Biometric Identification Method for Heart Sound Based on Multimodal Multiscale Dispersion Entropy.

Xiefeng Cheng,Chenjun She,Pengfei Wang

doi:10.3390/e22020238

Abstract

In this paper, a new method of biometric characterization of heart sounds based on multimodal multiscale dispersion entropy is proposed. Firstly, the heart sound is periodically segmented, and then each single-cycle heart sound is decomposed into a group of intrinsic mode functions (IMFs) by improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN). These IMFs are then segmented to a series of frames, which is used to calculate the refine composite multiscale dispersion entropy (RCMDE) as the characteristic representation of heart sound. In the simulation experiments I, carried out on the open heart sounds database Michigan, Washington and Littman, the feature representation method was combined with the heart sound segmentation method based on logistic regression (LR) and hidden semi-Markov models (HSMM), and feature selection was performed through the Fisher ratio (FR). Finally, the Euclidean distance (ED) and the close principle are used for matching and identification, and the recognition accuracy rate was 96.08%. To improve the practical application value of this method, the proposed method was applied to 80 heart sounds database constructed by 40 volunteer heart sounds to discuss the effect of single-cycle heart sounds with different starting positions on performance in experiment II. The experimental results show that the single-cycle heart sound with the starting position of the start of the first heart sound (S1) has the highest recognition rate of 97.5%. In summary, the proposed method is effective for heart sound biometric recognition.

Highlights

Heart sound is a complex, non-stationary and quasi-periodic signal that is consisted of multiple heartbeats or cardiac cycles, which mainly contain components such as the first heart sound S1, the second heart sound S2, systolic murmur and diastolic murmur
88 of database used in this paper consists of 72 heart sounds from the three open heart sound databases used in this paper consists of 72 heart sounds from the three open heart sound databases Michigan, Michigan, Washington and Littman, including 18 normal heart sounds and 54 abnormal heart
The heart sound database built by our research group consisted built by our research group consisted of 80 cases of heart sound recordings from college student and of 80 cases of heart sound recordings from college student and teacher volunteers, which are collected teacher volunteers, which are collected by using the Ω shoulder-belt wireless heart sound sensor selfby using the Ω shoulder-belt wireless heart sound sensor self-developed by our research group

Summary

Introduction

Heart sound is a complex, non-stationary and quasi-periodic signal that is consisted of multiple heartbeats or cardiac cycles, which mainly contain components such as the first heart sound S1, the second heart sound S2, systolic murmur and diastolic murmur. The biggest advantage of heart sound is universality, stability, uniqueness and collectability [1]. There have been studies that have verified the feasibility of heart sound signals for biometric identification. The heart sound signal as an option for biometric identification was first introduced by Beritelli and Spadaccini [2]. Their method needs to locate and describe S1 and S2, chirp-z transform (CZT) is performed to obtain the feature set, and Euclidean distance (ED) is used as classifier. Phua et al [3] introduced linear frequency band cepstrum (LFBC) for heart sound feature extraction and used two classifiers of vector quantization (VQ) and Gaussian mixture

Methods

Results

Conclusion