Simultaneous feature selection and feature weighting with K selection for KNN classification using BBO algorithm

K nearest neighbor algorithm (K-NN) is considered as one of the machine learning algorithms for data classification. This algorithm suffers of some disadvantages such as sensitivity to the distance function, K value selection and high computational complexity (time and spatial). In this paper, a novel hybrid approach is proposed for simultaneous feature selection and feature weighting with k value selection of K-NN rule based on Biogeography based optimization (BBO). The 6 evolutionary algorithms and 14 non-evolutionary algorithms are used to compare and evaluate with the novel proposed algorithm (BBO-KNN). The experimental results signify that the BBO-KNN has higher efficiency compared to other methods and is led to higher classification rate as well as effective data dimension reduction.