Cardiac auscultation is a basic method for the initial diagnosis and screening of congenital heart disease (CHD). The analysis of heart sound signals is conducive to the realization of machine-assisted auscultation. In this paper, the original heart sound signal was denoised and reconstructed by wavelet transform. The Shannon-envelope of the heart sound signal was extracted and the cardiac cycles were segmented. The feature parameters of MFCC and BFCC with a frame length of 2048 were extracted from S1 as the starting point, and a set of 32-dimensional feature was obtained. It was used as input to the BP neural network for learning, training, and testing of the network. 60 heart sounds of CHD and 60 normal heart sounds were selected randomly for training. Also the heart sounds of 40 CHD and 40 normal heart sounds were selected randomly to test after training. The experimental results show that the sensitivity is 85.11%, and the specificity is 88.89% of BP network by using BFCC features. The network sensitivity of using the MFCC is 86.96%, and the specificity is 90.91%. The BP network by using MFCC feature parameter has a more significant recognition ratio than the one using BFCC feature parameter as the input.
| Published in | Asia-Pacific Journal of Information Science and Technology (Volume 1, Issue 1) |
| Page(s) | 1-6 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2024. Published by Science Publishing Group |
Congenital Heart Disease (CHD), Wavelet Denoising, MFCC, BFCC, BP Neural Network
| [1] | 高燕,黄国英.先天性心脏病病因及流行病学研究进展[J].中国循证儿科杂志,2008,3(3):213-222。 |
| [2] | 田文雪.基于香农熵的心音信号检测方法研究[J].无线互联科技,2017(6):3-4。 |
| [3] | 郭兴明,何彦青,卢德林,等.平移不变小波在心音信号去噪中的应用[J].计算机工程与应用,2014,50(24):209-212。 |
| [4] | 郭兴明,蒋鸿,郑伊能.基于改进的维奥拉积分方法提取心音信号包络[J].仪器仪表学报,2016,37(10):2352-2358。 |
| [5] | Yan Z, Jiang Z, Miyamoto A, et al. The moment segmentation analysis of heart sound pattern.[J]. Computer Methods & Programs in Biomedicine, 2010, 98(2):140-150. |
| [6] | Abo-Zahhad M, Ahmed S M, Abbas S N. Biometrics from heart sounds: Evaluation of a new approach based on wavelet packet cepstral features using HSCT-11 database ☆[J]. Computers & Electrical Engineering, 2016, 53:346-358. |
| [7] | 孙科学,魏敏,宋江珉,等.双声道心音能量熵比的提取与识别研究[J].计算机技术与发展,2017,27(12):166-169。 |
| [8] | 郭兴明,张文英,袁志会,等.基于EMD关联维数和多重分形谱的心音识别[J].仪器仪表学报,2014,35(4):827-833。 |
| [9] | Arslan A, Yildiz O. Automated Auscultative Diagnosis System for Evaluation of Phonocardiogram Signals Associated with Heart Murmur Diseases[J]. Gazi University Journal of Science, 2018, 31(1). |
| [10] | Uyar K, İlhan A. Diagnosis of heart disease using genetic algorithm based trained recurrent fuzzy neural networks[J]. Procedia Computer Science, 2017, 120:588-593. |
| [11] | 许莉莉,师炜,郭学谦,等.基于最小二乘支持向量机的心音分类识别研究[J].中国医疗设备,2017,32(4):38-41。 |
| [12] | 钟丽莎,万江中,黄志伟,等.基于GMM的心音信号生物识别方法研究[J].中国医疗器械杂志,2013(2):92-95。 |
| [13] | Chen T, Zhao S, Shao S, et al. Non-invasive diagnosis methods of coronary disease based on wavelet denoising and sound analyzing[J]. Saudi Journal of Biological Sciences, 2017, 24(3):526. |
| [14] | 段瑞琪.基于MFCC和短时能量混合的心音身份识别[D].燕山大学,2015。 |
| [15] | Gulzar T, Singh A, Sharma S. Comparative Analysis of LPCC, MFCC and BFCC for the Recognition of Hindi Words using Artificial Neural Networks[J]. Acta Materialia, 2014, 56(13):3132-3145. |
| [16] | 张磊邦,唐荣斌,蒋建波,等.基于小波变换的心音特征值提取算法研究[J].电子测量技术,2014,37(6):42-46。 |
| [17] | Rehman F U, Kumar C, Kumar S, et al. VQ based comparative analysis of MFCC and BFCC speaker recognition system[C]// International Conference on Information and Communication Technologies. 2017:28-32. |
APA Style
Zhu Lili, Pan Jiahua, Shi Jihong, Yang Hongbo, Tan Chaowen, et al. (2019). Heart Sound Recognition of Congenital Heart Disease Based on MFCC and BFCC Feature Extraction. Asia-Pacific Journal of Information Science and Technology, 1(1), 1-6.
ACS Style
Zhu Lili; Pan Jiahua; Shi Jihong; Yang Hongbo; Tan Chaowen, et al. Heart Sound Recognition of Congenital Heart Disease Based on MFCC and BFCC Feature Extraction. Asia-Pac. J. Inf. Sci. Technol. 2019, 1(1), 1-6.
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10036154,
author = {Zhu Lili and Pan Jiahua and Shi Jihong and Yang Hongbo and Tan Chaowen and Wang Weilian},
title = {Heart Sound Recognition of Congenital Heart Disease Based on MFCC and BFCC Feature Extraction},
journal = {Asia-Pacific Journal of Information Science and Technology},
volume = {1},
number = {1},
pages = {1-6},
url = {https://www.sciencepublishinggroup.com/article/10036154},
abstract = {Cardiac auscultation is a basic method for the initial diagnosis and screening of congenital heart disease (CHD). The analysis of heart sound signals is conducive to the realization of machine-assisted auscultation. In this paper, the original heart sound signal was denoised and reconstructed by wavelet transform. The Shannon-envelope of the heart sound signal was extracted and the cardiac cycles were segmented. The feature parameters of MFCC and BFCC with a frame length of 2048 were extracted from S1 as the starting point, and a set of 32-dimensional feature was obtained. It was used as input to the BP neural network for learning, training, and testing of the network. 60 heart sounds of CHD and 60 normal heart sounds were selected randomly for training. Also the heart sounds of 40 CHD and 40 normal heart sounds were selected randomly to test after training. The experimental results show that the sensitivity is 85.11%, and the specificity is 88.89% of BP network by using BFCC features. The network sensitivity of using the MFCC is 86.96%, and the specificity is 90.91%. The BP network by using MFCC feature parameter has a more significant recognition ratio than the one using BFCC feature parameter as the input.},
year = {2019}
}
TY - JOUR T1 - Heart Sound Recognition of Congenital Heart Disease Based on MFCC and BFCC Feature Extraction AU - Zhu Lili AU - Pan Jiahua AU - Shi Jihong AU - Yang Hongbo AU - Tan Chaowen AU - Wang Weilian Y1 - 2019/02/01 PY - 2019 T2 - Asia-Pacific Journal of Information Science and Technology JF - Asia-Pacific Journal of Information Science and Technology JO - Asia-Pacific Journal of Information Science and Technology SP - 1 EP - 6 PB - Science Publishing Group UR - http://www.sciencepg.com/article/10036154 AB - Cardiac auscultation is a basic method for the initial diagnosis and screening of congenital heart disease (CHD). The analysis of heart sound signals is conducive to the realization of machine-assisted auscultation. In this paper, the original heart sound signal was denoised and reconstructed by wavelet transform. The Shannon-envelope of the heart sound signal was extracted and the cardiac cycles were segmented. The feature parameters of MFCC and BFCC with a frame length of 2048 were extracted from S1 as the starting point, and a set of 32-dimensional feature was obtained. It was used as input to the BP neural network for learning, training, and testing of the network. 60 heart sounds of CHD and 60 normal heart sounds were selected randomly for training. Also the heart sounds of 40 CHD and 40 normal heart sounds were selected randomly to test after training. The experimental results show that the sensitivity is 85.11%, and the specificity is 88.89% of BP network by using BFCC features. The network sensitivity of using the MFCC is 86.96%, and the specificity is 90.91%. The BP network by using MFCC feature parameter has a more significant recognition ratio than the one using BFCC feature parameter as the input. VL - 1 IS - 1 ER -
Information
Email: