Sugeno Fuzzy Integral Research Articles

Face recognition using modular neural networks and the fuzzy Sugeno integral for response integration

We describe a new approach for face recognition using modular neural networks with a fuzzy logic method for response integration. We proposed a new architecture for modular neural networks for achieving pattern recognition in the particular case of human faces. Also, the method for achieving response integration is based on the fuzzy Sugeno integral. Response integration is required to combine the outputs of all the modules in the modular network. We have applied the new approach for face recognition to a real database of faces of students at our institution. Recognition rates with the modular approach were compared against the monolithic single neural network approach to measure the improvement. The results of the new modular neural network approach were excellent overall and also in comparison to the monolithic approach. © 2005 Wiley Periodicals, Inc. Int J Int Syst 20: 275–291, 2005.

Economic Evaluation of AHS to Reduce Traffic Accidents with Conjoint Analysis

This paper provided the economic evaluation of AHS with conjoint analysis, in order to measure not only effect occurring from the reduced traffic accidents but also the impacts given to drivers' mental part. In this study, we applied the non-linear utility functions, CES type, Sugeno fuzzy integral and Choquet fuzzy integral, to the linear utility function in the precious conjoint analysis. From the results of mathematical simulation, we clarified that the onset effects for the introducing two type AHS are gotten by CES type analysis, and the offset effects are obtained by fuzzy integral type analysis. And we expressed the range of AHS introduced benefits through the simulation analysis.

An extension of Sugeno integral

In this paper, we extend the concept of Sugeno fuzzy integral from nonnegative fuzzy measurable functions to extended real-valued fuzzy measurable functions and discuss the lost genuine properties for this extension; several necessary and sufficient conditions of absolute ( S)-integrability for extended real-valued fuzzy measurable functions are given. Moreover, the space ( S( μ), ρ(.,.)) of all fuzzy measurable functions will be proved to be a pseudo-metric space under a necessary and sufficient condition. Finally, as an application of this extension the Pettis integral will be established for this kind of fuzzy integral.

Machine intelligence quotient: its measurements and applications

We have investigated the notion of machine intelligence, based on extensive literature survey and have proposed two methods to measure intelligence of a machine. Specially, we have first analyzed those engineering systems or products that are said to be intelligent and have extracted four common constructs, each of which consists of several variables. Based on them, we have then suggested two typical models, which are represented as entities in three-dimensional construct space. In order to find a number, called machine intelligence quotient (MIQ), we adopt two fuzzy integrals, Sugeno fuzzy integral and Choquet fuzzy integral. Two application examples are given for the typical models using two fuzzy integrals, and comparative comments are made.

PIECEWISE LINEAR AGGREGATION FUNCTIONS

The Choquet and Sugeno (fuzzy) integrals are examples of piecewise linear functions on a finite dimensional space ℝn. In this paper we consider piecewise linear functions as aggregation functions and establish a Max-Min polynomial representation of these functions.

Fusion of handwritten word classifiers

Methods for fusing multiple handwritten word classifiers are compared on standard data. A novel method based on data-dependent densities in a Choquet fuzzy integral is shown to outperform neural networks, Borda and weighted Borda counts, and Sugeno fuzzy integral.

Possibility and necessity integrals

In this paper, we introduce seminormed and semiconormed fuzzy integrals associated with confidence measures. These confidence measures have a field of sets as their domain, and a complete lattice as their codomain. In introducing these integrals, the analogy with the classical introduction of Lebesgue integrals is explored and exploited. It is amongst other things shown that our integrals are the most general integrals that satisfy a number of natural basic properties. In this way, our dual classes of fuzzy integrals constitute a significant generalization of Sugeno's fuzzy integrals. A large number of important general properties of these integrals is studied. Furthermore, and most importantly, the combination of seminormed fuzzy integrals and possibility measures on the one hand, and semiconormed fuzzy integrals and necessity measures on the other hand, is extensively studied. It is shown that these combinations are very natural, and have properties which are analogous to the combination of Lebesgue integrals and classical measures. Using these results, the very basis is laid for a unifying measure- and integral-theoretic account of possibility and necessity theory, in very much the same way as the theory of Lebesgue integration provides a proper framework for a unifying and formal account of probability theory.

Transformation theorems for fuzzy integrals on fuzzy sets

In this paper, Sugeno's fuzzy integrals studied in [5,8,9] are generalized, some equivalent definitions of fuzzy integrals on fuzzy sets are given, and several transformation theorems of such type of fuzzy integrals are proved. These results reveal the relations between the fuzzy integrals on fuzzy sets and on classical sets.

Two families of fuzzy integrals

In this paper we present two definitions of fuzzy integrals arising from the t-seminorm and the t-semiconorm concepts. We show that Sugeno's fuzzy integral is a particular case of them and we study their principal properties. Finally we suggest some applications of these results.

Integrales normadas y conormadas (Generalizacion de la integral de Sugeno)

In this paper an extensive generalization for Sugeno's fuzzy integral is given by defining two families of fuzzy integrals, a normed family and a conormed one. Sugeno's fuzzy integral is a particular case belonging to both families. The purpose of this paper is to study the properties for the mentioned integrals and the relationships existing between those families. The extension of this families to a fuzzy domain is also accomplished. Finally, some possible ways to use the obtained results are suggested in the paper.

Entropies in finite fuzzy sets

We introduce a general type of entropies (in the sense of De Luca and Termini) for finite fuzzy sets and study its properties for the case of the so-called θ- ∗ entropies, which generalize both the logarithmic entropy (as taken by the above mentioned authors), and Sugeno's fuzzy integral for finite sets.