1. College of Electronic Science and Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China;
2. Nation-Local Joint Project Engineering Lab of RF Integration & Micropackage, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
Here, a recognition system for a heart sound wavelet neural network was designed, with it heart sound features were extracted, the neural network structure was layered, identified and classified to solve the problem of heart sound classification recognition under complicated conditions. Firstly, a recognition model based on heart sound wavelet neural network was proposed. Then the method to construct heart sound wavelet and heart sound wavelet neural network was discussed. The algorithm for introducing heart sound wavelet as the activation function of neural network hidden layer was discussed specially to obtain a recognition system of heart sound wavelet neural network highly fusing heart sound targeted learning and heart sound recognition technique. Finally, normal heart sound signals and beats heart sound signals were selected as the test objects and to verify the effectiveness and practicality of a heart sound wavelet neural network recognition system. Compared with Morlet wavelet neural network recognition system and Mexican hat wavelet neural network recognition system, it was shown that the heart sound wavelet neural network recognition system is superior in convergence and alrorithm speed.
[1] Richard O. Duda, Peter E. Hart and David G. Stork.模式分类.北京：机械工业出版社. 2010, pp45—92.
Richard O. Duda, Peter E. Hart and David G. Stork. Pattern Classification. Beijing: Mechanical Industry Publishing. 2010, pp45-92.
[2] 蔡念,胡匡祜,李淑宇,苏万芳.小波神经网络及其应用[J].中国体视学与图像分析, 2001, 6(04):239-245.
Cai L，Hu K G,Li S Y,Su W F. Wavelet Neural Network and Its Application [J]. Chinese Journal of Stereology and Image Analysis, 2001, 6(04):239-245.
[3] 俞阿龙. 基于遗传小波神经网络的机器人腕力传感器动态建模研究[J]. 物理学报, 2008,57(06):3385-3390.
Yu A-Long. Research on the dynamic modeling based on genetic waveletneural network for the robot wrist force sensor[J]. Acta Physica Sinica, 2008, 57(06):3385-3390.
[4] 牛东晓,邢棉. 时间序列的小波神经网络预测模型的研究[J]. 系统工程理论与实践, 1999, 05:90-93.
NIU Dongxiao,XING Mian. A Study on Wavelet Neural Network Prediction Model of Time Series[J]. Systems Engineering-Theory & Practice, 2008,57(06):3385-3390.
[5] 缪志强,王耀南. 基于径向小波神经网络的混沌系统鲁棒自适应反演控制[J]. 物理学报, 2012,61(03):64-70.
Miao Zhi-Qiang,Wang Yao-Nan. Robust adaptive radial wavelet neural network control for chaotic systems using backstepping design[J]. Acta Physica Sinica, 2012,61(03):64-70.
[6] 陈增强,任东,袁著祉,杜升之. 基于多分辨率学习的正交基小波神经网络设计[J]. 系统工程学报,2003,03:218-223.
CHEN Zeng_qiang, REN Dong, YUAN Zhu_zhi, DU Sheng_zhi. Design of orthogonal basis wavelet neural network based onmultiresolution learning[J] Journal of system engineering,2003,03:218-223.
[7] 神经网络基本概念,陈瑞http://chenrui8712.blog.163.com/blog/static/183844271201212971112547/
Chen R,The basic concept of neural network
http://chenrui8712.blog.163.com/blog/static/183844271201212971112547/
[8] 成谢锋,张正. 一种双正交心音小波的构造方法[J]. 物理学报, 2013,62(16):454-465.
Cheng Xie-Feng, Zhang Zheng. A construction method of biorthogonalheart sound wavelet[J] Acta Physica Sinica, 2013,62(16):454-465.
[10] 成谢锋,马勇,刘陈,张学军,郭宇锋. 心音身份识别技术的研究[J]. 中国科学:信息科学,2012,42(02):235-249.
Cheng Xie Feng, MA Yong, LIU Chen, ZHANG Xue Jun GUO Yu Feng. An introduction to heart sounds identification technology[J]. Science China Press, 2012,42(02):235-249.
[11] 成谢锋,马勇,张少白,张瑛,郭宇锋. 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(08):1712-1719.
ChengXie-feng,MaYong,ZhangShaobai,ZhangYing,GuoYufeng.Tree-step identity recognition technology using heart sound based on information fusion[J]. Chinese Journal of Scientific Instrument, 2010, 31(08):1712-1719.
[12] 张国华,袁中凡,李彬彬. 心音信号特征提取小波包算法研究[J]. 振动与冲击,2008, 27(07):47-49+185.
Zhang Guo-hua,Yuan Zhong-fan,Li Bin-bin. Research on Wavelete Packet Algorithm for Feature Extraction of Heart Sound Signal[J]. Journal of Vibration and Shock, 2008, 27(07):47-49+185.
[13] Uğuz H. Adaptive neuro-fuzzy inference system for diagnosis of the heart valve diseases using wavelet transform with entropy[J]. Neural Computing and applications, 2012, 21(7): 1617-1628.
