|Table of Contents|

Identity Recognition Using Heart Sound Based on CPSO-LSSVM(PDF)

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2013年01期
Page:
68-
Research Field:
Publishing date:

Info

Title:
Identity Recognition Using Heart Sound Based on CPSO-LSSVM
Author(s):
Liu Jiajia; Zhou Hongbiao; Ju Yong
(1.School of Electrical and Automation Engineering,Nanjing Normal University,Nanjing 210042,China) (2.Faculty of Electronic and Electrical Engineering,Huaiyin Institute of Techology,Huaian 223003,China)
Keywords:
heart sound; identity recognition; cultural particle swarm optimization; least squares support vector machine; empirical mode decomposition
PACS:
TP391.9
DOI:
-
Abstract:
A method of identity recognition using heart sound based on CPSO-LSSVM is proposed.Two kinds of spaces,population space and belief space,are set in the algorithm.With the approach,the heart sound signals were decomposed using the empirical mode decomposition(EMD)to get stable IMF components at first,aiming at the non-stable and non-linear of heart sounds.Then,the IMFs containing the information of the first and second heart sounds were selected and the corresponding HHT instantaneous spectrum were drawn by Hilbert transformation.Subsequently,energy character vectors of spectrum were taken as the input of LSSVM to establish the classifier.To improve the classification accuracy,LSSVM’s parameters λ and σ are optimized by GA,PSO and CPSO(λ=28.86,σ=0.87).The experiment collects 120 heart sounds from 3 people to test the proposed algorithm.Compared with the GA and PSO,the CPSO has the advantages in the global search ability escaping from local optimum capacity,and convergence speed.The classification accuracy of the CPSO-LSSVM algorithm reached 97.7%,and result demonstrates that the method has an encouraging recognition performance and identity recognition using heart sound is feasible.

References:

[1] 胡玉良,王海滨,陈健.心音时域分析的新方法研究[J].生物医学工程学杂志,2010,27(2):425-428.
Hu Yuliang,Wang Haibin,Chen Jian.A new method for heart sound analysis in time domain[J].Journal of Biomedical Engineering,2010,27(2):425-428.(in Chinese)
[2]郭兴明,段赟,钟丽莎.基于HMM和WNN的心音信号身份识别研究[J].计算机应用研究,2010,27(12):4 561-4 564.
Guo Xingming,Duan Yun,Zhong Lisha.Study of human identity recognition based on HMM and WNN[J].Application Research of Computers,2010,27(12):4 561-4 564.(in Chinese)
[3]成谢锋,马勇,张少白.基于数据融合的三段式心音身份识别技术[J].仪器仪表学报,2010,31(8):1 712-1 719.
Cheng Xiefeng,Ma Yong,Zhang Shaobai.Three-step identity recognition technology using heart sound based on information fusion[J].Chinese Journal of Scientific Instrument,2010,31(8):1 712-1 719.(in Chinese)
[4]刘娟,赵治栋.基于心音信号的身份识别方法[J].科技通报,2011,27(2):182-185.
Liu Juan,Zhao Zhidong.Human identification method based on heart sound[J].Bulletin of Science and Technology,2011,27(2):182-185.(in Chinese)
[5]Beritelli F,Serrano S.Biometric identification based on frequency analysis of cardiac sounds[J].IEEE Trans on Information Forensics and Security,2007,2(3):596-604.
[6]Jasper J,Othman K R.Feature extraction for human identification based on envelogram signal analysis of cardiac sounds in time-frequency domain[C]//International Conference on Electronics and Information Engineering,2010(2):228-233.
[7]程志颖,孔浩辉,张俊,等.粒子群算法结合支持向量机回归法用于近红外光谱建模[J].分析测试学报,2010,29(12):1 215-1 219.
Cheng Zhiying,Kong Haohui,Zhang Jun,et al.Application of particle swarm optimization-least square support vector machine regression to modeling of near infrared spectra[J].Journal of Instrumental Analysis,2010,29(12):1 215-1 219.(in Chinese)
[8]贾嵘,张云,洪刚.基于改进PSO的LSSVM参数优化在变压器故障诊断中的应用[J].电力系统保护与控制,2010,38(17):121-124.
Jia Rong,Zhang Yun,Hong Gang.Parameter optimization of least squares support vector machine based on improved particle swarm optimization in fault diagnosis of transformer[J].Power System Protection and Control,2010,38(17):121-124.(in Chinese)
[9]吴亚丽,袁瑛.一种基于文化粒子群算法的BP网络优化方法[J].系统仿真学报,2011,23(5):930-934.
Wu Yali,Yuan Ying.Back propagation network optimization algorithm based on cultural particle swarm algorithm[J].Journal of System Simulation,2011,23(5):930-934.(in Chinese)
[10]任斌,丰镇平.改进遗传算法与粒子群优化算法及其对比分析[J].南京师范大学学报:工程技术版,2002,2(2):16-22.
Ren Bin,Feng Zhenping.Improved genetic algorithm and particle swarm optimization as well as comparison between them[J].Journal of Nanjing Normal University:Engineering and Technology Edition,2002,2(2):16-22.(in Chinese)
[11]周红标,蒋鼎国,柯永斌,等.基于STC单片机和LabVIEW的心音信号检测系统[J].电子技术应用,2012,38(1):31-33.
Zhou Hongbiao,Jiang Dingguo,Ke Yongbin,et al.The heart sound signal detecting system based on STC microprocessor and LabVIEW[J].Application of Electronic Technique,2012,38(1):31-33.(in Chinese)
[12]南姣芬,艾玲梅,申军.HHT方法在驾驶疲劳脑电分析中的应用[J].生物医学工程学杂志,2011,28(4):653-657.
Nan Jiaofen,Ai Lingmei,Shen Jun.Application of HHT to driving fatigue in EEG analysis[J].Journal of Biomedical Engineering,2011,28(4):653-657.(in Chinese)

Memo

Memo:
-
Last Update: 2013-03-31