ALBERT

All Library Books, journals and Electronic Records Telegrafenberg

X
feed icon rss

Your email was sent successfully. Check your inbox.

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

Proceed reservation?

Export
  • 1
    Electronic Resource
    Electronic Resource
    A generalization of the Hoffman - Lovász upper boundon the independence number of a regular graph (1998)
    Springer
    Annals of operations research 81 (1998), S. 307-320 
    Details
    ISSN: 1572-9338
    Source: Springer Online Journal Archives 1860-2000
    Topics: Mathematics , Economics
    Notes: Abstract A family of quadratic programming problems whose optimal values are upper boundson the independence number of a graph is introduced. Among this family, the quadraticprogramming problem which gives the best upper bound is identified. Also the proof thatthe upper bound introduced by Hoffman and Lovász for regular graphs is a particular caseof this family is given. In addition, some new results characterizing the class of graphs forwhich the independence number attains the optimal value of the above best upper bound aregiven. Finally a polynomial-time algorithm for approximating the size of the maximumindependent set of an arbitrary graph is described and the computational experiments carriedout on 36 DIMACS clique benchmark instances are reported.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1018965309522
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 2
    Electronic Resource
    Electronic Resource
    Unifying instance-based and rule-based induction (1996)
    Springer
    Machine learning 24 (1996), S. 141-168 
    Details
    ISSN: 0885-6125
    Keywords: Concept learning ; multi-strategy learning ; rule induction ; instance-based learning ; nearest-neighbor classification ; case-based reasoning
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Several well-developed approaches to inductive learning low exist, but each has specific limitations that are hard to overcome. Multi-strategy learning attempts to tackle this problem combining multiple methods in one algorithm. This article describes a unification of two widely-used empirical approaches: rule induction and instance-based learning. In the new algorithm, instances are treated as maximally specific rules, and classification is oerformed using a best-match strategy. Rules are learned by gradually generalizing instances until no improvement in apparent accuracy is obtained. Theoretical analysis shows this approach to be efficient. It is implemented in the RISE 3.1 system. In an extensive empirical study, RISE consistently achieves higher accuracies than state-of-the-art representatives of both its parent approaches (PEBLS and CN2), as well as a decision tree learner (C4.5). Lesion studies show that eachoof RISE's components is essential to this performance. Most significantly, in 14 of the 30 domains studied, RISE is more accurate than the best of PEBLS and CN2, showing that a significant synergy can be obtained by combining multiple empirical methods.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF00058656
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 3
    Electronic Resource
    Electronic Resource
    On the Optimality of the Simple Bayesian Classifier under Zero-One Loss (1997)
    Springer
    Machine learning 29 (1997), S. 103-130 
    Details
    ISSN: 0885-6125
    Keywords: Simple Bayesian classifier ; naive Bayesian classifier ; zero-one loss ; optimal classification ; induction with attribute dependences
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract The simple Bayesian classifier is known to be optimal when attributes are independent given the class, but the question of whether other sufficient conditions for its optimality exist has so far not been explored. Empirical results showing that it performs surprisingly well in many domains containing clear attribute dependences suggest that the answer to this question may be positive. This article shows that, although the Bayesian classifier's probability estimates are only optimal under quadratic loss if the independence assumption holds, the classifier itself can be optimal under zero-one loss (misclassification rate) even when this assumption is violated by a wide margin. The region of quadratic-loss optimality of the Bayesian classifier is in fact a second-order infinitesimal fraction of the region of zero-one optimality. This implies that the Bayesian classifier has a much greater range of applicability than previously thought. For example, in this article it is shown to be optimal for learning conjunctions and disjunctions, even though they violate the independence assumption. Further, studies in artificial domains show that it will often outperform more powerful classifiers for common training set sizes and numbers of attributes, even if its bias is a priori much less appropriate to the domain. This article's results also imply that detecting attribute dependence is not necessarily the best way to extend the Bayesian classifier, and this is also verified empirically.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1007413511361
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 4
    Electronic Resource
    Electronic Resource
    Unifying Instance-Based and Rule-Based Induction (1996)
    Springer
    Machine learning 24 (1996), S. 141-168 
    Details
    ISSN: 0885-6125
    Keywords: Concept learning ; multi-strategy learning ; rule induction ; instance-based learning ; nearest-neighbor classification ; case-based reasoning
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Several well-developed approaches to inductive learning now exist, but each has specific limitations that are hard to overcome. Multi-strategy learning attempts to tackle this problem by combining multiple methods in one algorithm. This article describes a unification of two widely-used empirical approaches: rule induction and instance-based learning. In the new algorithm, instances are treated as maximally specific rules, and classification is performed using a best-match strategy. Rules are learned by gradually generalizing instances until no improvement in apparent accuracy is obtained. Theoretical analysis shows this approach to be efficient. It is implemented in the RISE 3.1 system. In an extensive empirical study, RISE consistently achieves higher accuracies than state-of-the-art representatives of both its parent approaches (PEBLS and CN2), as well as a decision tree learner (C4.5). Lesion studies show that each of RISE‘s components is essential to this performance. Most significantly, in 14 of the 30 domains studied, RISE is more accurate than the best of PEBLS and CN2, showing that a significant synergy can be obtained by combining multiple empirical methods.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1018006431188
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 5
    Electronic Resource
    Electronic Resource
    Hemerocallis as bioindicator of fluoride pollution in tropical countries (1995)
    Springer
    Environmental monitoring and assessment 35 (1995), S. 27-42 
    Details
    ISSN: 1573-2959
    Source: Springer Online Journal Archives 1860-2000
    Topics: Energy, Environment Protection, Nuclear Power Engineering
    Notes: Abstract In the frame of an active monitoring study at the Serra do Mar near the industrial pool of Cubatão, Brazil,Hemerocallis was tested for its suitability as bioindicator of airborne fluoride pollution. In a screening experiment with various cultivars comparison of susceptibility, correlation of visible injury and foliar fluoride concentration as well as comparison with exposure ofGladiolus gave best results for theHemerocallis cultivar ‘Red Moon’. When exposed simultaneously foliar fluoride accumulation ofHemerocallis showed a highly significant linear correlation with fluoride content ofLolium multiflorum, the ‘standardized grass culture’ andGladiolus, well-known bioindicator species for fluoride impact. With respect to the extent of foliar injuryHemerocallis was less sensitive thanGladiolus, in terms of accumulation capacity it ranged betweenLolium andGladiolus. In general, the results of the biomonitoring study proved that the Atlantic Forest vegetation in a valley downwind from the Cubatão fertilizer industries is still suffering from severe fluoride pollution.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF00552573
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 6
    Electronic Resource
    Electronic Resource
    Hemerocallis as bioindicator of fluoride pollution in tropical countries (1995)
    Springer
    Environmental monitoring and assessment 35 (1995), S. 27-42 
    Details
    ISSN: 1573-2959
    Source: Springer Online Journal Archives 1860-2000
    Topics: Energy, Environment Protection, Nuclear Power Engineering
    Notes: Abstract In the frame of an active monitoring study at the Serra do Mar near the industrial pool of Cubatão, Brazil,Hemerocallis was tested for its suitability as bioindicator of airborne fluoride pollution. In a screening experiment with various cultivars comparison of susceptibility, correlation of visible injury and foliar fluoride concentration as well as comparison with exposure ofGladiolus gave best results for theHemerocallis cultivar ‘Red Moon’. When exposed simultaneously foliar fluoride accumulation ofHemerocallis showed a highly significant linear correlation with fluoride content ofLolium multiflorum, the ‘standardized grass culture’ andGladiolus, well-known bioindicator species for fluoride impact. With respect to the extent of foliar injuryHemerocallis was less sensitive thanGladiolus, in terms of accumulation capacity it ranged betweenLolium andGladiolus. In general, the results of the biomonitoring study proved that the Atlantic Forest vegetation in a valley downwind from the Cubatão fertilizer industries is still suffering from severe fluoride pollution.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF02396408
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 7
    Electronic Resource
    Electronic Resource
    Phytoplankton species composition is more sensitive than OECD criteria to the trophic status of three Brazilian tropical lakes (1998)
    Springer
    Hydrobiologia 369-370 (1998), S. 59-71 
    Details
    ISSN: 1573-5117
    Keywords: trophic gradient ; phytoplankton ; tropical freshwater environments ; species assemblages ; shallow lakes
    Source: Springer Online Journal Archives 1860-2000
    Topics: Biology
    Notes: Abstract We compared the structure and function of the phytoplankton community in three tropical systems in Brazil: an oligo-mesotrophic floodplain lake; an eutrophic reservoir; and a hypereutrophic coastal lagoon. Phytoplankton biomass increased along this trophic gradient averaging 2.6, 6.2 and 31.6 mm3 l-1 in the lake, reservoir and lagoon, respectively. Similarly, production increased from 427 to 918 gC m-2 y-1. Along the trophic gradient, diversity and species richness of phytoplankton decreased. There was, however, no relationship between trophy and rates of change of phytoplankton communities or the ratio of maximum/mean biomass. Phytoplankton size varied between systems with small algae (2–20 µm) dominating in the hypereutrophic lagoon and larger algae (20–200 µm) dominating in the other systems. Many of the trophic indices developed for temperate areas could not be applied to these tropical systems since there was no clear relationship between Secchi depth, chlorophyll, or TP and trophic status. Phytoplankton species may be more useful than these trophic indices to the classification of the condition of tropical lakes.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1017047221384
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 8
    Electronic Resource
    Electronic Resource
    Taxonomic remarks on planktonic phytoflagellates in a hypertrophic tropical lagoon (Brazil) (1998)
    Springer
    Hydrobiologia 369-370 (1998), S. 297-313 
    Details
    ISSN: 1573-5117
    Keywords: planktonic phytoflagellates ; taxonomy ; seasonality ; hypertrophic brackish water ; tropical coastal lagoon ; Brazil
    Source: Springer Online Journal Archives 1860-2000
    Topics: Biology
    Notes: Abstract The phototrophic flagellate flora of the Barra Lagoon (22°57′ S and 42°47′ W), Rio de Janeiro State, southeastern Brazil, is described. The lagoon is a shallow, oligohaline, hypertrophic ecosystem in which Cyanophyceae, Chlorophyceae and phytoflagellates are dominant. Between October 1990 and August 1993, weekly integrated samples were collected from a bay, using a plexiglass tube, 8 cm diameter and 1m length. All identifications, descriptions and measurements were carried out on live or in Lugol-fixed material. A total of 30 taxa, belonging to Euglenophyceae (5), Cryptophyceae (7), Raphidophyceae (1), Dinophyceae (4), Chrysophyceae (3), Prymnesiophyceae (2), Prasinophyceae (7) and Chlorophyceae (1) were identified. All the phytoflagellate species identified have been recorded previously from temperate sites. Nine of them were registered in a tropical water for the first time, suggesting that they have much broader distributions. Gymnodinium sanguineum, Pavlova lutheri and Pyramimonas grossii were the most frequently observed phytoflagellates in this study. The seasonal occurrence and some environmental requirements of selected phytoflagellates species are discussed.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1017097826410
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 9
    Electronic Resource
    Electronic Resource
    Coulomb interaction symmetries and the Mayer series in the two-dimensional dipole gas (1997)
    Springer
    Journal of statistical physics 87 (1997), S. 877-889 
    Details
    ISSN: 1572-9613
    Keywords: Coulomb interaction symmetries ; Mayer series ; two-dimensional dipole gas
    Source: Springer Online Journal Archives 1860-2000
    Topics: Physics
    Notes: Abstract We study the Mayer series of the two-dimensional dipole gas in the high-temperature, low-density regime. Without performing any multiscale analysis, we obtain bounds showing that the Mayer coefficients are finite in the thermodynamic limit. These bounds are obtained by exploiting a particular partial symmetry of the interaction (which we nameO-symmetry), already used in some problems related to the two-dimensional Coulomb gas. By direct bounds on some Mayer graphs we also conjecture that any technique based uniquely on theO-symmetry will not be sufficient to prove analyticity of the series.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF02181248
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 10
    Electronic Resource
    Electronic Resource
    Fluoride impact on native tree species of the atlantic forest near Cubatão, Brazil (1996)
    Springer
    Water, air & soil pollution 87 (1996), S. 57-71 
    Details
    ISSN: 1573-2932
    Source: Springer Online Journal Archives 1860-2000
    Topics: Energy, Environment Protection, Nuclear Power Engineering
    Notes: Abstract Air pollutant emissions from the industrial complex of Cubatão, Brazil, have led to a severe deterioration of the Atlantic Forest ecosystem. In a field study, leaves of the tree speciesTibouchina pulchra, Miconia pyrifolia, andCecropia glazioui were collected at four sites with different pollution characteristics. Leaf fluoride contents of the three species were found to be highly elevated in a valley near to fertilizer factories. In an area further from the emission sources, which in the past had been affected by fluoride pollution, fluoride concentrations inTibouchina andMiconia continued to be elevated. Preliminary exposure experiments using Tibouchina seedlings as accumulative indicators are reported.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF00696829
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...