TY - CHAP
T1 - Fuzzy grouping genetic algorithms
T2 - Advances for real-world grouping
AU - Mutingi, Michael
AU - Mbohwa, Charles
N1 - Publisher Copyright:
© Springer International Publishing Switzerland 2017.
PY - 2017
Y1 - 2017
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84990966978&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-44394-2_4
DO - 10.1007/978-3-319-44394-2_4
M3 - Chapter
AN - SCOPUS:84990966978
T3 - Studies in Computational Intelligence
SP - 67
EP - 86
BT - Studies in Computational Intelligence
PB - Springer Verlag
ER -