Universiti Teknologi Malaysia Institutional Repository

A fast discrete gravitational search algorithm

Shamsudin, Hasrul Che and Irawan, Addie and Ibrahim, Zuwairie and Zainal Abidin, Amar Faiz and Wahyudi, S. and Abdul Rahim, Muhammad Arif and Khalil, Kamal (2012) A fast discrete gravitational search algorithm. Proceedings of International Conference on Computational Intelligence, Modelling and Simulation . pp. 24-28. ISSN 2166-8523

Full text not available from this repository.

Official URL: http://dx.doi.org/10.1109/CIMSim.2012.28

Abstract

This study introduces a variant of Gravitational Search Algorithm (GSA) for discrete optimization problem namely, Fast Discrete Gravitational Search Algorithm (FDGSA). The main difference between the proposed FDGSA and the existing Binary Gravitational Search Algorithm (BGSA) is that an agent's posiion is updated based on its direction and velocity. Both the direction and velocity determine the candidates of integer values for the position update of an agent and then the selection is done randomly. Unimodal test functions, such as De Jong's function, Scwefel's function and Rosenbrock's valley are used to evaluate the performance of the proposed FDGSA. Comparison with BGSA is done to benchmark the proposed FDGSA in terms of speed of convergence and quality of solution. The experimental result shows that the proposed FDGSA converges faster compared to the BGSA.

Item Type:Article
Uncontrolled Keywords:Computational intelligence, modelling, simulation
Subjects:Q Science
Divisions:Electrical Engineering
ID Code:46483
Deposited By: Haliza Zainal
Deposited On:22 Jun 2015 13:56
Last Modified:11 Sep 2017 15:23

Repository Staff Only: item control page