Vitality-based elephant search algorithm
- 92 Downloads
Elephant search algorithm (ESA) is one of the contemporary meta-heuristic search algorithms recently proposed. The male elephants are responsible for global exploration, roaming to new dimensions of search space. The female elephants focus on doing local search, for finding the optimal solution. A lifespan mechanism is designed to control the birth and death that all agents will have an increasing dead probability with their aging incrementally. This mechanism is set to avoid whole agents falling into local optimum and those new-born elephants will evolve by inheriting heuristic information from the ancestors. In the naïve version of ESA, the search agents expire at equal probability regardless of their current locations. It is supposed that search agents who have shown to improve their solutions are more likely to continue producing better results than those mediocre agents. By this concept, a vitality-based elephant search algorithm called VESA is proposed to fine-tune the lifespan of search agents using a vitality computation mechanism that rewards the good performing agents’ longer life at the expense of the mediocre agents. With the lifespan extended, the fit agents have more time to continue enhancing the solutions. Computer simulation on nine testing functions shows the VESA outperforms the naïve ESA in terms of the final fitness value. A min–max based self-adaptive ratio search strategy is also proposed to help find a good gender ratio in a reasonable time.
KeywordsElephant search algorithm Vitality Meta-heuristic Min–max strategy
The authors are thankful for the financial supports from the Research Grants titled: “Temporal Data Stream Mining by Using Incrementally Optimized Very Fast Decision Forest (iOVFDF)”, Grant No. MYRG2015-00128-FST; “Nature-Inspired Computing and Metaheuristics Algorithms for Optimizing Data Mining Performance”, Grant No. MYRG2016-00069-FST; and “A Scalable Data Stream Mining Methodology: Stream-based Holistic Analytics and Reasoning in Parallel”, Grant no. FDCT/126/2014/A3, offered by the University of Macau, and FDCT or Macau SAR government respectively.
- Beheshti Z, Shamsuddin SMH (2013) A review of population-based meta-heuristic algorithms. Int J Adv Soft Comput Appl 5(1):1–35Google Scholar
- Deb S, Fong S, Tian Z, Wong RK, Mohammed S, Fiaidhi J (2016) Finding approximate solutions of NP-hard optimization and TSP problems using elephant search algorithm. J Supercomput 24:1–33Google Scholar
- Kennedy J (2011) Particle swarm optimization. Encyclopedia of machine learning. Springer, New York, pp 760–766Google Scholar
- Simon F, Robert PB-A, Richard CM (2018) Swarm Search Methods in Weka for Data Mining. In: ICMLC 2018 Proceedings of the 2018 10th international conference on machine learning and computing, ACM, February 26–28, 2018, pp 122–127Google Scholar
- Suash D, Simon F, Zhonghuan T (2015) Elephant Search Algorithm for optimization problems. In: 10th International conference on digital information management (ICDIM), 2015 IEEEGoogle Scholar
- Tian Z et al (2016) Optimizing self-adaptive gender ratio of elephant search algorithm by min-max strategy. In: 12th International conference on natural computation, fuzzy systems and knowledge discovery (ICNC-FSKD), IEEEGoogle Scholar
- Vidya TNC, Sukumar R (2005) Social and reproductive behaviour in elephants. Curr Sci 89(7):1200–1207Google Scholar