Recognition of heart sound based on distribution of Choi-Williams

Introduction

To realize noninvasive diagnosis and early diagnosis of coronary heart disease, the study proposes a new time-frequency method for analyzing heart sound signals. This method is based on Choi-Williams Distribution (CWD).

Methods

CWD distribution is developed and modified from Wigner Ville distribution (WVD). To solve the problem of cross-term interference existing in WVD there is an improved version of WVD, called Choi-Williams Distribution (CWD), which introduces the smoothing window as the kernel function and deals with the time-frequency analysis of heart sound signal.

Results

The improved method has good performance and can be implemented simply without much increase of operation complexity.

Conclusion

In this paper, 21 cases of heart sound signals are acquired from the outpatients and hospitalized patients with coronary heart diseases. The research results of 21 cases show that the CWD method can be used to analyze heart sounds. It accurately identifies the 9 cases of heart sounds of health people and 12 cases of heart sounds of patients with coronary heart disease. Besides, the CWD displays obvious differences between heart sounds of healthy people and abnormal heart sounds. The contour line of heart sounds from healthy people shows the following characteristics: concise, columnar and non-divergence; while the contour line of abnormal heart sounds is divergent and has many columnar links. These research shows that CWD method can effectively distinguish heart sounds between healthy people and patients with coronary heart disease.

Heart sound signals; Choi-Williams distribution; Biomedical signal processing; Non-invasive diagnosis; Time-frequency analysis