Title: Clustering-based hierarchical genetic algorithm for complex fitness landscapes

Authors: Rahul Kala, Anupam Shukla, Ritu Tiwari

Addresses: Soft Computing and Expert Systems Laboratory, Indian Institute of Information Technology and Management Gwalior, Room No 101, BH-1, ABV-IIITM Gwalior, Gwalior, Madhya Pradesh, India. ' Soft Computing and Expert Systems Laboratory, Indian Institute of Information Technology and Management Gwalior, Gwalior, Madhya Pradesh, India. ' Soft Computing and Expert Systems Laboratory, Indian Institute of Information Technology and Management Gwalior, Gwalior, Madhya Pradesh, India

Abstract: We propose the use of a hierarchical genetic algorithm (GA) for optimisation in complex landscapes. While the slave GA tries to find the local optima in the restricted fitness landscape of low complexity, the master GA tries to identify interesting regions in the entire landscape. The slave GA is a conventional GA with high convergence. The master GA is more exploratory in nature. This GA clusters the fitness landscape with each cluster in control of a slave GA. The number of clusters decreases with time to get global characteristics. The novelty of the suggested approach lies in the trade-off between the search for global optima and convergence to local optima that can be controlled between the two GAs. We tested the algorithm and observed that the approach exceeds conventional GA as well as particle swarm optimisation in complex landscapes.

Keywords: HGA; hierarchal genetic algorithms; evolutionary algorithms; fitness landscape; dimensionality; optimisation; GAs; machine learning; soft computing; complexity; random algorithms; swarm intelligence; clustering; intelligent systems.

DOI: 10.1504/IJISTA.2010.034320

International Journal of Intelligent Systems Technologies and Applications, 2010 Vol.9 No.2, pp.185 - 205

Published online: 31 Jul 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article