| Summary: | Salp swarm algorithm (SSA) is a recently created bio-inspired optimization algorithm presented in 2017 which is based on the swarming mechanism of salps. This paper tries to improve the structure of basic SSA to enhance solution accuracy, reliability and convergence speed. A new control parameter, inertia weight, is added to adjust the present best solution. The new method known as improved salp swarm algorithm (ISSA) is tested in feature selection task. The ISSA algorithm is consolidated with the K-nearest neighbor classier for feature selection in which twenty-three UCI datasets are utilized to assess the performance of ISSA algorithm. The ISSA is compared with the basic SSA and four other swarm methods. The results demonstrated that the proposed method produced superior results than the other optimizers in terms of classification accuracy and feature reduction. Keywords: Feature selection, Salp swarm algorithm, Bio-inspired optimization, K-Nearest Neighbor, Classification
|
|---|
