EUSFLAT Conf.Pub Date : 2011-08-06DOI: 10.2991/eusflat.2011.46
C. Moewes, R. Kruse
{"title":"On the usefulness of fuzzy SVMs and the extraction of fuzzy rules from SVMs","authors":"C. Moewes, R. Kruse","doi":"10.2991/eusflat.2011.46","DOIUrl":"https://doi.org/10.2991/eusflat.2011.46","url":null,"abstract":"In this paper we reason about the usefulness of two recent trends in fuzzy methods in machine learning. That is, we discuss both fuzzy support vector machines (FSVMs) and the extraction of fuzzy rules from SVMs. First, we show that an FSVM is identical to a special type of SVM. Second, we categorize and analyze existing approaches to obtain fuzzy rules from SVMs. Finally, we question both trends and conclude with more promising alternatives.","PeriodicalId":403191,"journal":{"name":"EUSFLAT Conf.","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130601990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
EUSFLAT Conf.Pub Date : 2011-08-06DOI: 10.2991/eusflat.2011.72
Arne-Jens Hempel, G. Herbst, S. Bocklisch
{"title":"Modelling and aggregation of heterogeneous fuzzy data","authors":"Arne-Jens Hempel, G. Herbst, S. Bocklisch","doi":"10.2991/eusflat.2011.72","DOIUrl":"https://doi.org/10.2991/eusflat.2011.72","url":null,"abstract":"This article proposes an individual fuzzy modelling and treatment of data allowing for the specific uncertainty of each datum. A modelling approach based on parametric fuzzy sets is being introduced which can be employed to model both data with individual uncertainties as well as abstract phenomena in a feature space (classes). An aggregation procedure is being presented which takes the individual characteristics of all learning objects into account, resulting in a fuzzy description of the same, interpretable structure. Examples are given using both synthetic and real-world data.","PeriodicalId":403191,"journal":{"name":"EUSFLAT Conf.","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130685949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
EUSFLAT Conf.Pub Date : 2011-08-06DOI: 10.2991/eusflat.2011.44
B. Paris, J. Eynard, Michaël Salvador, S. Grieu
{"title":"Fuzzy logic as a useful tool for managing resources in multi-energy buildings","authors":"B. Paris, J. Eynard, Michaël Salvador, S. Grieu","doi":"10.2991/eusflat.2011.44","DOIUrl":"https://doi.org/10.2991/eusflat.2011.44","url":null,"abstract":"The present paper focuses on using fuzzy logic as a useful tool to manage energy resources in buildings and to reduce their energy impact. To that purpose, one requires the design and the implementation of efficient and readily adaptable control schemes. As everyone knows, fuzzy logic allows taking advantage of the flexibility offered by linguistic reasoning. With this kind of approaches, both the specific use of a building and the specificities of a proposed energy management strategy can be easily considered when designing or adjusting the proposed control schemes. First, a hybrid PID-fuzzy scheme is used for managing resources in multi-energy buildings, as the combination of two usual control structures based on PID and fuzzy controllers: the \"parallel\" structure and the \"fuzzy supervision\" of a PID controller. Next, fuzzy logic is used to define scenarios dealing with building occupancy and to control the ventilation system of a building, with the aim of reducing its energy impact on the grid.","PeriodicalId":403191,"journal":{"name":"EUSFLAT Conf.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130733051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
EUSFLAT Conf.Pub Date : 2011-08-06DOI: 10.2991/eusflat.2011.91
Anett Hoppe, R. Seising, A. Nürnberger, Constanze Wenzel
{"title":"Wisdom - the blurry top of human cognition in the DIKW-model?","authors":"Anett Hoppe, R. Seising, A. Nürnberger, Constanze Wenzel","doi":"10.2991/eusflat.2011.91","DOIUrl":"https://doi.org/10.2991/eusflat.2011.91","url":null,"abstract":"Wisdom is an ancient concept, that experiences a renaissance since the last century throughout several scientific communities. In each of them it is interpreted in rather different ways - from a key ability to succesful aging to a human peak perfomance transcending mere knowledge. As a result, miscellaneous definitions and models exist. There is for instance the DIKW-hierarchy that tempts to integrate the concept of wisdom into information science, still without providing a proper definition. The work at hand tries to sum up current approaches (out of computer science as well as others) with a focus on their usefulness for the positioning of wisdom atop the DIKW-model and the actual usefulness of the term for information science. At the end, with our characterization of wisdom as a fluctuating concept, we propose fuzzy sets to model wisdom as a scientific concept.","PeriodicalId":403191,"journal":{"name":"EUSFLAT Conf.","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133616405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
EUSFLAT Conf.Pub Date : 2011-08-06DOI: 10.2991/eusflat.2011.37
Jana Kelemenova
{"title":"The Inclusion-Exclusion Principle On the Set of IF-sets","authors":"Jana Kelemenova","doi":"10.2991/eusflat.2011.37","DOIUrl":"https://doi.org/10.2991/eusflat.2011.37","url":null,"abstract":"P. Grzegorzewski [3] has worked the probability version of the inclusion-exclusion principle and made a generalization for IF-events. He had applied two versions of the generalized formula, corresponding to dierent t-conorms and so defined the union of IF-events. This paper contains the generalization of the Grzegorzewski theorem. We prove it for mappings from the set of IF sets to the unit interval([2], [1]). Similar generalizations are presented in [4] and [5].","PeriodicalId":403191,"journal":{"name":"EUSFLAT Conf.","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132194222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
EUSFLAT Conf.Pub Date : 2011-08-06DOI: 10.2991/eusflat.2011.49
E. Lughofer
{"title":"All-Pairs Evolving Fuzzy Classifiers for On-line Multi-Class Classification Problems","authors":"E. Lughofer","doi":"10.2991/eusflat.2011.49","DOIUrl":"https://doi.org/10.2991/eusflat.2011.49","url":null,"abstract":"In this paper, we propose a novel design of evolving fuzzy classifiers in case of multi-class classification problems. Therefore, we exploit the concept of all-pairs aka all-versus-all classification using binary classifiers for each pair of classes, which has some advantages over direct multi-class as well as one-versus-rest classification variants. Regressionbased as well as singleton class label fuzzy classifiers are used as architectures for the binary classifiers, which are evolved and incrementally trained based on the concepts included in the FLEXFIS family (a connection of eVQ and recursive fuzzily weighted least squares). The classification phase considers the preference levels of each pair of classes stored in a preference relation matrix and uses a weighted voting scheme of preference levels, including reliability aspects. The advantage of the new evolving fuzzy classifier concept over single model (using direct multi-class classification concept) and multi model (using one-versus-rest classification concept) architectures will be underlined by empirical evaluations and comparisons at the end of the paper based on high-dimensional real-world multi-class classification problems.","PeriodicalId":403191,"journal":{"name":"EUSFLAT Conf.","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133412073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
EUSFLAT Conf.Pub Date : 2011-08-06DOI: 10.2991/eusflat.2011.42
O. Sokolov, O. Molchanova
{"title":"Fuzzy assessment of test results","authors":"O. Sokolov, O. Molchanova","doi":"10.2991/eusflat.2011.42","DOIUrl":"https://doi.org/10.2991/eusflat.2011.42","url":null,"abstract":"The objective of this research is to study various assessment methods used in modern test systems. Methods based on classical test theory and IRT (item response theory) have been considered in this paper. The approaches to improve the quality of assessment of the ability level as a function of the diversity of evaluation points have been proposed. Statistical analysis packages SPSS, the tests analysis WinSteps and MatLab packages have been applied as software tools.","PeriodicalId":403191,"journal":{"name":"EUSFLAT Conf.","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132518771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
EUSFLAT Conf.Pub Date : 2011-08-06DOI: 10.2991/eusflat.2011.76
H. Prade, S. Schockaert
{"title":"Completing rule bases in symbolic domains by analogy making","authors":"H. Prade, S. Schockaert","doi":"10.2991/eusflat.2011.76","DOIUrl":"https://doi.org/10.2991/eusflat.2011.76","url":null,"abstract":"The paper considers the problem of completing a set of parallel if-then rules that provides a partial description of how a conclusion variable depends on the values of condition variables, where each variable takes its value among a finite ordered set of labels. The proposed approach does not require the use of fuzzy sets for the interpretation of these labels or for defining similarity measures, but rather relies on the extrapolation of missing rules on the basis of analogical proportions that hold for each variable between the labels of several parallel rules. The analogical proportions are evaluated for binary and multiple-valued variables on the basis of a logical expression involving Eukasiewicz implication. The underlying assumption is that the mapping partially specified by the given rules is as regular as suggested by these rules. A comparative discussion with other approaches is presented.","PeriodicalId":403191,"journal":{"name":"EUSFLAT Conf.","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116745566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
EUSFLAT Conf.Pub Date : 2011-08-06DOI: 10.2991/eusflat.2011.119
G. Herbst, Arne-Jens Hempel, Rainer Fletling, S. Bocklisch
{"title":"Membership-based clustering of heterogeneous fuzzy data","authors":"G. Herbst, Arne-Jens Hempel, Rainer Fletling, S. Bocklisch","doi":"10.2991/eusflat.2011.119","DOIUrl":"https://doi.org/10.2991/eusflat.2011.119","url":null,"abstract":"This article contributes to clustering and fuzzy modelling of data such that specific characteristics of each datum can be incorporated. Particularly, each object may exhibit an individual area of influence in its feature space, for which it is representative. For such objects, a similarity measure is introduced, which is used to modify common clustering algorithms to take each object’s extent into account when finding clusters. A real-world example demonstrates the practical usability of the presented methods, which deliver results in accordance to findings of experts in that field.","PeriodicalId":403191,"journal":{"name":"EUSFLAT Conf.","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133637259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}