Auscultation Signals Analysis in Traditional Chinese Medicine Using Wavelet Packet Energy Entropy and Support Vector Machines

Abstract

In this paper, wavelet packet energy entropy (WPEE) and support vector machine (SVM) were utilized to detect and classify auscultation signals in Traditional Chinese Medicine (TCM). The auscultation signals of health and qi-vacuity and yin-vacuity subjects were collected from the outpatient by Shanghai University of TCM. And the wavelet packet decomposition (WPD) at level 6 was employed to split more elaborate frequency bands of the auscultation signals, then to obtain energy entropies features of frequency bands. SVM are designed and trained for making a decision regarding the type of the auscultation signals. The experimental results showed the algorithm using WPEE and SVM classifier feasibility and effectiveness, and this paper is valuable for auscultation research in TCM.