1,720,961 research outputs found
Knowledge transfer between robots with identical tasks execution
No full textThis paper considers the transfer of knowledge expressed in the form of a collection of fuzzy or linguistic inference rules, also called knowledge or rule-base, from one robot (teacher) to another robot (student) in the case where both robots are supposed to perform the same task. Some rules are assumed taught or transferred to the student; i.e., they are known, and others are missing. The objective of this study is to have the student robot uncover the missing rules through self-experience and using the transferred rules. This objective is achieved by devising a novel method that enables the student robot to complete the knowledge-base. The completed rule-base would not necessarily turn out to be identical to the one possessed by the teacher robot. But, once it is used in the execution of the same task, it leads to satisfactory performance from a comparative perspective
Knowledge transfer between robots with identical tasks execution
No full textThis paper considers the transfer of knowledge expressed in the form of a collection of fuzzy or linguistic inference rules, also called knowledge or rule-base, from one robot (teacher) to another robot (student) in the case where both robots are supposed to perform the same task. Some rules are assumed taught or transferred to the student; i.e., they are known, and others are missing. The objective of this study is to have the student robot uncover the missing rules through self-experience and using the transferred rules. This objective is achieved by devising a novel method that enables the student robot to complete the knowledge-base. The completed rule-base would not necessarily turn out to be identical to the one possessed by the teacher robot. But, once it is used in the execution of the same task, it leads to satisfactory performance from a comparative perspective
Defuzzification methods and new techniques for fuzzy controllers
No full textBased on the various components involved in the structure of fuzzy logic controllers, this study provides an in-depth examination of the different features and disadvantages of commonly used defuzzification methods. Then based on this examination, and taking into account the compatible assignment of the logical connectives, inference rules as well as membership functions (MFs), a superior defuzzification technique is described and justified. It is shown that this technique integrates the defuzzification problem into the global structure of fuzzy controllers. It also helps the designer achieve his design objectives in a simple and systematic manner. Another defuzzification strategy, which falls within the general framework of this study, is also given and commented upon. It is shown that this strategy satisfies properties which should be possessed by a desired defuzzification method, and also shares important features with the former one. Further, a recent defuzzification-based methodology for the systematic data-driven design of fuzzy controllers is outlined.
Performance measures and preferences for fuzzy controllers design algorithms
No full textThis study defines practical performance measures for testing data-driven design algorithms for fuzzy controllers through the use of non-linear control functions. Also, criteria, which can be applied to these measures in order to determine preferences between data-driven algorithms, are discussed and a framework for solutions is proposed. After offering a summary of a new algorithm for the design of Mamdani-type fuzzy controllers with emphasis on its design requirements, the algorithm is tested along with neuro-fuzzy and other design methods and performance comparisons are given. This is done by considering the defined measures and typical non-linear functions, which were adopted in published research. The new algorithm is found to provide better noise-free data-fitting than some published algorithms based on clustering, fuzzy partitions, and heuristics. However, the error values were found higher than those obtained using neuro-fuzzy and clustering-position-gradient approaches. In the practical noisy data case, however, the algorithm outperforms the combined fuzzy-neuro-least-square algorithm and the heuristic approach. This superiority is verfied based on performance measures related to noise-free data-fitting in the noisy data case, noise insensitivity, and generalization capability, the combination of these latter two measures and function shape representation.Al-Khatib M, 2003, FUZZY SET SYST, V134, P65, DOI 10.1016-S0165-0114(02)00230-0; BUCKLEY JJ, 1993, FUZZY SET SYST, V60, P1, DOI 10.1016-0165-0114(93)90283-N; Carse B, 1996, FUZZY SET SYST, V80, P273, DOI 10.1016-0165-0114(95)00196-4; Chen JQ, 1998, FUZZY SET SYST, V98, P319, DOI 10.1016-S0165-0114(96)00384-3; Delgado M, 1997, IEEE T FUZZY SYST, V5, P223, DOI 10.1109-91.580797; HORIKAWA S, 1992, IEEE T NEURAL NETWOR, V3, P801, DOI 10.1109-72.159069; JANG JSR, 1993, IEEE T SYST MAN CYB, V23, P665, DOI 10.1109-21.256541; JANG JSR, 1995, P IEEE, V83, P378, DOI 10.1109-5.364486; JANG JSR, 1992, IEEE T NEURAL NETWOR, V3, P714, DOI 10.1109-72.159060; Klawonn F, 1997, FUZZY SET SYST, V85, P177, DOI 10.1016-0165-0114(95)00350-9; Klawonn F, 1996, FUZZY SET SYST, V81, P331, DOI 10.1016-0165-0114(96)83710-9; Klir GJ, 1995, FUZZY SETS FUZZY LOG; Koczy LT, 1997, FUZZY SET SYST, V85, P203, DOI 10.1016-0165-0114(95)00348-7; Lee CW, 2003, FUZZY SET SYST, V137, P297, DOI 10.1016-S0165-0114(02)00344-5; LEE J, 1993, FUZZY SET SYST, V56, P127, DOI 10.1016-0165-0114(93)90138-8; Li Y, 2002, FUZZY SET SYST, V127, P85, DOI 10.1016-S0165-0114(01)00154-3; Lin YH, 1997, IEEE T FUZZY SYST, V5, P614; NOMURA H, 1992, IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, P203, DOI 10.1109-FUZZY.1992.258618; Nozaki K, 1997, FUZZY SET SYST, V86, P251, DOI 10.1016-0165-0114(95)00413-0; Saade J. J., 2000, MATHWARE SOFT COMPUT, V7, P159; Saade JJ, 1996, IEEE T FUZZY SYST, V4, P227, DOI 10.1109-91.531767; SAADE JJ, 1992, FUZZY SET SYST, V50, P237, DOI 10.1016-0165-0114(92)90222-P; Shi Y, 2000, FUZZY SET SYST, V112, P99, DOI 10.1016-S0165-0114(98)00238-3; Shi Y, 2000, FUZZY SET SYST, V112, P51, DOI 10.1016-S0165-0114(98)00056-6; Siarry P, 1998, FUZZY SET SYST, V99, P37, DOI 10.1016-S0165-0114(97)00003-1; Sugeno M., 1993, IEEE Transactions on Fuzzy Systems, V1, DOI 10.1109-TFUZZ.1993.390281; TAKAGI T, 1985, IEEE T SYST MAN CYB, V15, P116; Tarng YS, 1996, FUZZY SET SYST, V83, P301, DOI 10.1016-0165-0114(95)00335-5; ZADEH LA, 1973, IEEE T SYST MAN CYB, VSMC3, P28, DOI 10.1109-TSMC.1973.54085750
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
- …
