Self-adaptive virus optimization algorithm for continuous optimization problems  

Oleh:

Liang, Yun-Chia ; Cuevas, Josue R.

Jenis: Article from Proceeding
Dalam koleksi: The 14th Asia Pacific Industrial Engineering and Management Systems Conference (APIEMS), 3-6 December 2013 Cebu, Philippines, page 1-9.
Topik: Self-adaptation; Virus Optimization Algorithm; Continuous domain functions; Parameter setting
Fulltext: 1178.pdf (1.2MB)

Isi artikel

Given the outstanding performance in different fields such as image processing and energy dispatching, the Virus Optimization Algorithm (VOA), a newly developed metaheuristic for general optimization purposes has been further improved. Similar to other metaheuristic methods, the performance of VOA to some degree relies on the proper parameter setting, which may need lots of experiments to decide. Therefore, in this paper we proposed a Self-adaptive version of VOA (SaVOA) to decrease the number of controllable parameters in the algorithm, and thus, reduce the time needed when deciding proper parameter values by following any sort of experimentation design process. When performing the comparison, SaVOA is put into the test by optimizing six benchmark functions also used when proposing the original VOA. From the computational results, SaVOA proved its superiority on functions where the original VOA was not powerful enough to perform well such as Rosenbrock, Schwefel, and Easom's functions. In terms of implementation the number of controllable parameters in SaVOA was greatly reduced to one only - the stopping criterion. The aforementioned promises the easiness of using SaVOA for any type of continuous domain optimization problems.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali