Comparison on the Selection Strategies in the Artificial Bee Colony Algorithm for Examination Timetabling Problems
Malek Alzaqebah1, Salwani Abdullah2
1Malek Alzaqebah, Data Mining and Optimization Research Group (DMO) Center for Artificial Intelligence Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia.
2Salwani Abdullah, Data Mining and Optimization Research Group (DMO) Center for Artificial Intelligence Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia.
Manuscript received on October 04, 2011. | Revised Manuscript received on October 21, 2011. | Manuscript published on November 05, 2011. | PP: 158-163 | Volume-1 Issue-5, November 2011. | Retrieval Number: E0175091511/2011©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper presents an investigation of selection strategies upon the Artificial Bee Colony (ABC) algorithm in examination timetabling problems. ABC is a global stochastic optimisation algorithm that is based on the behavior of honey bee swarms. Onlooker bees in ABC algorithm choose food source based on the proportional selection strategy. In this paper, three selection strategies are introduced (i.e. disruptive, tournament and rank selection strategies), in order to improve the diversity of the population and avoid the premature convergence in the evolutionary process. Experimental results show that the modified ABC with the three selection strategies outperforms the ABC algorithm alone. Among the selection strategies, the disruptive selection strategy shows the better performance when tested on standard benchmark examination timetabling problem.
Keywords: Artificial Bee Colony Algorithm, Examination Timetabling problems, Selection Strategies.