This special issue is dedicated to the 9th International FLINS Conference on Foundations and Applications of Computational Intelligence (FLINS2010) held in Chengdu/E'Mei, China, on 2–4 August 2010. After peer review, the Editor-in-Chief and guest editor accepted eight revised and extended papers of FLINS2010 to reflect the current development of fuzziness in systems modelling.
The first paper by Bouchon-Meunier et al. (France) focuses on the modelling and management of subjective information in a fuzzy setting. The three aspects of subjectivity are distinguished: the first is to deal with perception and sensory information; the second is related to emotions, their fuzzy nature, and their identification; and the third is to take into account information quality and reliability of information.
The second paper by Vilem Novak (Czech Republic) presents a class of methods encapsulated under the term modelling with words. The theoretical frame, mathematical fuzzy logic in broader sense, is outlined for building models using genuine expressions of natural language. Its constituents are formal logical theory of evaluative linguistic expressions, intermediate quantifiers, and the related concepts of linguistic description and perception-based logical deduction. Various kinds of applications in decision making are presented based on the proposed framework.
The third paper by Komkhao et al. (Germany, Australia) develops an incremental collaborative filtering algorithm based on Mahalanobis distance and fuzzy membership for recommender systems. It has the learning and prediction phases. In the first phrase, models of similar users are constructed incrementally; in the second phase, interested users are clustered by measuring their similarity to existing clusters in a model. Fuzzy sets are employed to handle confusion of decision making on overlapping clusters. Experimental results indicate that the proposed algorithm improves prediction accuracy and prevents the scalability problem in recommendation systems.
The fourth paper by Jiri Mockor (Czech Republic) validates that fuzzy sets in Ω-sets [in both categories Set(Ω) and SetR(Ω)] can be equivalently expressed as special cut systems in Ω-sets. Models of first-order fuzzy logic based on these cut systems are defined. Then, relationships between interpretations of formulas in classical models (based on Ω-sets) and in models based on these cut systems are investigated.
The fifth paper by Arien J. van der Wal (The Netherlands) indicates that distributed decision making in a sensor network can be described by a simple system consisting of phase oscillators. This system shows spontaneous organization in the thermodynamic limit. Simulations demonstrate that phase synchronization spontaneously emerges for finite populations if the coupling strength is strong enough.
The sixth paper by Ding et al. (China) aims to deal with a class of uncertain Takagi-Sugeno fuzzy delayed systems with nonlinear perturbations. The norm equivalent conditions of robust exponential stability for such systems are presented based on the Gronwall–Bellman inequality. It is concluded that the robust exponential stability can be achieved if the delay terms and the nonlinear terms can be controlled by the norm of system states.
The seventh paper by Shi et al. (Belgium) introduces a similarity measure between fuzzy sets by using a fuzzy implication. The eight most important potential properties of fuzzy implications which ones should be taken into consideration to measure the similarity are investigated. Then a suitable fuzzy implication that satisfies these potential properties is chosen. The application of the chosen fuzzy implication is illustrated in a partition algorithm used for multi-criteria decision making.
The eighth paper by Rosa M. Rodriguez and Luis Martinez (Spain) overviews the relationship between decision making and computing with words. An analysis of different symbolic linguistic computing models including 2-tuple linguistic model in decision making is presented. It is shown that 2-tuple linguistic model represented by means of a linguistic term and a numerical value keeps the syntax and fuzzy semantics and provides results accurate and easy to understand.
Finally, I wish to express my gratitude to all the authors for their contribution, to the reviewers for their careful, insightful, and constructive reviews that led to further improvement of the articles. I would like to give special thanks to Prof. George Klir, Editor-in-Chief of the Journal, for accepting to publish this Special Issue and for his help throughout the publication process.
Related Research Data
