Abstract:
Brain Storm Optimization (BSO) is an effective population-based optimization method inspired by human brainstorming process. This paper proposes a new binary BSO algorith...Show MoreMetadata
Abstract:
Brain Storm Optimization (BSO) is an effective population-based optimization method inspired by human brainstorming process. This paper proposes a new binary BSO algorithm (BBSO) to develop a new feature selection approach in order to reduce the number of selected features and/or improve the classification accuracy. Specifically, a new update rule mechanism for generating new solutions is proposed, which improves the convergence speed and reduces the possibility of immature convergence in the algorithm. Furthermore, a fuzzy ARTMAP (FAM) neural network, which is an incremental learning model, is utilized as a classification approach to evaluate the effectiveness of the selected feature subsets. The performance of the proposed method is compared with those from the original BSO, particle swarm optimization (PSO) and genetic algorithm (GA) on eight commonly used and well-known benchmark problems. The experimental results indicate the superiority of the BBSO as compared with other state-of-the-art feature selection methods.
Published in: 2019 IEEE 6th International Conference on Cloud Computing and Intelligence Systems (CCIS)
Date of Conference: 19-21 December 2019
Date Added to IEEE Xplore: 23 April 2020
ISBN Information: