SEARCH RESULT

The Galactic Swarm Optimization (GSO) is a novel method inspired by the movements of stars and star clusters. The GSO is a framework that uses the optimization methods known in the literature. GSO has a two-stage structure. In the first stage, the optimization method identifies possible good solutions by scanning the search space. In the second stage, the best solution is tried to be found by using possible good solutions. In the original GSO study, Particle Swarm Optimization (PSO) was used as an optimization method in both stage. In this study, Tree Seed Algorithm (TSA), a new optimization method in the literature, is used in GSO framework instead of PSO. In the experimental study, the performance of the GSO_TSA model has been investigated on numeric benchmark functions and obtained results are compared with GSO_PSO model.

International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES

Ersin Kaya Oğuzhan Uymaz Sedat Korkmaz Eyüp Sıramkaya Mustafa Servet Kıran

The Salp Swarm Algorithm (SSA) is one of the recently proposed nature-inspired metaheuristic algorithms. SSA mimics the life cycle of salp swarms. Salp swarm is an animal group which lived in oceans. The navigating and foraging behaviors are the characteristic properties of the salp swarms. These behaviors are modeled as an optimization algorithmin SSA and it is firstly proposed for solving continuous optimization problems. In literature, there is no binary version of this algorithm which uses transfer functions. In this work, SSA is modified for solving binary optimization problems by using transfer functions. Transfer functions are used to convert the continuous decision variables to the binary decision variables. With this modification, the structure of SSA has not been changed, but only the Sigmoid and the Tangent Hyperbolic transfer functions are adapted. In order to validate the performance of the proposed binary SSA, a well-known pure binary optimization problem, uncapacitated facility location problems (UFLP), set is considered. UFLPs are used for a benchmarking of many metaheuristic algorithms such as; artificial bee colony, tree-seed algorithm, particle swarm optimization, differential evolution and artificial algae algorithm. The experimental results of 12 UFLPs are compared with each other and state-of-art algorithms. Experimental results demonstrate that the SSA is a promising solver for lower dimensional problems, but its performance should be improved on higher dimensional problems.

International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES

Ersin Kaya Ahmet Cevahir Çınar Oğuzhan Uymaz Sedat Korkmaz Mustafa Servet Kıran