|
|||||
|
|
Wavelet packet feature selection for lung sounds based on optimization |
|
| Authors: | YU Bin TIAN Feng-chun HE Qing-hu RAN Jian LV Bo HONG Xin LIU Tao and BI Yu-tian |
| Institution: | College of Communication Engineering, Chongqing University, Chongqing 400044, P. R. China,College of Communication Engineering, Chongqing University, Chongqing 400044, P. R. China,State Key Laboratory of Trauma, Burns and Combined Injury, Daping Hospital, Surgery Institute of the Third Military Medical University, Chongqing 400042, P. R. China,College of Communication Engineering, Chongqing University, Chongqing 400044, P. R. China,College of Communication Engineering, Chongqing University, Chongqing 400044, P. R. China,State Key Laboratory of Trauma, Burns and Combined Injury, Daping Hospital, Surgery Institute of the Third Military Medical University, Chongqing 400042, P. R. China,College of Communication Engineering, Chongqing University, Chongqing 400044, P. R. China and State Key Laboratory of Trauma, Burns and Combined Injury, Daping Hospital, Surgery Institute of the Third Military Medical University, Chongqing 400042, P. R. China |
| Abstract: | In this paper, a wavelet packet feature selection method for lung sounds based on optimization is proposed to obtain the best feature set which maximizes the differences between normal lung sounds and abnormal lung sounds (sounds with wheezes or rales). The proposed method includes two main steps: Firstly, the wavelet packet transform (WPT) is used to extract the original features of lung sounds; then the genetic algorithm (GA) is used to select the best feature set. The obtained optimal feature set is sent to four different classifiers to evaluate the performance of the proposed method. Experimental results show that the feature set obtained by the proposed method provides a higher classification accuracy of 94.6% in comparison with the best wavelet packet basis approach and multi-scale principal component analysis (PCA) approach. Meanwhile, the proposed method has effective generalization performance and can obtain the best feature set without priori knowledge of lung sounds. |
| Keywords: | wavelet packet transform feature selection genetic algorithm lung sound pattern recognition |
| 本文献已被 CNKI 等数据库收录！ | |
| 点击此处可从《重庆大学学报(英文版)》浏览原始摘要信息 | |
| 点击此处可从《重庆大学学报(英文版)》下载免费的PDF全文 | |