Feature Selection Algorithm Based on K-means Clustering

In order to improve the performance of the feature selection algorithm, a feature selection algorithm based on K-means clustering is designed. The algorithm makes use of the idea of K-means clustering based on cosine distance to cluster the features, so that the obtained feature subset has strong correlation and no redundancy. The experimental results show that the feature selection algorithm based on K-means clustering has high efficiency for classification tasks and has short running time, so the algorithm has strong practicability for feature selection.