Feature Selection Algorithm for Palm Bio-impedance Spectroscopy based on Immune Clone
According to the features of Palm bio-impedance spectroscopy (BIS) data,this paper suggests a kind of effective feature model of palm BIS data— elliptical model.The model combines immune clone algorithm and least squares method,establishes a palm BIS feature selection algorithm,and uses the algorithm to obtain the optimal feature subset that can completely represent the palm BIS data,and then use several classification algorithms for classification and comparison.The experimental results show that accuracy of the feature subset obtained through the algorithm in SVM classification algorithm test can reach 93.2,thereby verifying the algorithm is a valid and reliable palm BIS feature selection algorithm.
palm BIS immune clone feature extraction feature selection pattern classification
Lü Lin-tao Li-peng YANG Yu-xiang Tan-fang
College of Computer Science and Engineering Xian University of Technology Xian ,China College of Computer Science and Engineering, School of Mechanical and Precision Instrument Engineeri
国际会议
太原
英文
702-705
2013-04-06（万方平台首次上网日期，不代表论文的发表时间）