Identification of λ-fuzzy measures using sampling design and genetic algorithms

doi:10.1016/S0165-0114(01)00010-0

Fuzzy Sets and Systems

Volume 123, Issue 3, 1 November 2001, Pages 321-341

https://doi.org/10.1016/S0165-0114(01)00010-0 Get rights and content

Abstract

The data collection and identification of $λ$ -fuzzy measures are fundamental tasks to be capable of using them in practice. Although several studies have been made on $λ$ -fuzzy measure identification, their methods require the knowledge of subjective estimates for all subsets of an attribute set, or the corresponding computation process is rather complicated. Since little attention has been given to the issue of data collection, this study designed a sampling procedure of attribute subsets to capture the most useful information and thus reduce the original information demand in solving $λ$ -fuzzy measures. Then, this study developed an identification procedure for $λ$ -fuzzy measures using genetic algorithms. Several experiments were implemented to show the applicability and feasibility of the proposed methods.

References (26)

A. Basile
Sequential compactness for sets of Sugeno fuzzy measures
Fuzzy Sets and Systems
(1987)
D.G. Conway et al.
Genetic search and the dynamic facility layout problem
Comput. Oper. Res.
(1994)
K. Ishii et al.
A model of human evaluation process using fuzzy measure
Internat. J. Man–Mach. Stud.
(1985)
K.-M. Lee et al.
Identification of $λ$ -fuzzy measure by genetic algorithms
Fuzzy Sets and Systems
(1995)
K. Leszczyński et al.
Sugeno's fuzzy measure and fuzzy clustering
Fuzzy Sets and Systems
(1985)
T. Murofushi et al.
An interpretation of fuzzy measures and the Choquet integral as an integral with respect to a fuzzy measure
Fuzzy Sets and Systems
(1989)
T. Onisawa et al.
Fuzzy measure analysis of public attitude towards the use of nuclear energy
Fuzzy Sets and Systems
(1986)
T.J. Stewart
A critical survey on the status of multiple criteria decision making theory and practice
OMEGA Internat. J. Management Sci.
(1992)
S.T. Wierzchoń
An algorithm for identification of fuzzy measure
Fuzzy Sets and Systems
(1983)
L. Davis
Handbook of Genetic Algorithms
(1991)

K. De Jong

Learning with genetic algorithms: an overview

Mach. Learning

(1988)

D.R. Frantz, Non-linearities in genetic adaptive search, Ph.D. Dissertation, University of Michigan,...

D.E. Goldberg

Genetic Algorithms in Search, Optimization and Machine Learning

(1989)

Cited by (36)

Aggregation of neural classifiers using Choquet integral with respect to a fuzzy measure
2018, Neurocomputing
Citation Excerpt :
In order to simplify the fuzzy measure, [43] also proposed the λ-fuzzy measure, where n values need to be identified. Since then, aiming to identify these n values, different supervised approaches have been proposed [4,24,27,45]. However, these methods have some shortcomings related to slow convergence and/or computational burden [22].
Data classification appears in many real-world problems, e.g., recognition of image patterns, differentiation among species of plants, classifying between benign and malignant tumors, among others. Many of these problems present data patterns, which are difficult to be identified, thus requiring more advanced techniques to be solved. Over the last few years, various classification algorithms have been developed to address these problems, but there is no classifier able to be the best choice in all situations. As a simple and effective methodology, an ensemble of classifiers has been applied to several classification problems aiming to improve performance and increase reliability. However, for an ensemble of classifiers to be able to improve the classification accuracy, an aggregation technique must be performed. In this work, we present an aggregation methodology for an ensemble of neural classifiers using Choquet integral with respect to a fuzzy measure based on Shannon’s entropy. We apply this methodology to conventional benchmarks and large databases and the results are promising.
Disassembly line balancing problem using interdependent weights-based multi-criteria decision making and 2-Optimal algorithm
2018, Journal of Cleaner Production
With the rapid technology advancement and market changes products are becoming outdated and subsequently discarded faster than ever before. As a result, recovery, recycling, and remanufacturing of end-of-life products are gaining more attention. Disassembly is indispensable to recycle and remanufacture end-of-life products, and a disassembly line is an efficient way to achieve it. A disassembly line balancing problem aims at optimizing the disassembly sequences in which the disassembly times of workstations are approximately equal and approaching the cycle time. However, in addition to line balancing assigning disassembly tasks to workstations needs to consider other factors, such as how to recover valuable components as fast as possible and reduce undesirable impacts on the environment as much as possible. This work aims at addressing a disassembly line balancing problem with multiple objectives, including economic and environmental factors and disassembly line efficiency. A three-phased methodology is proposed to solve this problem. The proposed method not only enables the consideration of objectives with interdependent weights in multi-criteria decision making but effectively generates a good enough trade-off disassembly solution using a 2-optimal algorithm. The proposed approach is tested on a benchmark and compared with three other methods. Experiment results are shown to verify its performance.
Choquet based TOPSIS and TODIM for dynamic and heterogeneous decision making with criteria interaction
2017, Information Sciences
Citation Excerpt :
Also assuming that the decision maker is able to provide some a priori information about the fuzzy measure, Lee and Leekwang [35] applied a genetic algorithm (GA) to find the fuzzy measure that matches the most with the prior information. There are several other works that use GA to determine the fuzzy measure [8,9], but they all need some a priori information or input-output data. Grabisch [18] used a gradient descent method to determine the fuzzy measure from learning data.
Decision making problems are becoming increasingly complicated. Consequently, the developed methods to support decision makers are more and more general. Group decision-making is a very common scenario. When a team of decision makers is faced with a problem, it is natural to assume that due to diversity of their backgrounds and experience they may require different ways of providing their evaluations and opinions. A very common, and quite unreasonable, assumption made by decision-making methods that deal with groups of decision makers is to consider that all decision makers agreed on a unique criteria set to evaluate given alternatives. Criteria interaction is another common issue in multi-criteria decision making and it is normally addressed using Choquet integral, which alone brings another serious problem of capacity identification. In addition, the decision-making environments are rarely static. Aiming to address all these issues at once, we propose two generalized approaches based on the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) and the TODIM (an acronym in Portuguese for Interactive and Multi-Criteria Decision Making). The new methods are able to consider groups of decision makers with all their different opinions, heterogeneous types of information, criteria interaction, fuzzy measure identification and dynamic environments. The methods are applied in two examples and two case studies showing their feasibility in solving complex real world problems.
A Short Survey on the Usage of Choquet Integral and its Associated Fuzzy Measure in Multiple Attribute Analysis
2015, Procedia Computer Science
Choquet integral operator is currently making inroads into many real multiple attribute analysis due to its ability on modeling the usual interactions held by the attributes during the aggregation process. Unfortunately, the process of identifying 2ⁿ values of fuzzy measure prior to employing Choquet integral normally turns into a very complex one with the increasing number of attributes, n. On that note, this paper mainly reviews on some of the methods that have been proposed in reducing the complexity of identifying fuzzy measure values together with their pros and cons. The paper begins with a discussion on the aggregation process in multiple attribute analysis which then focuses on the usage of Choquet integral and its associated fuzzy measure before investigating some of the fuzzy measure identification methods. A simple numerical example to demonstrate the merit of using Choquet integral and the indications for future research are provided as well. The paper to some extent would be helpful in stimulating new ideas for developing simpler or enhanced versions of fuzzy measure identification methods.
A novel approach to evaluate software vulnerability prioritization
2013, Journal of Systems and Software
The aim of this study is to formulate an analysis model which can express the security grades of software vulnerability and serve as a basis for evaluating danger level of information program or filtering hazardous weaknesses of the system and improve it to counter the threat of different danger factors. Through the utilization of fuzzy analytic hierarchy process (FAHP), we will organize the crossover factors of the software blind spots and build an evaluation framework. First of all, via the fuzzy Delphi method the aspects and relative determinants affecting security will be filtered out. Then we will identify the value equation of each factor and settle down the fuzzy synthetic decision making model of software vulnerability. Thanks to this model we will be able to analyze the various degrees to which the vulnerability is affecting the security and this information will serve as a basis for future ameliorations of the system itself. The higher the security score obtained therefore imply securer system. Beside this, this study also propose an improvement from the traditional fuzzy synthetic decision making model for measuring the fuzziness between enhancement and independence of various aspects and criteria. Furthermore taking into consideration the subjectivity of human in reality and constructing the fuzzy integral decision making model. Through case study, we show that the evaluation model in question is practical and can be applied on the new software vulnerabilities and measure their degree of penetration. The fuzzy integral decision making emphasize through formulation the multiply-add effect between different factors influencing information security.
Particle swarm optimization for determining fuzzy measures from data
2011, Information Sciences
Citation Excerpt :
Wang also proposed using the genetic algorithm (GA) to determine fuzzy measures [14,40,51,56–58,63]. Due to the better robustness, GAs are further used by many researchers [9,10,12,27,28,73]. References show that the design of GAs depends on the type of training data.
Fuzzy measures and fuzzy integrals have been successfully used in many real applications. How to determine fuzzy measures is the most difficult problem in these applications. Though there have existed some methodologies for solving this problem, such as genetic algorithms, gradient descent algorithms and neural networks, it is hard to say which one is more appropriate and more feasible. Each method has its advantages and limitations. Therefore it is necessary to develop new methods or techniques to learn distinct fuzzy measures. In this paper, we make the first attempt to design a special particle swarm algorithm to determine a type of general fuzzy measures from data, and demonstrate that the algorithm is effective and efficient. Furthermore we extend this algorithm to identify and revise other types of fuzzy measures. To test our algorithms, we compare them with the basic particle swarm algorithms, gradient descent algorithms and genetic algorithms in literatures. In addition, for verifying whether our algorithms are robust in noisy-situations, a number of numerical experiments are conducted. Theoretical analysis and experimental results show that, for determining fuzzy measures, the particle swarm optimization is feasible and has a better performance than the existing genetic algorithms and gradient descent algorithms.

View all citing articles on Scopus

View full text

Identification of λ-fuzzy measures using sampling design and genetic algorithms

Abstract

Fuzzy Sets and Systems

Comput. Oper. Res.

Internat. J. Man–Mach. Stud.

Fuzzy Sets and Systems

Fuzzy Sets and Systems

Fuzzy Sets and Systems

Fuzzy Sets and Systems

OMEGA Internat. J. Management Sci.

Fuzzy Sets and Systems

Handbook of Genetic Algorithms

Learning with genetic algorithms: an overview

Mach. Learning

Genetic Algorithms in Search, Optimization and Machine Learning

Identification of $λ$ -fuzzy measures using sampling design and genetic algorithms