; in fact, their complexity is just a bit higher than that of (piecewise) linear regression models and is significantly lower than that of traditional ensemble based regression models. CPXR is especially effective for high-dimensional data. The paper also discusses how to use CPXR methodology for analyzing prediction models and correcting their prediction errors.

Description: This paper presents an anomaly detection model that is granular and distributed to accurately and efficiently identify sensed data anomalies within wireless sensor networks. A more decentralised mechanism is introduced with wider use of in-network processing on a hierarchical sensor node topology resulting in a robust framework for dynamic data domains. This efficiently addresses the big data issue that is encountered in large scale industrial sensor network applications. Data vectors on each node’s observation domain is first partitioned using an unsupervised approach that is adaptive regarding dynamic data streams using cumulative point-wise entropy and average relative density . Second order statistical analysis applied on average relative densities and mean entropy values is then used to differentiate anomalies through robust and adaptive thresholds that are responsive to a dynamic environment. Anomaly detection is then performed in a non-parametric and non-probabilistic manner over the different network tiers in the hierarchical topology in offering increased granularity for evaluation. Experiments were performed extensively using both real and artificial data distributions representative of different dynamic and multi-density observation domains. Results demonstrate higher accuracies in detection as more than 94 percent accompanied by a desirable reduction of more than 85 percent in communication costs when compared to existing centralized methods.

Description: We analyze models for predicting the probability of a strikeout for a batter/pitcher matchup in baseball using player descriptors that can be estimated accurately from small samples. We start with the log5 model which has been used extensively for describing matchups in sports. Log5 is a special case of a logit model and we use constrained logistic regression over nearly one million matchup observations to assess the use of the log5 explanatory variables for this application. We also show that a batter/pitcher ground ball rate interaction variable is significant for the prediction of strikeout probability and we provide physical justification for the inclusion of this variable in the model. We quantify the differences among the models and show that batters control the majority of the variance in predicted strikeout rate.

Description: This study proposes a quantitative measurement of split of the second heart sound (S2) based on nonstationary signal decomposition to deal with overlaps and energy modeling of the subcomponents of S2. The second heart sound includes aortic (A2) and pulmonic (P2) closure sounds. However, the split detection is obscured due to A2-P2 overlap and low energy of P2. To identify such split, HVD method is used to decompose the S2 into a number of components while preserving the phase information. Further, A2s and P2s are localized using smoothed pseudo Wigner-Ville distribution followed by reassignment method. Finally, the split iscalculated by taking the differences between the means of time indices of A2s and P2s. Experiments on total 33 clips of S2 signals are performed for evaluation of the method. The mean ± standard deviation of the split is 34.7 ± 4.6 ms. The method measures the splitefficiently, even when A2-P2 overlap is ≤ 20 ms and the normalized peak temporal ratio of P2 to A2 is low (≥ 0.22). This proposed method thus, demonstrates its robustness by defining split detectability (SDT), the split detection aptness through detecting P2s, by measuring upto 96 percent. Such findings reveal the effectiveness of the method as competent against the other baselines, especially for A2-P2 overlaps and low energy P2.

Description: Post-acquisition denoising of magnetic resonance (MR) images is an important step to improve any quantitative measurement of the acquired data. In this paper, assuming a Rician noise model, a new filtering method based on the linear minimum mean square error (LMMSE) estimation is introduced, which employs the self-similarity property of the MR data to restore the noise-less signal. This method takes into account the structural characteristics of images and the Bayesian mean square error (Bmse) of the estimator to address the denoising problem. In general, a twofold data processing approach is developed; first, the noisy MR data is processed using a patch-based L 2 -norm similarity measure to provide the primary set of samples required for the estimation process. Afterwards, the Bmse of the estimator is derived as the optimization function to analyze the pre-selected samples and minimize the error between the estimated and the underlying signal. Compared to the LMMSE method and also its recently proposed SNR-adapted realization (SNLMMSE), the optimized way of choosing the samples together with the automatic adjustment of the filtering parameters lead to a more robust estimation performance with our approach. Experimental results show the competitive performance of the proposed method in comparison with related state-of-the-art methods.

Description: Large-scale ad hoc analytics of genomic data is popular using the R-programming language supported by over 700 software packages provided by Bioconductor. More recently, analytical jobs are benefitting from on-demand computing and storage, their scalability and their low maintenance cost, all of which are offered by the cloud. While biologists and bioinformaticists can take an analytical job and execute it on their personal workstations, it remains challenging to seamlessly execute the job on the cloud infrastructure without extensive knowledge of the cloud dashboard. How analytical jobs can not only with minimum effort be executed on the cloud, but also how both the resources and data required by the job can be managed is explored in this paper. An open-source light-weight framework for executing R-scripts using Bioconductor packages, referred to as ‘RBioCloud’, is designed and developed. RBioCloud offers a set of simple command-line tools for managing the cloud resources, the data and the execution of the job. Three biological test cases validate the feasibility of RBioCloud. The framework is available from http://www.rbiocloud.com .

Description: Of major interest to translational genomics is the intervention in gene regulatory networks (GRNs) to affect cell behavior; in particular, to alter pathological phenotypes. Owing to the complexity of GRNs, accurate network inference is practically challenging and GRN models often contain considerable amounts of uncertainty. Considering the cost and time required for conducting biological experiments, it is desirable to have a systematic method for prioritizing potential experiments so that an experiment can be chosen to optimally reduce network uncertainty. Moreover, from a translational perspective it is crucial that GRN uncertainty be quantified and reduced in a manner that pertains to the operational cost that it induces, such as the cost of network intervention. In this work, we utilize the concept of mean objective cost of uncertainty (MOCU) to propose a novel framework for optimal experimental design. In the proposed framework, potential experiments are prioritized based on the MOCU expected to remain after conducting the experiment. Based on this prioritization, one can select an optimal experiment with the largest potential to reduce the pertinent uncertainty present in the current network model. We demonstrate the effectiveness of the proposed method via extensive simulations based on synthetic and real gene regulatory networks.

Description: A novel approach to Contact Map Overlap (CMO) problem is proposed using the two dimensional clusters present in the contact maps. Each protein is represented as a set of the non-trivial clusters of contacts extracted from its contact map. The approach involves finding matching regions between the two contact maps using approximate 2D-pattern matching algorithm and dynamic programming technique. These matched pairs of small contact maps are submitted in parallel to a fast heuristic CMO algorithm. The approach facilitates parallelization at this level since all the pairs of contact maps can be submitted to the algorithm in parallel. Then, a merge algorithm is used in order to obtain the overall alignment. As a proof of concept, MSVNS, a heuristic CMO algorithm is used for global as well as local alignment. The divide and conquer approach is evaluated for two benchmark data sets that of Skolnick and Ding et al. It is interesting to note that along with achieving saving of time, better overlap is also obtained for certain protein folds.

Description: Canalizing genes possess broad regulatory power over a wide swath of regulatory processes. On the other hand, it has been hypothesized that the phenomenon of intrinsically multivariate prediction (IMP) is associated with canalization. However, applications have relied on user-selectable thresholds on the IMP score to decide on the presence of IMP. A methodology is developed here that avoids arbitrary thresholds, by providing a statistical test for the IMP score. In addition, the proposed procedure allows the incorporation of prior knowledge if available, which can alleviate the problem of loss of power due to small sample sizes. The issue of multiplicity of tests is addressed by family-wise error rate (FWER) and false discovery rate (FDR) controlling approaches. The proposed methodology is demonstrated by experiments using synthetic and real gene-expression data from studies on melanoma and ionizing radiation (IR) responsive genes. The results with the real data identified DUSP1 and p53, two well-known canalizing genes associated with melanoma and IR response, respectively, as the genes with a clear majority of IMP predictor pairs. This validates the potential of the proposed methodology as a tool for discovery of canalizing genes from binary gene-expression data. The procedure is made available through an R package.

Description: Prospective authors are requested to submit new, unpublished manuscripts for inclusion in the upcoming event described in this call for papers.

Description: Kalyani Nair reviews "Multiscale Modeling in Biomechanics and Mechanobiology", edited by S. De, W. Hwang, and E. Kuhl, declaring it useful for anyone looking to get a quick overview of the field over a broad spectrum of areas.

Description: Presents the information on the 2016 Richard E. Merwin Distinguished Service Award.

Description: As part of the Naming the Pain in Requirements Engineering (NaPiRE) initiative, researchers compared problems that companies in Brazil and Germany encountered during requirements engineering (RE). The key takeaway was that in RE, human interaction is necessary for eliciting and specifying high-quality requirements, regardless of country, project type, or company size.

Description: A swift execution from idea to market has become a key competitive advantage for software companies to enable them to survive and grow in turbulent business environments. To combat this challenge, companies are using hackathons. A hackathon is a highly engaging, continuous event in which people in small groups produce working software prototypes in a limited amount of time. F-Secure, a software product company, views hackathons as a possible solution to the fundamental business problem of how to make revenue from an idea, spanning the phases from creating the idea to producing a software prototype. However, hackathons pose the challenge of how to transform those promising prototypes into finalized products that create revenue and real business value.

Description: "The Karlskrona Manifesto on Sustainability Design" is a call for discussion and action on the challenge of sustainability and its relation to software engineering. The manifesto aims to create common ground and develop a reference point for the global community of research and practice in software and sustainability. The Web extra at http://youtu.be/PXhFgswJPco is an audio podcast in which author Birgit Penzenstadler provides an audio recording of this column.

Description: Software adaptation has become prominent owing to the proliferation of software in everyday devices. In particular, computing with the Internet of Things requires adaptability. Traditional software maintenance, which involves long, energy-consuming cycles, is no longer satisfactory. Adaptation is a lightweight software evolution that provides more transparent maintenance for users. This article classifies types of adaptation and describes an implementation of it.

Description: There's much discussion about being open, with topics such as open source software, open innovation, open research, and open education. Will the whole world be open, and, if so, what was all closed in the past? The authors analyze the similarities and differences between the open movements they've been part of and come up with expectations for software's future.

Description: License plate recognition is a computer vision method that identifies vehicles from their license plates. The most crucial step of such a system is accurate localization of the plate. The authors propose a system for automatic recognition that has three phases: image capture, plate localization, and license plate number recognition. They tested their methodology on 40 different car models with different types of license plates.

Description: A novel approach for event summarization and rare event detection is proposed. Unlike conventional methods that deal with event summarization and rare event detection independently, our method solves them in a single framework by transforming them into a graph editing problem. In our approach, a video is represented by a graph, each node of which indicates an event obtained by segmenting the video spatially and temporally. The edges between nodes describe the relationship between events. Based on the degree of relations, edges have different weights. After learning the graph structure, our method finds subgraphs that represent event summarization and rare events in the video by editing the graph, that is, merging its subgraphs or pruning its edges. The graph is edited to minimize a predefined energy model with the Markov Chain Monte Carlo (MCMC) method. The energy model consists of several parameters that represent the causality, frequency, and significance of events. We design a specific energy model that uses these parameters to satisfy each objective of event summarization and rare event detection. The proposed method is extended to obtain event summarization and rare event detection results across multiple videos captured from multiple views. For this purpose, the proposed method independently learns and edits each graph of individual videos for event summarization or rare event detection. Then, the method matches the extracted multiple graphs to each other, and constructs a single composite graph that represents event summarization or rare events from multiple views. Experimental results show that the proposed approach accurately summarizes multiple videos in a fully unsupervised manner . Moreover, the experiments demonstrate that the approach is advantageous in detecting rare transition of events .

Description: Object tracking has been one of the most important and active research areas in the field of computer vision. A large number of tracking algorithms have been proposed in recent years with demonstrated success. However, the set of sequences used for evaluation is often not sufficient or is sometimes biased for certain types of algorithms. Many datasets do not have common ground-truth object positions or extents, and this makes comparisons among the reported quantitative results difficult. In addition, the initial conditions or parameters of the evaluated tracking algorithms are not the same, and thus, the quantitative results reported in literature are incomparable or sometimes contradictory. To address these issues, we carry out an extensive evaluation of the state-of-the-art online object-tracking algorithms with various evaluation criteria to understand how these methods perform within the same framework. In this work, we first construct a large dataset with ground-truth object positions and extents for tracking and introduce the sequence attributes for the performance analysis. Second, we integrate most of the publicly available trackers into one code library with uniform input and output formats to facilitate large-scale performance evaluation. Third, we extensively evaluate the performance of 31 algorithms on 100 sequences with different initialization settings. By analyzing the quantitative results, we identify effective approaches for robust tracking and provide potential future research directions in this field.

Description: Fused Lasso is a popular regression technique that encodes the smoothness of the data. It has been applied successfully to many applications with a smooth feature structure. However, the computational cost of the existing solvers for fused Lasso is prohibitive when the feature dimension is extremely large. In this paper, we propose novel screening rules that are able to quickly identity the adjacent features with the same coefficients. As a result, the number of variables to be estimated can be significantly reduced, leading to substantial savings in computational cost and memory usage. To the best of our knowledge, the proposed approach is the first attempt to develop screening methods for the fused Lasso problem with general data matrix. Our major contributions are: 1) we derive a new dual formulation of fused Lasso that comes with several desirable properties; 2) we show that the new dual formulation of fused Lasso is equivalent to that of the standard Lasso by two affine transformations; 3) we propose a novel framework for developing effective and efficient screening rules for f used La sso via the m onotonicity of the s ubdifferentials (FLAMS). Some appealing features of FLAMS are: 1) our methods are safe in the sense that the detected adjacent features are guaranteed to have the same coefficients; 2) the dataset needs to be scanned only once to run the screening, whose computational cost is negligible compared to that of solving the fused Lasso; (3) FLAMS is independent of the solvers and can be integrated with any existing solvers. We have evaluated the proposed FLAMS rules on both synthetic and real datasets. The experiments indicate that FLAMS is very effective in identifying the adjacent features with the same coefficients. The speedup gained by FLAMS can be orders of magnitude.

Description: Hidden conditional random fields (HCRFs) are discriminative latent variable models which have been shown to successfully learn the hidden structure of a given classification problem. An Infinite hidden conditional random field is a hidden conditional random field with a countably infinite number of hidden states, which rids us not only of the necessity to specify a priori a fixed number of hidden states available but also of the problem of overfitting. Markov chain Monte Carlo (MCMC) sampling algorithms are often employed for inference in such models. However, convergence of such algorithms is rather difficult to verify, and as the complexity of the task at hand increases the computational cost of such algorithms often becomes prohibitive. These limitations can be overcome by variational techniques. In this paper, we present a generalized framework for infinite HCRF models, and a novel variational inference approach on a model based on coupled Dirichlet Process Mixtures, the HCRF-DPM. We show that the variational HCRF-DPM is able to converge to a correct number of represented hidden states, and performs as well as the best parametric HCRFs—chosen via cross-validation—for the difficult tasks of recognizing instances of agreement, disagreement, and pain in audiovisual sequences.

Description: In this paper, we address the challenging problem of detecting pedestrians who appear in groups. A new approach is proposed for single-pedestrian detection aided by two-pedestrian detection. A mixture model of two-pedestrian detectors is designed to capture the unique visual cues which are formed by nearby pedestrians but cannot be captured by single-pedestrian detectors. A probabilistic framework is proposed to model the relationship between the configurations estimated by single- and two-pedestrian detectors, and to refine the single-pedestrian detection result using two-pedestrian detection. The two-pedestrian detector can integrate with any single-pedestrian detector. Twenty-five state-of-the-art single-pedestrian detection approaches are combined with the two-pedestrian detector on three widely used public datasets: Caltech, TUD-Brussels, and ETH. Experimental results show that our framework improves all these approaches. The average improvement is $9$ percent on the Caltech-Test dataset, $11$ percent on the TUD-Brussels dataset and $17$ percent on the ETH dataset in terms of average miss rate. The lowest average miss rate is reduced from $37$ to percent on the Caltech-Test dataset, from $55$ to $50$ percent on the TUD-Brussels dataset and from $43$ to $38$ percent on the ETH dataset.

Description: The Regression Network plugin for Cytoscape ( RegNetC ) implements the RegNet algorithm for the inference of transcriptional association network from gene expression profiles. This algorithm is a model tree-based method to detect the relationship between each gene and the remaining genes simultaneously instead of analyzing individually each pair of genes as correlation-based methods do. Model trees are a very useful technique to estimate the gene expression value by regression models and favours localized similarities over more global similarity, which is one of the major drawbacks of correlation-based methods. Here, we present an integrated software suite, named RegNetC , as a Cytoscape plugin that can operate on its own as well. RegNetC facilitates, according to user-defined parameters, the resulted transcriptional gene association network in .sif format for visualization, analysis and interoperates with other Cytoscape plugins, which can be exported for publication figures. In addition to the network, the RegNetC plugin also provides the quantitative relationships between genes expression values of those genes involved in the inferred network, i.e., those defined by the regression models.

Description: The problem of securing data present on USB memories and SD cards has not been adequately addressed in the cryptography literature. While the formal notion of a tweakable enciphering scheme (TES) is well accepted as the proper primitive for secure data storage, the real challenge is to design a low cost TES which can perform at the data rates of the targeted memory devices. In this work, we provide the first answer to this problem. Our solution, called STES, combines a stream cipher with a XOR universal hash function. The security of STES is rigorously analyzed in the usual manner of provable security approach. By carefully defining appropriate variants of the multi-linear hash function and the pseudo-dot product based hash function we obtain controllable trade-offs between area and throughput. We combine the hash function with the recent hardware oriented stream ciphers, namely Mickey, Grain and Trivium. Our implementations are targeted towards two low cost FPGAs—Xilinx Spartan 3 and Lattice ICE40. Simulation results demonstrate that the speeds of encryption/decryption match the data rates of different USB and SD memories. We believe that our work opens up the possibility of actually putting FPGAs within controllers of such memories to perform low-level in-place encryption.

Description: Over the past decade or so, several research groups have addressed the problem of multi-label classification where each example can belong to more than one class at the same time. A common approach, called  Binary Relevance (BR) , addresses this problem by inducing a separate classifier for each class. Research has shown that this framework can be improved if mutual class dependence is exploited: an example that belongs to class $X$ is likely to belong also to class $Y$ ; conversely, belonging to $X$ can make an example less likely to belong to $Z$ . Several works sought to model this information by using the vector of class labels as additional example attributes. To fill the unknown values of these attributes during prediction, existing methods resort to using outputs of other classifiers, and this makes them prone to errors. This is where our paper wants to contribute. We identified two potential ways to prune unnecessary dependencies and to reduce error-propagation in our new classifier-stacking technique, which is named PruDent . Experimental results indicate that the classification performance of PruDent compares favorably with that of other state-of-the-art approaches over a broad range of testbeds. Mor- over, its computational costs grow only linearly in the number of classes.

Description: Cellular automata (CAs) have been widely used to model and simulate physical systems and processes. CAs have also been successfully used as a VLSI architecture that proved to be very efficient at least in terms of silicon-area utilization and clock-speed maximization. Quantum cellular automata (QCAs) as one of the promising emerging technologies for nanoscale and quantum computing circuit implementation, provides very high scale integration, very high switching frequency and extremely low power characteristics. In this paper we present a new automated design architecture and a tool, namely DATICAQ (Design Automation Tool of 1-D CAs using QCAs), that builds a bridge between 1-D CAs as models of physical systems and processes and 1-D QCAs as nanoelectronic architecture. The QCA implementation of CAs not only drives the already developed CAs circuits to the nanoelectronics era but improves their performance significantly. The inputs of the proposed architecture are CA dimensionality, size, local rule, and initial and boundary conditions imposed by the particular problem. DATICAQ produces as output the layout of the QCA implementation of the particular 1-D CA model. Simulations of CA models for zero and periodic boundary conditions and the corresponding QCA circuits showed that the CA models have been successfully implemented.

Description: Role-based access control is an important access control method for securing computer systems. A role-based access control policy can be implemented incorrectly due to various reasons, such as programming errors. Defects in the implementation may lead to unauthorized access and security breaches. To reveal access control defects, this paper presents a model-based approach to automated generation of executable access control tests using predicate/transition nets. Role-permission test models are built by integrating declarative access control rules with functional test models or contracts (preconditions and postconditions) of the associated activities (the system functions). The access control tests are generated automatically from the test models to exercise the interactions of access control activities. They are transformed into executable code through a model-implementation mapping that maps the modeling elements to implementation constructs. The approach has been implemented in an industry-adopted test automation framework that supports the generation of test code in a variety of languages. The full model-based testing process has been applied to three systems implemented in Java. The effectiveness is evaluated through mutation analysis of role-based access control rules. The experiments show that the model-based approach is highly effective in detecting the seeded access control defects.

Description: Heterogeneous multiprocessor systems, which are composed of a mix of processing elements, such as commodity multicore processors, graphics processing units (GPUs), and others, have been widely used in scientific computing community. Software applications incorporate the code designed and optimized for different types of processing elements in order to exploit the computing power of such heterogeneous computing systems. In this paper, we consider the problem of optimal distribution of the workload of data-parallel scientific applications between processing elements of such heterogeneous computing systems. We present a solution that uses functional performance models (FPMs) of processing elements and FPM-based data partitioning algorithms. Efficiency of this approach is demonstrated by experiments with parallel matrix multiplication and numerical simulation of lid-driven cavity flow on hybrid servers and clusters.

Description: In this paper, we propose a new notion called $k$ -times attribute-based anonymous access control , which is particularly designed for supporting cloud computing environment. In this new notion, a user can authenticate himself/herself to the cloud computing server anonymously. The server only knows the user acquires some required attributes, yet it does not know the identity of this user. In addition, we provide a $k$ -times limit for anonymous access control. That is, the server may limit a particular set of users (i.e., those users with the same set of attribute) to access the system for a maximum $k$ -times within a period or an event. Further additional access will be denied. We also prove the security of our instantiation. Our implementation result shows that our scheme is practical.

Description: In face of high partial and complete disk failure rates and untimely system crashes, the executions of low-priority background tasks become increasingly frequent in large-scale data centers. However, the existing algorithms are all reactive optimizations and only exploit the temporal locality of workloads to reduce the user I/O requests during the low-priority background tasks. To address the problem, this paper proposes Intelligent Data Outsourcing (IDO), a zone-based and proactive data migration optimization, to significantly improve the efficiency of the low-priority background tasks. The main idea of IDO is to proactively identify the hot data zones of RAID-structured storage systems in the normal operational state. By leveraging the prediction tools to identify the upcoming events, IDO proactively migrates the data blocks belonging to the hot data zones on the degraded device to a surrogate RAID set in the large-scale data centers. Upon a disk failure or crash reboot, most user I/O requests addressed to the degraded RAID set can be serviced directly by the surrogate RAID set rather than the much slower degraded RAID set. Consequently, the performance of the background tasks and user I/O performance during the background tasks are improved simultaneously. Our lightweight prototype implementation of IDO and extensive trace-driven experiments on two case studies demonstrate that, compared with the existing state-of-the-art approaches, IDO effectively improves the performance of the low-priority background tasks. Moreover, IDO is portable and can be easily incorporated into any existing algorithms for RAID-structured storage systems.

Description: This work deals with the problem of producing a fast and accurate data classification, learning it from a possibly small set of records that are already classified. The proposed approach is based on the framework of the so-called Logical Analysis of Data (LAD), but enriched with information obtained from statistical considerations on the data. A number of discrete optimization problems are solved in the different steps of the procedure, but their computational demand can be controlled. The accuracy of the proposed approach is compared to that of the standard LAD algorithm, of support vector machines and of label propagation algorithm on publicly available datasets of the UCI repository. Encouraging results are obtained and discussed.

Description: Cloud computing that provides elastic computing and storage resource on demand has become increasingly important due to the emergence of “big data”. Cloud computing resources are a natural fit for processing big data streams as they allow big data application to run at a scale which is required for handling its complexities (data volume, variety and velocity). With the data no longer under users’ direct control, data security in cloud computing is becoming one of the most concerns in the adoption of cloud computing resources. In order to improve data reliability and availability, storing multiple replicas along with original datasets is a common strategy for cloud service providers. Public data auditing schemes allow users to verify their outsourced data storage without having to retrieve the whole dataset. However, existing data auditing techniques suffers from efficiency and security problems. First, for dynamic datasets with multiple replicas, the communication overhead for update verifications is very large, because each update requires updating of all replicas, where verification for each update requires O(log n ) communication complexity. Second, existing schemes cannot provide public auditing and authentication of block indices at the same time. Without authentication of block indices, the server can build a valid proof based on data blocks other than the blocks client requested to verify. In order to address these problems, in this paper, we present a novel public auditing scheme named MuR-DPA. The new scheme incorporated a novel authenticated data structure (ADS) based on the Merkle hash tree (MHT), which we call MR-MHT. To support full dynamic data updates and authentication of block indices, we included rank and level values in computation of MHT nodes. In contrast to existing schemes, level values of nodes in MR-MHT are assigned in a top-down order, and all replica blocks for each data block are organized into a - ame replica sub-tree. Such a configuration allows efficient verification of updates for multiple replicas. Compared to existing integrity verification and public auditing schemes, theoretical analysis and experimental results show that the proposed MuR-DPA scheme can not only incur much less communication overhead for both update verification and integrity verification of cloud datasets with multiple replicas, but also provide enhanced security against dishonest cloud service providers.

Description: A new graph based constrained semi-supervised learning (G-CSSL) framework is proposed. Pairwise constraints (PC) are used to specify the types (intra- or inter-class) of points with labels. Since the number of labeled data is typically small in SSL setting, the core idea of this framework is to create and enrich the PC sets using the propagated soft labels from both labeled and unlabeled data by special label propagation (SLP), and hence obtaining more supervised information for delivering enhanced performance. We also propose a Two-stage Sparse Coding, termed TSC, for achieving adaptive neighborhood for SLP. The first stage aims at correcting the possible corruptions in data and training an informative dictionary, and the second stage focuses on sparse coding. To deliver enhanced inter-class separation and intra-class compactness, we also present a mixed soft-similarity measure to evaluate the similarity/dissimilarity of constrained pairs using the sparse codes and outputted probabilistic values by SLP. Simulations on the synthetic and real datasets demonstrated the validity of our algorithms for data representation and image recognition, compared with other related state-of-the-art graph based semi-supervised techniques.

Description: In large databases, the amount and the complexity of the data calls for data summarization techniques. Such summaries are used to assist fast approximate query answering or query optimization. Histograms are a prominent class of model-free data summaries and are widely used in database systems. So-called self-tuning histograms look at query-execution results to refine themselves. An assumption with such histograms, which has not been questioned so far, is that they can learn the dataset from scratch, that is—starting with an empty bucket configuration. We show that this is not the case. Self-tuning methods are very sensitive to the initial configuration. Three major problems stem from this. Traditional self-tuning is unable to learn projections of multi-dimensional data, is sensitive to the order of queries, and reaches only local optima with high estimation errors. We show how to improve a self-tuning method significantly by starting with a carefully chosen initial configuration. We propose initialization by dense subspace clusters in projections of the data, which improves both accuracy and robustness of self-tuning. Our experiments on different datasets show that the error rate is typically halved compared to the uninitialized version.

Description: Recently, two ideas have been explored that lead to more accurate algorithms for time-series classification (TSC). First, it has been shown that the simplest way to gain improvement on TSC problems is to transform into an alternative data space where discriminatory features are more easily detected. Second, it was demonstrated that with a single data representation, improved accuracy can be achieved through simple ensemble schemes. We combine these two principles to test the hypothesis that forming a collective of ensembles of classifiers on different data transformations improves the accuracy of time-series classification. The collective contains classifiers constructed in the time, frequency, change, and shapelet transformation domains. For the time domain, we use a set of elastic distance measures. For the other domains, we use a range of standard classifiers. Through extensive experimentation on 72 datasets, including all of the 46 UCR datasets, we demonstrate that the simple collective formed by including all classifiers in one ensemble is significantly more accurate than any of its components and any other previously published TSC algorithm. We investigate alternative hierarchical collective structures and demonstrate the utility of the approach on a new problem involving classifying Caenorhabditis elegans mutant types.

Description: In real-world graphs such as social networks, Semantic Web and biological networks, each vertex usually contains rich information, which can be modeled by a set of tokens or elements. In this paper, we study a subgraph matching with set similarity (SMS $^2$ ) query over a large graph database, which retrieves subgraphs that are structurally isomorphic to the query graph, and meanwhile satisfy the condition of vertex pair matching with the (dynamic) weighted set similarity. To efficiently process the SMS $^2$ query, this paper designs a novel lattice-based index for data graph, and lightweight signatures for both query vertices and data vertices. Based on the index and signatures, we propose an efficient two-phase pruning strategy including set similarity pruning and structure-based pruning, which exploits the unique features of both (dynamic) weighted set similarity and graph topology. We also propose an efficient dominating-set-based subgraph matching algorithm guided by a dominating set selection algorithm to achieve better query performance. Extensive experiments on both real and synthetic datasets demonstrate that our method outperforms state-of-the-art methods by an order of magnitude.

Description: Data imputation aims at filling in missing attribute values in databases. Most existing imputation methods to string attribute values are inferring-based approaches, which usually fail to reach a high imputation recall by just inferring missing values from the complete part of the data set. Recently, some retrieving-based methods are proposed to retrieve missing values from external resources such as the World Wide Web, which tend to reach a much higher imputation recall, but inevitably bring a large overhead by issuing a large number of search queries. In this paper, we investigate the interaction between the inferring-based methods and the retrieving-based methods. We show that retrieving a small number of selected missing values can greatly improve the imputation recall of the inferring-based methods. With this intuition, we propose an inTeractive Retrieving-Inferring data imPutation approach (TRIP), which performs retrieving and inferring alternately in filling in missing attribute values in a data set. To ensure the high recall at the minimum cost, TRIP faces a challenge of selecting the least number of missing values for retrieving to maximize the number of inferable values. Our proposed solution is able to identify an optimal retrieving-inferring scheduling scheme in deterministic data imputation, and the optimality of the generated scheme is theoretically analyzed with proofs. We also analyze with an example that the optimal scheme is not feasible to be achieved in $tau$ -constrained stochastic data imputation ( $tau$ -SDI), but still, our proposed solution identifies an expected-optimal scheme in $tau$ -SDI. Extensive experiments on four data collections show that TRIP retrieves on average 20 percent missing values and achieves the same high recall that was reached by the retrieving-based approach.

Description: Visual classification has attracted considerable research interests in the past decades. In this paper, a novel $ell _1$ -hypergraph model for visual classification is proposed. Hypergraph learning, as a natural extension of graph model, has been widely used in many machine learning tasks. In previous work, hypergraph is usually constructed by attribute-based or neighborhood-based methods. That is, a hyperedge is generated by connecting a set of samples sharing a same feature attribute or in a neighborhood. However, these methods are unable to explore feature space globally or sensitive to noises. To address these problems, we propose a novel hypergraph construction approach that leverages sparse representation to generate hyperedges and learns the relationship among hyperedges and their vertices. First, for each sample, a hyperedge is generated by regarding it as the centroid and linking it as well as its nearest neighbors. Then, the sparse representation method is applied to represent the centroid vertex by other vertices within the same hyperedge. The vertices with zero coefficients are removed from the hyperedge. Finally, the representation coefficients are used to define the incidence relation between the hyperedge and the vertices. In our approach, we also optimize the hyperedge weights to modulate the effects of different hyperedges. We leverage the prior knowledge on the hyperedges so that the hyperedges sharing more vertices can have closer weights, where a graph Laplacian is used to regularize the optimization of the weights. Our approach is named $ell _1$ -hypergraph since the $ell _1$ sparse representation is employed in the hypergraph construction process. The method is evaluated on various visual classification tasks, and it demonstrates promising performance.

Description: We introduce a new method for normalization of data acquired by liquid chromatography coupled with mass spectrometry (LC-MS) in label-free differential expression analysis. Normalization of LC-MS data is desired prior to subsequent statistical analysis to adjust variabilities in ion intensities that are not caused by biological differences but experimental bias. There are different sources of bias including variabilities during sample collection and sample storage, poor experimental design, noise, etc. In addition, instrument variability in experiments involving a large number of LC-MS runs leads to a significant drift in intensity measurements. Although various methods have been proposed for normalization of LC-MS data, there is no universally applicable approach. In this paper, we propose a Bayesian normalization model (BNM) that utilizes scan-level information from LC-MS data. Specifically, the proposed method uses peak shapes to model the scan-level data acquired from extracted ion chromatograms (EIC) with parameters considered as a linear mixed effects model. We extended the model into BNM with drift (BNMD) to compensate for the variability in intensity measurements due to long LC-MS runs. We evaluated the performance of our method using synthetic and experimental data. In comparison with several existing methods, the proposed BNM and BNMD yielded significant improvement.

Description: Performing clustering analysis is one of the important research topics in cancer discovery using gene expression profiles, which is crucial in facilitating the successful diagnosis and treatment of cancer. While there are quite a number of research works which perform tumor clustering, few of them considers how to incorporate fuzzy theory together with an optimization process into a consensus clustering framework to improve the performance of clustering analysis. In this paper, we first propose a random double clustering based cluster ensemble framework (RDCCE) to perform tumor clustering based on gene expression data. Specifically, RDCCE generates a set of representative features using a randomly selected clustering algorithm in the ensemble, and then assigns samples to their corresponding clusters based on the grouping results. In addition, we also introduce the random double clustering based fuzzy cluster ensemble framework (RDCFCE), which is designed to improve the performance of RDCCE by integrating the newly proposed fuzzy extension model into the ensemble framework. RDCFCE adopts the normalized cut algorithm as the consensus function to summarize the fuzzy matrices generated by the fuzzy extension models, partition the consensus matrix, and obtain the final result. Finally, adaptive RDCFCE (A-RDCFCE) is proposed to optimize RDCFCE and improve the performance of RDCFCE further by adopting a self-evolutionary process (SEPP) for the parameter set. Experiments on real cancer gene expression profiles indicate that RDCFCE and A-RDCFCE works well on these data sets, and outperform most of the state-of-the-art tumor clustering algorithms.

Description: Named-entity recognition (NER) plays an important role in the development of biomedical databases. However, the existing NER tools produce multifarious named-entities which may result in both curatable and non-curatable markers. To facilitate biocuration with a straightforward approach, classifying curatable named-entities is helpful with regard to accelerating the biocuration workflow. Co-occurrence Interaction Nexus with Named-entity Recognition (CoINNER) is a web-based tool that allows users to identify genes, chemicals, diseases, and action term mentions in the Comparative Toxicogenomic Database (CTD). To further discover interactions, CoINNER uses multiple advanced algorithms to recognize the mentions in the BioCreative IV CTD Track. CoINNER is developed based on a prototype system that annotated gene, chemical, and disease mentions in PubMed abstracts at BioCreative 2012 Track I (literature triage). We extended our previous system in developing CoINNER. The pre-tagging results of CoINNER were developed based on the state-of-the-art named entity recognition tools in BioCreative III. Next, a method based on conditional random fields (CRFs) is proposed to predict chemical and disease mentions in the articles. Finally, action term mentions were collected by latent Dirichlet allocation (LDA). At the BioCreative IV CTD Track, the best F-measures reached for gene/protein, chemical/drug and disease NER were 54 percent while CoINNER achieved a 61.5 percent F-measure. System URL: http://ikmbio.csie.ncku.edu.tw/coinner/introduction.htm.

Description: Next-generation short-read sequencing is widely utilized in genomic studies. Biological applications require an alignment step to map sequencing reads to the reference genome, before acquiring expected genomic information. This requirement makes alignment accuracy a key factor for effective biological interpretation. Normally, when accounting for measurement errors and single nucleotide polymorphisms, short read mappings with a few mismatches are generally considered acceptable. However, to further improve the efficiency of short-read sequencing alignment, we propose a method to retrieve additional reliably aligned reads (reads with more than a pre-defined number of mismatches), using a Bayesian-based approach. In this method, we first retrieve the sequence context around the mismatched nucleotides within the already aligned reads; these loci contain the genomic features where sequencing errors occur. Then, using the derived pattern, we evaluate the remaining (typically discarded) reads with more than the allowed number of mismatches, and calculate a score that represents the probability that a specific alignment is correct. This strategy allows the extraction of more reliably aligned reads, therefore improving alignment sensitivity. Implementation: The source code of our tool, ResSeq, can be downloaded from: https://github.com/hrbeubiocenter/Resseq.

Description: In genome assembly graphs, motifs such as tips, bubbles, and cross links are studied in order to find sequencing errors and to understand the nature of the genome. Superbubble, a complex generalization of bubbles, was recently proposed as an important subgraph class for analyzing assembly graphs. At present, a quadratic time algorithm is known. This paper gives an -time algorithm to solve this problem for a graph with $m$ edges.

Description: The papers in this special section focus on software and databases that are central in bioinformatics and computational biology.. These programs are playing more and more important roles in biology and medical research. These papers cover a broad range of topics, including computational genomics and transcriptomics, analysis of biological networks and interactions, drug design, biomedical signal/image analysis, biomedical text mining and ontologies, biological data mining, visualization and integration, and high performance computing application in bioinformatics.

Description: In the computational biology community, machine learning algorithms are key instruments for many applications, including the prediction of gene-functions based upon the available biomolecular annotations. Additionally, they may also be employed to compute similarity between genes or proteins. Here, we describe and discuss a software suite we developed to implement and make publicly available some of such prediction methods and a computational technique based upon Latent Semantic Indexing (LSI), which leverages both inferred and available annotations to search for semantically similar genes. The suite consists of three components. BioAnnotationPredictor is a computational software module to predict new gene-functions based upon Singular Value Decomposition of available annotations. SimilBio is a Web module that leverages annotations available or predicted by BioAnnotationPredictor to discover similarities between genes via LSI. The suite includes also SemSim , a new Web service built upon these modules to allow accessing them programmatically. We integrated SemSim in the Bio Search Computing framework (http://www.bioinformatics.deib.polimi.it/bio-seco/seco/), where users can exploit the Search Computing technology to run multi-topic complex queries on multiple integrated Web services. Accordingly, researchers may obtain ranked answers involving the computation of the functional similarity between genes in support of biomedical knowledge discovery.

Description: Identification of cancer subtypes plays an important role in revealing useful insights into disease pathogenesis and advancing personalized therapy. The recent development of high-throughput sequencing technologies has enabled the rapid collection of multi-platform genomic data (e.g., gene expression, miRNA expression, and DNA methylation) for the same set of tumor samples. Although numerous integrative clustering approaches have been developed to analyze cancer data, few of them are particularly designed to exploit both deep intrinsic statistical properties of each input modality and complex cross-modality correlations among multi-platform input data. In this paper, we propose a new machine learning model, called multimodal deep belief network (DBN), to cluster cancer patients from multi-platform observation data. In our integrative clustering framework, relationships among inherent features of each single modality are first encoded into multiple layers of hidden variables, and then a joint latent model is employed to fuse common features derived from multiple input modalities. A practical learning algorithm, called contrastive divergence (CD), is applied to infer the parameters of our multimodal DBN model in an unsupervised manner. Tests on two available cancer datasets show that our integrative data analysis approach can effectively extract a unified representation of latent features to capture both intra- and cross-modality correlations, and identify meaningful disease subtypes from multi-platform cancer data. In addition, our approach can identify key genes and miRNAs that may play distinct roles in the pathogenesis of different cancer subtypes. Among those key miRNAs, we found that the expression level of miR-29a is highly correlated with survival time in ovarian cancer patients. These results indicate that our multimodal DBN based data analysis approach may have practical applications in cancer pathogenesis studies and provide useful guidelines for personali- ed cancer therapy.

Description: The Internet of Anything and sustainability are coevolving concepts Their convergence is occurring in a world that can no longer be viewed in terms of often mechanistic and static precision characteristics, as was the thinking of our recently industrialized era. This special issue examines and reinforces this vital union and explores its potential.

Description: Crowdsourcing is a powerful technique that harnesses distributed intelligence to solve organizational problems. As a distributed network, crowdsourcing's strength comes from how information is transmitted to and from an organization that identifies a problem to be solved or an issue to be addressed to the crowd members who provide solutions or ideas. Here, the authors critically review the latest developments in crowdsourcing in China. As crowdsourcing gains momentum, information technology professionals should realize the challenges and opportunities arising from Chinese crowdsourcing.

Description: The Internet of Things (IoT) will democratize knowledge. Organizations are looking for ways to create active knowledge and insight from IoT data and apply this data to new business models in which understanding and addressing customer needs and demands is key. To ensure that the IoT can meet this challenge, the author identifies six key interest areas to pay attention to.

Description: In this era of interconnectivity, where almost everybody, everything, and anything are networked, cyber-physical systems (CPS), also known as the Internet of Things (IoT), have emerged as vital systems that use information systems to observe and modify the physical world. Despite the proliferation of CPS in our lives, many such systems still use hardwired designs to accomplish a limited set of functions, such as sensing, actuating, or processing data or information. To achieve the vision of a platform for enabling the full potential of CPS that will encourage and drive innovation, CPS designers will need a new architectural design that can help connect everybody, everything, and anything together to achieve both our known and unknown goals. In this article, the authors present such a conceptual design and discuss its essential parts and key characteristics.

Description: Over the last few years, we've seen a plethora of Internet of Things (IoT) solutions, products, and services make their way into the industry's marketplace. All such solutions will capture large amounts of data pertaining to the environment as well as their users. The IoT's objective is to learn more and better serve system users. Some IoT solutions might store data locally on devices ("things"), whereas others might store it in the cloud. The real value of collecting data comes through data processing and aggregation on a large scale, where new knowledge can be extracted. However, such procedures can lead to user privacy issues. This article discusses some of the main challenges of privacy in the IoT as well as opportunities for research and innovation. The authors also introduce some of the ongoing research efforts that address IoT privacy issues.

Description: Systems based on bag-of-words models from image features collected at maxima of sparse interest point operators have been used successfully for both computer visual object and action recognition tasks. While the sparse, interest-point based approach to recognition is not inconsistent with visual processing in biological systems that operate in ‘saccade and fixate’ regimes, the methodology and emphasis in the human and the computer vision communities remains sharply distinct. Here, we make three contributions aiming to bridge this gap. First, we complement existing state-of-the art large scale dynamic computer vision annotated datasets like Hollywood-2  [1] and UCF Sports  [2] with human eye movements collected under the ecological constraints of visual action and scene context recognition tasks. To our knowledge these are the first large human eye tracking datasets to be collected and made publicly available for video, vision.imar.ro/eyetracking (497,107 frames, each viewed by 19 subjects), unique in terms of their (a) large scale and computer vision relevance, (b) dynamic, video stimuli, (c) task control, as well as free-viewing . Second, we introduce novel dynamic consistency and alignment measures , which underline the remarkable stability of patterns of visual search among subjects. Third, we leverage the significant amount of collected data in order to pursue studies and build automatic, end-to-end trainable computer vision systems based on human eye movements. Our studies not only shed light on the differences between computer vision spatio-temporal interest point image sampling strategies and the human fixations, as well as their impact for visual recognition performance, but also demonstrate that human fixations can be accurately predicted, and when used in an end-to-end automatic system, leveraging some of the advanced computer vision practice, can lead to state of the art results.

Description: We consider the problem of parameter estimation and energy minimization for a region-based semantic segmentation model. The model divides the pixels of an image into non-overlapping connected regions, each of which is to a semantic class. In the context of energy minimization, the main problem we face is the large number of putative pixel-to-region assignments. We address this problem by designing an accurate linear programming based approach for selecting the best set of regions from a large dictionary. The dictionary is constructed by merging and intersecting segments obtained from multiple bottom-up over-segmentations. The linear program is solved efficiently using dual decomposition. In the context of parameter estimation, the main problem we face is the lack of fully supervised data. We address this issue by developing a principled framework for parameter estimation using diverse data. More precisely, we propose a latent structural support vector machine formulation, where the latent variables model any missing information in the human annotation. Of particular interest to us are three types of annotations: (i) images segmented using generic foreground or background classes; (ii) images with bounding boxes specified for objects; and (iii) images labeled to indicate the presence of a class. Using large, publicly available datasets we show that our methods are able to significantly improve the accuracy of the region-based model.

Description: In this paper we address the problem of finding the most probable state of a discrete Markov random field (MRF), also known as the MRF energy minimization problem. The task is known to be NP-hard in general and its practical importance motivates numerous approximate algorithms. We propose a submodular relaxation approach (SMR) based on a Lagrangian relaxation of the initial problem. Unlike the dual decomposition approach of Komodakis et al. [29] SMR does not decompose the graph structure of the initial problem but constructs a submodular energy that is minimized within the Lagrangian relaxation. Our approach is applicable to both pairwise and high-order MRFs and allows to take into account global potentials of certain types. We study theoretical properties of the proposed approach and evaluate it experimentally.

Description: Higher-order Markov Random Fields, which can capture important properties of natural images, have become increasingly important in computer vision. While graph cuts work well for first-order MRF’s, until recently they have rarely been effective for higher-order MRF’s. Ishikawa’s graph cut technique [1] , [2] shows great promise for many higher-order MRF’s. His method transforms an arbitrary higher-order MRF with binary labels into a first-order one with the same minima. If all the terms are submodular the exact solution can be easily found; otherwise, pseudoboolean optimization techniques can produce an optimal labeling for a subset of the variables. We present a new transformation with better performance than [1] , [2] , both theoretically and experimentally. While [1] , [2] transforms each higher-order term independently, we use the underlying hypergraph structure of the MRF to transform a group of terms at once. For $n$ binary variables, each of which appears in terms with $k$ other variables, at worst we produce $n$ non-submodular terms, while [1] , [2] produces $O(- k)$ . We identify a local completeness property under which our method perform even better, and show that under certain assumptions several important vision problems (including common variants of fusion moves) have this property. We show experimentally that our method produces smaller weight of non-submodular edges, and that this metric is directly related to the effectiveness of QPBO [3] . Running on the same field of experts dataset used in [1] , [2] we optimally label significantly more variables (96 versus 80 percent) and converge more rapidly to a lower energy. Preliminary experiments suggest that some other higher-order MRF’s used in stereo [4] and segmentation [5] are also locally complete and would thus benefit from our work.

Description: We introduce a conceptually novel structured prediction model, GPstruct , which is kernelized, non-parametric and Bayesian, by design. We motivate the model with respect to existing approaches, among others, conditional random fields (CRFs), maximum margin Markov networks (M $^3$ N), and structured support vector machines (SVMstruct), which embody only a subset of its properties. We present an inference procedure based on Markov Chain Monte Carlo. The framework can be instantiated for a wide range of structured objects such as linear chains, trees, grids, and other general graphs. As a proof of concept, the model is benchmarked on several natural language processing tasks and a video gesture segmentation task involving a linear chain structure. We show prediction accuracies for GPstruct which are comparable to or exceeding those of CRFs and SVMstruct.

Description: The papers in this special issue contain extended versions of works that were originally presented at the Brazilian Symposium on Bioinformatics 2013 (BSB 2013), held in Recife, Brazil, November 3-6, 2013.

Description: Computational methods for predicting protein-protein interactions are important tools that can complement high-throughput technologies and guide biologists in designing new laboratory experiments. The proteins and the interactions between them can be described by a network which is characterized by several topological properties. Information about proteins and interactions between them, in combination with knowledge about topological properties of the network, can be used for developing computational methods that can accurately predict unknown protein-protein interactions. This paper presents a supervised learning framework based on Bayesian inference for combining two types of information: i) network topology information, and ii) information related to proteins and the interactions between them. The motivation of our model is that by combining these two types of information one can achieve a better accuracy in predicting protein-protein interactions, than by using models constructed from these two types of information independently.

Description: We develop a theory of algebraic operations over linear and context-free grammars that makes it possible to combine simple “atomic” grammars operating on single sequences into complex, multi-dimensional grammars. We demonstrate the utility of this framework by constructing the search spaces of complex alignment problems on multiple input sequences explicitly as algebraic expressions of very simple one-dimensional grammars. In particular, we provide a fully worked frameshift-aware, semiglobal DNA-protein alignment algorithm whose grammar is composed of products of small, atomic grammars. The compiler accompanying our theory makes it easy to experiment with the combination of multiple grammars and different operations. Composite grammars can be written out in $ {rm L}^AT_{E}X$ for documentation and as a guide to implementation of dynamic programming algorithms. An embedding in Haskell as a domain-specific language makes the theory directly accessible to writing and using grammar products without the detour of an external compiler. Software and supplemental files available here: http://www.bioinf.uni-leipzig.de/Software/gramprod/

Description: Recent advancements in genomics and proteomics provide a solid foundation for understanding the pathogenesis of diabetes. Proteomics of diabetes associated pathways help to identify the most potent target for the management of diabetes. The relevant datasets are scattered in various prominent sources which takes much time to select the therapeutic target for the clinical management of diabetes. However, additional information about target proteins is needed for validation. This lacuna may be resolved by linking diabetes associated genes, pathways and proteins and it will provide a strong base for the treatment and planning management strategies of diabetes. Thus, a web source “Diabetes Associated Proteins Database (DAPD)” has been developed to link the diabetes associated genes, pathways and proteins using PHP, MySQL. The current version of DAPD has been built with proteins associated with different types of diabetes. In addition, DAPD has been linked to external sources to gain the access to more participatory proteins and their pathway network. DAPD will reduce the time and it is expected to pave the way for the discovery of novel anti-diabetic leads using computational drug designing for diabetes management. DAPD is open accessed via following url www.mkarthikeyan.bioinfoau.org/dapd.

Description: Determining the glycan topology automatically from mass spectra represents a great challenge. Existing methods fall into approximate and exact ones. The former including greedy and heuristic ones can reduce the computational complexity, but suffer from information lost in the procedure of glycan interpretation. The latter including dynamic programming and exhaustive enumeration are much slower than the former. In the past years, nearly all emerging methods adopted a tree structure to represent a glycan. They share such problems as repetitive peak counting in reconstructing a candidate structure. Besides, tree-based glycan representation methods often have to give different computational formulas for binary and ternary glycans. We propose a new directed acyclic graph structure for glycan representation. Based on it, this work develops a de novo algorithm to accurately reconstruct the tree structure iteratively from mass spectra with logical constraints and some known biosynthesis rules, by a single computational formula. The experiments on multiple complex glycans extracted from human serum show that the proposed algorithm can achieve higher accuracy to determine a glycan topology than prior methods without increasing computational burden.

Description: A crucial step in understanding the architecture of cells and tissues from microscopy images, and consequently explain important biological events such as wound healing and cancer metastases, is the complete extraction and enumeration of individual filaments from the cellular cytoskeletal network. Current efforts at quantitative estimation of filament length distribution, architecture and orientation from microscopy images are predominantly limited to visual estimation and indirect experimental inference. Here we demonstrate the application of a new algorithm to reliably estimate centerlines of biological filament bundles and extract individual filaments from the centerlines by systematically disambiguating filament intersections. We utilize a filament enhancement step followed by reverse diffusion based filament localization and an integer programming based set combination to systematically extract accurate filaments automatically from microscopy images. Experiments on simulated and real confocal microscope images of flat cells (2D images) show efficacy of the new method.

Description: The Local/Global Alignment (Zemla, 2003), or LGA, is a popular method for the comparison of protein structures. One of the two components of LGA requires us to compute the longest common contiguous segments between two protein structures. That is, given two structures $A=(a_1, ldots , a_n)$ and $B=(b_1, ldots , b_n)$ where $a_k$ , $b_kin mathbb {R}^3$ , we are to find, among all the segments $f=(a_i,ldots ,a_j)$ and $g=(b_i,ldots ,b_j)$ that fulfill a certain criterion regarding their similarity, those of the maximum length. We consider the following criteria: (1) the root mean squared deviation (RMSD) between $f$ and $g$ is to be within a given $tin mathbb {R}$ ; (2) $f$ and $g$ can be superposed such that for each $k$ , $ile kle j$ , $Vert a_k-b_kVert le t$ for a given $tin mathbb {R}$ . We give an algorithm of $O(n;log; n+n{{boldsymbol l}})$ time complexity when the first requirement applies, where ${{boldsymbol l}}$ is the maximum length of the segments fulfilling the criterion. We show an FPTAS which, for any

Description: Noise can induce various dynamical behaviors in nonlinear systems. White noise perturbed systems have been extensively investigated during the last decades. In gene networks, experimentally observed extrinsic noise is colored. As an attempt, we investigate the genetic toggle switch systems perturbed by colored extrinsic noise and with kinetic parameters. Compared with white noise perturbed systems, we show there also exists optimal colored noise strength to induce the best stochastic switch behaviors in the single toggle switch, and the best synchronized switching in the networked systems, which demonstrate that noise-induced optimal switch behaviors are widely in existence. Moreover, under a wide range of system parameter regions, we find there exist wider ranges of white and colored noises strengths to induce good switch and synchronization behaviors, respectively; therefore, white noise is beneficial for switch and colored noise is beneficial for population synchronization. Our observations are very robust to extrinsic stimulus strength, cell density, and diffusion rate. Finally, based on the Waddington’s epigenetic landscape and the Wiener-Khintchine theorem, physical mechanisms underlying the observations are interpreted. Our investigations can provide guidelines for experimental design, and have potential clinical implications in gene therapy and synthetic biology.

Description: Revealing the underlying evolutionary mechanism plays an important role in understanding protein interaction networks in the cell. While many evolutionary models have been proposed, the problem about applying these models to real network data, especially for differentiating which model can better describe evolutionary process for the observed network remains a challenge. The traditional way is to use a model with presumed parameters to generate a network, and then evaluate the fitness by summary statistics, which however cannot capture the complete network structures information and estimate parameter distribution. In this work, we developed a novel method based on Approximate Bayesian Computation and modified Differential Evolution algorithm (ABC-DEP) that is capable of conducting model selection and parameter estimation simultaneously and detecting the underlying evolutionary mechanisms for PPI networks more accurately. We tested our method for its power in differentiating models and estimating parameters on simulated data and found significant improvement in performance benchmark, as compared with a previous method. We further applied our method to real data of protein interaction networks in human and yeast. Our results show duplication attachment model as the predominant evolutionary mechanism for human PPI networks and Scale-Free model as the predominant mechanism for yeast PPI networks.

Description: Single nucleotide polymorphisms, a dominant type of genetic variants, have been used successfully to identify defective genes causing human single gene diseases. However, most common human diseases are complex diseases and caused by gene-gene and gene-environment interactions. Many SNP-SNP interaction analysis methods have been introduced but they are not powerful enough to discover interactions more than three SNPs. The paper proposes a novel method that analyzes all SNPs simultaneously. Different from existing methods, the method regards an individual’s genotype data on a list of SNPs as a point with a unit of energy in a multi-dimensional space, and tries to find a new coordinate system where the energy distribution difference between cases and controls reaches the maximum. The method will find different multiple SNPs combinatorial patterns between cases and controls based on the new coordinate system. The experiment on simulated data shows that the method is efficient. The tests on the real data of age-related macular degeneration (AMD) disease show that it can find out more significant multi-SNP combinatorial patterns than existing methods.

Description: Disulfide connectivity is an important protein structural characteristic. Accurately predicting disulfide connectivity solely from protein sequence helps to improve the intrinsic understanding of protein structure and function, especially in the post-genome era where large volume of sequenced proteins without being functional annotated is quickly accumulated. In this study, a new feature extracted from the predicted protein 3D structural information is proposed and integrated with traditional features to form discriminative features. Based on the extracted features, a random forest regression model is performed to predict protein disulfide connectivity. We compare the proposed method with popular existing predictors by performing both cross-validation and independent validation tests on benchmark datasets. The experimental results demonstrate the superiority of the proposed method over existing predictors. We believe the superiority of the proposed method benefits from both the good discriminative capability of the newly developed features and the powerful modelling capability of the random forest. The web server implementation, called TargetDisulfide, and the benchmark datasets are freely available at: http://csbio.njust.edu.cn/bioinf/TargetDisulfide for academic use.

Description: Proteins are molecules that form the mass of living beings. These proteins exist in dissociated forms like amino-acids and carry out various biological functions, in fact, almost all body reactions occur with the participation of proteins. This is one of the reasons why the analysis of proteins has become a major issue in biology. In a more concrete way, the identification of conserved patterns in a set of related protein sequences can provide relevant biological information about these protein functions. In this paper, we present a novel algorithm based on teaching learning based optimization (TLBO) combined with a local search function specialized to predict common patterns in sets of protein sequences. This population-based evolutionary algorithm defines a group of individuals (solutions) that enhance their knowledge (quality) by means of different learning stages. Thus, if we correctly adapt it to the biological context of the mentioned problem, we can get an acceptable set of quality solutions. To evaluate the performance of the proposed technique, we have used six instances composed of different related protein sequences obtained from the PROSITE database. As we will see, the designed approach makes good predictions and improves the quality of the solutions found by other well-known biological tools.

Description: We introduce Supervised Variational Relevance Learning (Suvrel), a variational method to determine metric tensors to define distance based similarity in pattern classification, inspired in relevance learning. The variational method is applied to a cost function that penalizes large intraclass distances and favors small interclass distances. We find analytically the metric tensor that minimizes the cost function. Preprocessing the patterns by doing linear transformations using the metric tensor yields a dataset which can be more efficiently classified. We test our methods using publicly available datasets, for some standard classifiers. Among these datasets, two were tested by the MAQC-II project and, even without the use of further preprocessing, our results improve on their performance.

Description: Bandwidth reservation has been recognized as a value-added service to the cloud provider in recent years. We consider an open market of cloud bandwidth reservation, in which cloud providers offer bandwidth reservation services to cloud tenants, especially online streaming service providers, who have strict requirements on the amount of bandwidth to guarantee their quality of services. In this paper, we model the open market as a double-sided auction, and propose the first family of ST rategy-proof double A uctions for multi-cloud, multi-tenant bandwidth R eservation (STAR). STAR contains two auction mechanisms. The first one, STAR-Grouping, divides the tenants into groups by a bid-independent way, and carefully matches the cloud providers with the tenant groups to form good trades. The second one, STAR-Padding, greedily matches the cloud providers with the tenants, and fills the partially reserved cloud provider(s) with a novel virtual padding tenant who can be a component of the auctioneer. Our analysis shows that both of the two auction mechanisms achieve strategy-proofness and ex-post budget balance. Our evaluation results show that they achieve good performance in terms of social welfare, cloud bandwidth utilization, and tenant satisfaction ratio.

Description: In a distributed real-time system (DRTS), jobs are often executed on a number of processors and must complete by their end-to-end deadlines. Job deadline requirements may be violated if resource competition among different jobs on a given processor is not considered. This paper introduces a distributed, locally optimal algorithm to assign local deadlines to the jobs on each processor without any restrictions on the mappings of the applications to the processors in the distributed soft real-time system. Improvedschedulability results are achieved by the algorithm since disparate workloads among the processors due to competing jobs havingdifferent paths are considered. Given its distributed nature, the proposed algorithm is adaptive to dynamic changes of the applications and avoids the overhead of global clock synchronization. In order to make the proposed algorithm more practical, two derivatives of the algorithm are proposed and compared. Simulation results based on randomly generated workloads indicate that the proposed approach outperforms existing work both in terms of the number of feasible jobs (between 51% and 313% on average) and the number of feasible task sets (between 12% and 71% on average).

Description: Reproducibility, i.e. getting bitwise identical floating point results from multiple runs of the same program, is a property that many users depend on either for debugging or correctness checking in many codes [10] . However, the combination of dynamic scheduling of parallel computing resources, and floating point nonassociativity, makes attaining reproducibility a challenge even for simple reduction operations like computing the sum of a vector of numbers in parallel. We propose a technique for floating point summation that is reproducible independent of the order of summation. Our technique uses Rump’s algorithm for error-free vector transformation [7] , and is much more efficient than using (possibly very) high precision arithmetic. Our algorithm reproducibly computes highly accurate results with an absolute error bound of $n cdot 2^{-28} cdot macheps cdot max _i |v_i|$ at a cost of $7n$ FLOPs and a small constant amount of extra memory usage. Higher accuracies are also possible by increasing the number of error-free transformations. As long as all operations are performed in to-nearest rounding mode, results computed by the proposed algorithms are reproducible for any run on any platform. In particular, our algorithm requires the minimum number of reductions, i.e. one reduction of an array of six double precision floating point numbers per sum, and hence is well suited for massively parallel environments.

Description: In recent years, embedded dynamic random-access memory (eDRAM) technology has been implemented in last-level caches due to its low leakage energy consumption and high density. However, the fact that eDRAM presents slower access time than static RAM (SRAM) technology has prevented its inclusion in higher levels of the cache hierarchy. This paper proposes to mingle SRAM and eDRAM banks within the data array of second-level (L2) caches. The main goal is to achieve the best trade-off among performance, energy, and area. To this end, two main directions have been followed. First, this paper explores the optimal percentage of banks for each technology. Second, the cache controller is redesigned to deal with performance and energy. Performance is addressed by keeping the most likely accessed blocks in fast SRAM banks. In addition, energy savings are further enhanced by avoiding unnecessary destructive reads of eDRAM blocks. Experimental results show that, compared to a conventional SRAM L2 cache, a hybrid approach requiring similar or even lower area speedups the performance on average by 5.9 percent, while the total energy savings are by 32 percent. For a 45 nm technology node, the energy-delay-area product confirms that a hybrid cache is a better design than the conventional SRAM cache regardless of the number of eDRAM banks, and also better than a conventional eDRAM cache when the number of SRAM banks is an eighth of the total number of cache banks.

Description: Nearly all of the currently used signature schemes, such as RSA or DSA, are based either on the factoring assumption or the presumed intractability of the discrete logarithm problem. As a consequence, the appearance of quantum computers or algorithmic advances on these problems may lead to the unpleasant situation that a large number of today’s schemes will most likely need to be replaced with more secure alternatives. In this work we present such an alternative—an efficient signature scheme whose security is derived from the hardness of lattice problems. It is based on recent theoretical advances in lattice-based cryptography and is highly optimized for practicability and use in embedded systems. The public and secret keys are roughly $1.5$  kB and $0.3$  kB long, while the signature size is approximately $1.1$  kB for a security level of around $80$ bits. We provide implementation results on reconfigurable hardware (Spartan/Virtex-6) and demonstrate that the scheme is scalable, has low area consumption, and even outperforms classical schemes.

Description: With the rising demands on cloud services, the electricity consumption has been increasing drastically as the main operational expenditure (OPEX) to data center providers. The geographical heterogeneity of electricity prices motivates us to study the task placement problem over geo-distributed data centers. We exploit the dynamic frequency scaling technique and formulate an optimization problem that minimizes OPEX while guaranteeing the quality-of-service, i.e., the expected response time of tasks. Furthermore, an optimal solution is discovered for this formulated problem. The experimental results show that our proposal achieves much higher cost-efficiency than the traditional resizing scheme, i.e., by activating/deactivating certain servers in data centers.

Description: A new methodology for DRAM performance analysis has been proposed based on accurate characterization of DRAM bus cycles. The proposed methodology allows cycle-accurate performance analysis of arbitrary DRAM traces, obviates the need for functional simulations, allows accurate estimation of DRAM performance maximum, and enables root causing of suboptimal DRAM operation.

Description: Improving the quality of degraded images is a key problem in image processing, but the breadth of the problem leads to domain-specific approaches for tasks such as super-resolution and compression artifact removal. Recent approaches have shown that a general approach is possible by learning application-specific models from examples; however, learning models sophisticated enough to generate high-quality images is computationally expensive, and so specific per-application or per-dataset models are impractical. To solve this problem, we present an efficient semi-local approximation scheme to large-scale Gaussian processes. This allows efficient learning of task-specific image enhancements from example images without reducing quality. As such, our algorithm can be easily customized to specific applications and datasets, and we show the efficiency and effectiveness of our approach across five domains: single-image super-resolution for scene, human face, and text images, and artifact removal in JPEG- and JPEG 2000-encoded images.

Description: Parsimony, including sparsity and low rank, has been shown to successfully model data in numerous machine learning and signal processing tasks. Traditionally, such modeling approaches rely on an iterative algorithm that minimizes an objective function with parsimony-promoting terms. The inherently sequential structure and data-dependent complexity and latency of iterative optimization constitute a major limitation in many applications requiring real-time performance or involving large-scale data. Another limitation encountered by these modeling techniques is the difficulty of their inclusion in discriminative learning scenarios. In this work, we propose to move the emphasis from the model to the pursuit algorithm, and develop a process-centric view of parsimonious modeling, in which a learned deterministic fixed-complexity pursuit process is used in lieu of iterative optimization. We show a principled way to construct learnable pursuit process architectures for structured sparse and robust low rank models, derived from the iteration of proximal descent algorithms. These architectures learn to approximate the exact parsimonious representation at a fraction of the complexity of the standard optimization methods. We also show that appropriate training regimes allow to naturally extend parsimonious models to discriminative settings. State-of-the-art results are demonstrated on several challenging problems in image and audio processing with several orders of magnitude speed-up compared to the exact optimization algorithms.

Description: CANDECOMP/PARAFAC (CP) tensor factorization of incomplete data is a powerful technique for tensor completion through explicitly capturing the multilinear latent factors. The existing CP algorithms require the tensor rank to be manually specified, however, the determination of tensor rank remains a challenging problem especially for CP rank . In addition, existing approaches do not take into account uncertainty information of latent factors, as well as missing entries. To address these issues, we formulate CP factorization using a hierarchical probabilistic model and employ a fully Bayesian treatment by incorporating a sparsity-inducing prior over multiple latent factors and the appropriate hyperpriors over all hyperparameters, resulting in automatic rank determination. To learn the model, we develop an efficient deterministic Bayesian inference algorithm, which scales linearly with data size. Our method is characterized as a tuning parameter-free approach, which can effectively infer underlying multilinear factors with a low-rank constraint, while also providing predictive distributions over missing entries. Extensive simulations on synthetic data illustrate the intrinsic capability of our method to recover the ground-truth of CP rank and prevent the overfitting problem, even when a large amount of entries are missing. Moreover, the results from real-world applications, including image inpainting and facial image synthesis, demonstrate that our method outperforms state-of-the-art approaches for both tensor factorization and tensor completion in terms of predictive performance.

Description: Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224 $times$ 224) input image. This requirement is “artificial” and may reduce the recognition accuracy for the images or sub-images of an arbitrary size/scale. In this work, we equip the networks with another pooling strategy, “spatial pyramid pooling”, to eliminate the above requirement. The new network structure, called SPP-net, can generate a fixed-length representation regardless of image size/scale. Pyramid pooling is also robust to object deformations. With these advantages, SPP-net should in general improve all CNN-based image classification methods. On the ImageNet 2012 dataset, we demonstrate that SPP-net boosts the accuracy of a variety of CNN architectures despite their different designs. On the Pascal VOC 2007 and Caltech101 datasets, SPP-net achieves state-of-the-art classification results using a single full-image representation and no fine-tuning. The power of SPP-net is also significant in object detection. Using SPP-net, we compute the feature maps from the entire image only once, and then pool features in arbitrary regions (sub-images) to generate fixed-length representations for training the detectors. This method avoids repeatedly computing the convolutional features. In processing test images, our method is 24-102 $times$ faster than the R-CNN method, while achieving better or comparable accuracy on Pascal VOC 2007. In ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2014, our methods rank #2 in object detection and #3 in image classification among all 38 teams. This manuscript also introduces the improvement made for this - ompetition.

Description: We present efficient graph cut algorithms for three problems: (1) finding a region in an image, so that the histogram (or distribution) of an image feature within the region most closely matches a given model; (2) co-segmentation of image pairs and (3) interactive image segmentation with a user-provided bounding box. Each algorithm seeks the optimum of a global cost function based on the Bhattacharyya measure, a convenient alternative to other matching measures such as the Kullback–Leibler divergence. Our functionals are not directly amenable to graph cut optimization as they contain non-linear functions of fractional terms, which make the ensuing optimization problems challenging. We first derive a family of parametric bounds of the Bhattacharyya measure by introducing an auxiliary labeling. Then, we show that these bounds are auxiliary functions of the Bhattacharyya measure, a result which allows us to solve each problem efficiently via graph cuts. We show that the proposed optimization procedures converge within very few graph cut iterations. Comprehensive and various experiments, including quantitative and comparative evaluations over two databases, demonstrate the advantages of the proposed algorithms over related works in regard to optimality, computational load, accuracy and flexibility.

Description: Genes can participate in multiple biological processes at a time and thus their expression can be seen as a composition of the contributions from the active processes. Biclustering under a plaid assumption allows the modeling of interactions between transcriptional modules or biclusters (subsets of genes with coherence across subsets of conditions) by assuming an additive composition of contributions in their overlapping areas. Despite the biological interest of plaid models, few biclustering algorithms consider plaid effects and, when they do, they place restrictions on the allowed types and structures of biclusters, and suffer from robustness problems by seizing exact additive matchings. We propose BiP (Biclustering using Plaid models), a biclustering algorithm with relaxations to allow expression levels to change in overlapping areas according to biologically meaningful assumptions (weighted and noise-tolerant composition of contributions). BiP can be used over existing biclustering solutions (seizing their benefits) as it is able to recover excluded areas due to unaccounted plaid effects and detect noisy areas non-explained by a plaid assumption, thus producing an explanatory model of overlapping transcriptional activity. Experiments on synthetic data support BiP’s efficiency and effectiveness. The learned models from expression data unravel meaningful and non-trivial functional interactions between biological processes associated with putative regulatory modules.

Description: We propose a classifier system called iPFPi that predicts the functions of un-annotated proteins. iPFPi assigns an un-annotated protein $P$ the functions of GO annotation terms that are semantically similar to $P$ . An un-annotated protein $P$ and a GO annotation term $T$ are represented by their characteristics. The characteristics of $P$ are GO terms found within the abstracts of biomedical literature associated with $P$ . The characteristics of $T$ are GO terms found within the abstracts of biomedical literature associated with the proteins annotated with the function of $T$ . Let - F$ and $Fprime $ be the important (dominant) sets of characteristic terms representing $T$ and $P$ , respectively. iPFPi would annotate $P$ with the function of $T$ , if $F$ and $Fprime $ are semantically similar. We constructed a novel semantic similarity measure that takes into consideration several factors, such as the dominance degree of each characteristic term $t$ in set $F$