PSO Based Feature Weighting Algorithm for KNN
基于PSO面向K近邻分类的特征权重学习算法

Feature weighting is one of the important problems for feature weighting based KNN algorithm,and many heuristic methods have been employed to solve the problem traditionally.Recently,with the wide applications of evolutionary computation in pattern recognition and data mining areas,the evolutionary computation based feature weighting and distance learning method have got more and more attention.According to the feature-weighting problem of KNN,the paper proposes a PSO based feature weighting algorithm named PSOKNN.In comparison with other methods such as traditional KNN,GAKNN and ReliefKNN,the experiments show that the PSOKNN can get suitable feature weights,result in good classification accuracy and get rid of more redundant or irrelevant features.