Fuzzy grouping genetic algorithms: Advances for real-world grouping

Michael Mutingi, Charles Mbohwa

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

4 Citations (Scopus)

Abstract

Grouping genetic algorithm (GGA) is an effective and efficient algorithm that has been used to solve a number of grouping or clustering problems. The main challenge, however, is the development of the computational procedure for recent complex problems characterized with uncertain and imprecise variables, imprecise goals and preferences, the curse of dimensionality, and other complexities. In practice, it is difficult to understand how genetic parameters interact and how their interactions influence the performance of the algorithm. This is because the interactions are complex and difficult to model in a precise way. Thus, fine-tuning, control, and adaptation of the behavior of genetic parameters, such as divergence, crossover, mutation, and inversion probabilities, are a cause for concern in the research community. This chapter focused on proposing advances and innovations in the use of fuzzy logic control and dynamic adaptive control, and their incorporation into the GGA mechanism. In FGGA, grouping genetic operators are enriched with fuzzy logic control and other fuzzy theoretic concepts so as to enable the algorithm to accommodate expert choice, opinion, and guidance during its search and optimization processes. The algorithm is expected to be able to handle complex real-world grouping problems with fuzzy characteristics. It is hoped that the fuzzy GGA (FGGA) proposed in this chapter will be effective and efficient for solving real-world grouping problems, even in a fuzzy environment. Prospects for possible application areas in this direction were presented.

Original languageEnglish
Title of host publicationStudies in Computational Intelligence
PublisherSpringer Verlag
Pages67-86
Number of pages20
DOIs
Publication statusPublished - 2017

Publication series

NameStudies in Computational Intelligence
Volume666
ISSN (Print)1860-949X

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Fuzzy grouping genetic algorithms: Advances for real-world grouping'. Together they form a unique fingerprint.

Cite this