[1]朱春媚[],黎萍[]. 基于帧间PCA特征降维的咳嗽识别[J].计算机技术与发展,2016,26(03):40-43.
　ZHU Chun-mei[],LI Ping[]. Cough Recognition Based on Inter-frame PCA Feature Dimension Reduction[J].,2016,26(03):40-43.
点击复制

 基于帧间PCA特征降维的咳嗽识别()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
26
期数:
2016年03期
页码:
40-43
栏目:
智能、算法、系统工程
出版日期:
2016-03-10

文章信息/Info

Title:
 Cough Recognition Based on Inter-frame PCA Feature Dimension Reduction
文章编号:
1673-629X（2016)03-0040-04
作者:
 朱春媚[1] ; 黎萍[2]
 1.电子科技大学中山学院 机电工程学院；2.华南理工大学 自动化科学与工程学院
Author(s):
 ZHU Chun-mei[1]; LI Ping[2]
关键词:
 ; 咳嗽监测; 咳嗽识别; 主元分析法;  特征降维
Keywords:
 ; cough monitoring; cough recognition; PCA; feature dimension reduction
分类号:
TP391.42
文献标志码:
A
摘要:
 咳嗽是呼吸系统疾病常见的症状，咳嗽的自动监测在临床上具有重要的辅助诊断意义。作为便携式咳嗽监测仪的软件算法，咳嗽识别具有小样本、粗分类和运算速度要求高的特点，这使得特征降维在咳嗽识别中具有重要意义。咳嗽识别一般采用39维的Mel倒谱系数作为特征量，特征维数不高导致帧内特征降维效果不显著。针对这个问题，文中对咳嗽的声学特点进行分析，在得出咳嗽特征集中体现在爆发相的结论基础上，提出了一种基于主元分析法( PCA)的帧间特征降维方法。采用主元分析得到映射矩阵和主元个数后，以每6帧为一组进行分组降维，然后组合降维后的特征作为总特征，将咳嗽识别的特征数量降维至原来的23.9%。采用隐马尔可夫模型作为分类器，多组录音样本的咳嗽识别实验结果表明，该降维方法能在改善识别准确率的同时，有效减少算法的运行时间、提高咳嗽识别的效率。
Abstract:
 Cough is a common symptom of respiratory diseases and automatic cough monitoring has important significance in clinical di-agnosis. As a software algorithm of portable devices used in computer-aided diagnosis,cough recognition has the characteristics of small sample,rough classification and requirement for high computing speed,which makes feature dimension reduction necessary. Cough recog-nition commonly adopts 39-dimention MFCC as feature which results to the poor performance of dimension reduction within frame. To dress this problem,acoustic characteristics of cough is analyzed. Based on the finding that feature of cough is mainly reflected in explosive phase,a method of inter-frame feature dimension reduction based on Principal Component Analysis (PCA) is proposed. This method re-duces dimension in each group of six frames,and combines each group of reduced feature as the general feature,in which only 23. 9% of the original features are adopted. Automatic recognitions of cough using hidden Markov model are carried out,and the results of various groups of samples show that this method can both improve the recognition rate and reduce the running time of the recognition algorithm to increase the recognition efficiency.

相似文献/References:

[1]张志宏,吴庆波,邵立松,等.基于飞腾平台TOE协议栈的设计与实现[J].计算机技术与发展,2014,24(07):1.
　ZHANG Zhi-hong,WU Qing-bo,SHAO Li-song,et al. Design and Implementation of TCP/IP Offload Engine Protocol Stack Based on FT Platform[J].,2014,24(03):1.
[2]梁文快,李毅. 改进的基因表达算法对航班优化排序问题研究[J].计算机技术与发展,2014,24(07):5.
　LIANG Wen-kuai,LI Yi. Research on Optimization of Flight Scheduling Problem Based on Improved Gene Expression Algorithm[J].,2014,24(03):5.
[3]黄静,王枫,谢志新,等. EAST文档管理系统的设计与实现[J].计算机技术与发展,2014,24(07):13.
　HUANG Jing,WANG Feng,XIE Zhi-xin,et al. Design and Implementation of EAST Document Management System[J].,2014,24(03):13.
[4]侯善江[],张代远[][][]. 基于样条权函数神经网络P2P流量识别方法[J].计算机技术与发展,2014,24(07):21.
　HOU Shan-jiang[],ZHANG Dai-yuan[][][]. P2P Traffic Identification Based on Spline Weight Function Neural Network[J].,2014,24(03):21.
[5]李璨,耿国华,李康,等. 一种基于三维模型的文物碎片线图生成方法[J].计算机技术与发展,2014,24(07):25.
　LI Can,GENG Guo-hua,LI Kang,et al. A Method of Obtaining Cultural Debris’ s Line Chart Based on Three-dimensional Model[J].,2014,24(03):25.
[6]翁鹤,皮德常. 混沌RBF神经网络异常检测算法[J].计算机技术与发展,2014,24(07):29.
　WENG He,PI De-chang. Chaotic RBF Neural Network Anomaly Detection Algorithm[J].,2014,24(03):29.
[7]刘茜[],荆晓远[],李文倩[],等. 基于流形学习的正交稀疏保留投影[J].计算机技术与发展,2014,24(07):34.
　LIU Qian[],JING Xiao-yuan[,LI Wen-qian[],et al. Orthogonal Sparsity Preserving Projections Based on Manifold Learning[J].,2014,24(03):34.
[8]尚福华,李想,巩淼. 基于模糊框架-产生式知识表示及推理研究[J].计算机技术与发展,2014,24(07):38.
　SHANG Fu-hua,LI Xiang,GONG Miao. Research on Knowledge Representation and Inference Based on Fuzzy Framework-production[J].,2014,24(03):38.
[9]叶偲,李良福,肖樟树. 一种去除运动目标重影的图像镶嵌方法研究[J].计算机技术与发展,2014,24(07):43.
　YE Si,LI Liang-fu,XIAO Zhang-shu. Research of an Image Mosaic Method for Removing Ghost of Moving Targets[J].,2014,24(03):43.
[10]余松平[][],蔡志平[],吴建进[],等. GSM-R信令监测选择录音系统设计与实现[J].计算机技术与发展,2014,24(07):47.
　YU Song-ping[][],CAI Zhi-ping[] WU Jian-jin[],GU Feng-zhi[]. Design and Implementation of an Optional Voice Recording System Based on GSM-R Signaling Monitoring[J].,2014,24(03):47.

更新日期/Last Update: 2016-06-08