Article Preview
TopSwarm intelligence is the most promising area of optimization in the field of numerical data set for the researcher. All the socials living used their structure, shape and intelligent to optimized their problems. The Researchers of the diversified filed have developed many algorithms based on the swarming behaviour of various living being viz. ants, honey bees, fish, birds, BAT, Cuckoo and firefly to optimize the numerical problems.
Ant colony optimization (ACO) (M. Dorigo,1990) and particle swarm optimization (PSO) (J. Kennedy, R. Eberhart, 1995) are two major methods for swarm intelligent used by many authors to optimized the data set.
ACO algorithm is motivated by the foraging behaviour of ants to find a shortest path from their colony to find the food sources. In this metaheuristic, ants communicate with and influence others using pheromone to find the food source. Using the positive feedback of pheromone, the algorithm leads the ants to find the shortest path to a best food source (M. Dorigo,1990).
PSO algorithm is inspired by flock of birds or a school of fishes and used their positions in the search space to represent the feasible solutions of the optimization problem. Cognitive learning and social learning, lead the population to find a best way to perform optimization (J. Kennedy, R. Eberhart, 1995) in the search space.
The PSO and ABC have been applied to solve on vast range of different problems, e.g. (Liao et al.2012), (Kirchmaier et al. 2013) to optimized the problems domain. The most widely studied organism in swarm intelligence honey Bees Optimization (MBO)(H. A. Abbass, 2001) and ABC (D. Karaboga, B. Basturk, 2007). ABC balances exploration and exploitation using employed and onlooker bees for local search, and the scout bees for global search. ABC algorithm also demonstrates satisfactory performance in applications (Omkar et al. 2011), (B. Akay, 2013).