Improvement
of Imperialist Competitive Algorithm based on the Cosine Similarity Criterion
of Neighboring Objects
Maryam Houtinezhad and Hamid Reza
Ghaffary
Department of Computer Engineering,
Ferdows Branch, Islamic Azad University, Ferdows, Iran
Abstract: The goal of optimizing
the best acceptable answer is according to the limitations and needs of the
problem. For a problem, there are several different answers that are
defined to compare them and select an optimal answer; a function is called a
target function. The choice of this function depends on the nature of the problem. Sometimes several goals are together
optimized; such optimization problems are called multi-objective issues. One
way to deal with such problems is to form a new objective function in the form
of a linear combination of the main objective functions. In the proposed
approach, in order to increase the ability to discover new position in the Imperialist
Competitive Algorithm (ICA), its operators are combined with the
particle swarm optimization. The colonial
competition optimization algorithm has the ability to search global and has a
fast convergence rate, and the particle swarm algorithm added to it increases
the accuracy of searches. In this approach, the cosine similarity of the neighboring
countries is measured by the nearest colonies of an imperialist and closest
competitor country. In the proposed method, by balancing the global and local
search, a method for improving the performance of the two algorithms is
presented. The simulation results of the combined algorithm have been evaluated
with some of the benchmark functions. Comparison of the results has
been evaluated with respect to metaheuristic
algorithms such as Differential Evolution (DE), Ant Lion Optimizer
(ALO), ICA, Particle Swarm Optimization (PSO), and Genetic Algorithm (GA).
Keywords: Imperialist competitive algorithm, particle swarm optimization, optimization
problem.
Received March 24, 2018;
accepted November 17, 2019