首页 | 官方网站   微博 | 高级检索  
     

基于多尺度小波包分析的肺音特征提取与分类
引用本文:刘毅,张彩明,赵玉华,董亮.基于多尺度小波包分析的肺音特征提取与分类[J].计算机学报,2006,29(5):769-777.
作者姓名:刘毅  张彩明  赵玉华  董亮
作者单位:1. 山东大学计算机科学与技术学院,济南,250061
2. 山东大学信息科学与工程学院,250100
3. 山东大学齐鲁医院呼吸内科,济南,250012
基金项目:教育部科学技术研究项目
摘    要:提出了一种适于非平稳肺音信号的特征提取方法.以4种肺音信号(正常、气管炎、肺炎和哮喘)为样本数据,通过分析肺音信号的时频分布特点,选择了具有任意多分辨分解特性的小波包.对小波包进行空间划分后找到了适合肺音特征提取的最优基,并基于最优基对肺音信号进行快速多尺度的分解,得到了各级节点的高维小波系数矩阵,建立了小波系数与信号能量在时域上的等价关系,并将能量作为特征值,构造了低维的作为分类神经网络的输入特征矢量,大大降低了输入特征的维数.研究表明该算法的识别性能是高效的.

关 键 词:肺音  多尺度分析  小波包  特征提取  分类
收稿时间:2005-03-19
修稿时间:2005-03-192005-12-15

The Feature Extraction and Classification of Lung Sounds Based on Wavelet Packet Multiscale Analysis
LIU Yi,ZHANG Cai-Ming,ZHAO Yu-Hua,DONG Liang.The Feature Extraction and Classification of Lung Sounds Based on Wavelet Packet Multiscale Analysis[J].Chinese Journal of Computers,2006,29(5):769-777.
Authors:LIU Yi  ZHANG Cai-Ming  ZHAO Yu-Hua  DONG Liang
Affiliation:1.Schoolof Computer Science and Technology, Shandong University, Jinan 250061;2.School of Information Science and Engineering, Jinan 250100; 3.Department of Respiration Medicine in Qilu Hospital, Shandong University, Jinan 250012
Abstract:In this paper, a novel method of feature extraction in non-stable lung sound signals is put forward. Four kinds of lung sounds data(collected in the state of normal, bronchus, pneumonia and asthma respectively) are sampled from various subjects. By studying the time-frequency distribution characteristics of the respiratory signals, the authors select the wavelet packets that have the trait of arbitrary distinction and decomposition. After space partition of wavelet packets, the best wavelet packet basis for feature extraction is picked out. Based on the best basis, we can do fast arbitrary multi-scale WPT, and obtain each higher dimension wavelet coefficients matrix. And then the equal-value relation in time domain between wavelet coefficients and signal energy is found. The energy is used as eigenvalue, and feature vectors of artificial neural network(ANN) for classification are formes. This greatly decreases the number of input vectors of ANN. Extensive experimental results demonstrate that the proposed feature extraction method has encouraging recognition performance.
Keywords:lung sound  multiscale analysis  wavelet packet  feature extraction  classification
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号