An innovative approach for feature selection based on chicken swarm optimization

In this paper, a system for feature selection based on chicken swarm optimization (CSO) algorithm is proposed. Datasets ordinarily includes a huge number of attributes, with irrelevant and redundant attribute. Commonly wrapper-based approaches are used for feature selection but it always requires an intelligent search technique as part of the evaluation function. Chicken swarm optimization (CSO)is a new bio-inspired algorithm mimicking the hierarchal order of the chicken swarm and the behaviors of chicken swarm, including roosters, hens and chicks, CSO can efficiently extract the chickens´ swarm intelligence to optimize problems. Therefore, CSO was employed to feature selection in wrapper mode to search the feature space for optimal feature combination maximizing classification performance, while minimizing the number of selected features. The proposed system was benchmarked on 18 datasets drawn from the UCI repository and using different evaluation criteria and proves advance over particle swarm optimization (PSO) and genetic algorithms (GA) that commonly used in optimization problems.