A Heart Sound Signal Classification Method Based on the Mixed Characteristics of Mel Cepstrum Coefficient and Second-Order Spectrum
Pages 3533 - 3552
Abstract
Heart diseases have a great impact on human health. Heart sound signals contain a lot of useful information about heart diseases. Therefore, various heart diseases can be judged by heart sound auscultation. In order to improve the accuracy of classification and judgment, a heart sound signal classification method based on the mixed characteristics of Mel cepstrum coefficient and second-order spectrum is proposed: first, a class of normal heart sounds and aortic stenosis, mitral regurgitation, mitral stenosis, mitral valve prolapse. The Mel cepstrum coefficients and second-order spectral features of four kinds of abnormal heart sounds with mitral valve prolapse are extracted separately and then combined into a new feature. The convolution neural network is used for learning and classification. The whole data set has a total of 1000 audio records, which are randomly divided into test sets and training sets by 2:3. From the experimental results, it can be seen that the accuracy rate in the training set is 99.6%, and the accuracy rate in the test set is 98.5%. Compared with other traditional classification and recognition methods, the accuracy is significantly improved.
References
[1]
Ahmed N, Natarajan T, and Rao KR Discrete cosine transform IEEE Trans. Comput. 1974 100 1 90-93
[2]
Alqudah AM, Alquran H, and Qasmieh IA Classification of heart sound short records using bispectrum analysis approach images and deep learning Netw. Model. Anal. Health Informat. Bioinformat. 2020 9 1-16
[3]
W. Astuti, W. Sediono, A.M. Aibinu, R. Akmeliawati, M.J.E. Salami, Adaptive short time fourier transform (STFT) analysis of seismic electric signal (SES): a comparison of hamming and rectangular window (2012).
[4]
O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma., Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A.C. Berg, L. Fei-Fei, Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211–252 (2015)
[5]
D.R. Brillinger, An introduction to polyspectra. in Selected Works of David Brillinger (Springer, New York, NY, 2011), pp. 149–172
[6]
S. Davis, P. Mermelstein, Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust., Speech, Signal Process. 28(4), 357–366 (1980)
[7]
Deng S-W and Han J-Q Towards heart sound classification without segmentation via autocorrelation feature and diffusion maps Fut. Gener. Comput. Syst. 2016 60 13-21
[8]
Deng M, Meng T, Cao J, Wang S, Zhang J, and Fan H Heart sound classification based on improved mfcc features and convolutional recurrent neural networks Neural Netw. 2020 130 22-32
[9]
Ghosh SK, Ponnalagu RN, Tripathy RK, and Acharya UR Auto mated detection of heart valve diseases sing chirplet transform and multiclass composite classifer with PCG signals Comput. Biol. Med. 2020 118
[10]
K.M. Gaikwad, M.S. Chavan, Removal of high frequency noise from ECG signal using digital IIR Butterworth filter (IEEE, 2014), pp. 121–124
[11]
D.P. Kingma, J. Ba, Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
[12]
Krizhevsky A, Sutskever I, and Hinton GE Imagenet classification with deep convolutional neural networks Commun. ACM 2017 60 6 84-90
[13]
Lam M, Lee T, Boey P, Ng W, Hey H, Ho K, and Cheong P Factors influencing cardiac auscultation proficiency in physician trainees Singap. Med. J. 2005 46 1 11
[14]
S. McCandless, An algorithm for automatic formant extraction using linear prediction spectra. IEEE Trans. Acoust., Speech, Signal Process. 22(2), 135–141 (1974)
[15]
Nikias CL and Raghuveer MR Bispectrum estimation: a digital signal processing framework Proc. IEEE 1987 75 7 869-891
[16]
World Health Organization, Waist circumference and waist-hip ratio: report of a WHO xpert consultation, Geneva, 8–11 December 2008 (2011)
[17]
Quinlan JR Induction of decision trees Mach. Learn. 1986 1 81-106
[18]
Roth GA, Johnson C, Abajobir A, Abd-Allah F, Abera SF, Abyu G, Ahmed M, Aksut B, Alam T, Alam K, et al. Global, regional, and national burden of cardiovascular diseases for 10 causes, 1990 to 2015 J. Am. Coll. Cardiol. 2017 70 1 1-25
[19]
Ruan Y, Guo Y, Zheng Y, Huang Z, Sun S, Kowal P, Shi Y, and Wu F Cardiovascular disease (CVD) and associated risk factors among older adults in six low-and middle-income countries: results from sage wave 1 BMC Public Health 2018 18 1 1-13
[20]
K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
[21]
Springer DB, Tarassenko L, and Clifford GD Logistic regression-HSMM-based heart sound segmentation IEEE Trans. Biomed. Eng. 2015 63 4 822-832
[22]
S.L. Strunic, F. Rios-Gutiérrez, R. Alba-Flores, G. Nordehn, S. Burns, Detection and Classification of Cardiac Murmurs using Segmentation Techniques and Artificial Neural Networks (IEEE, 2007), pp. 397–404
[23]
Sun S, Jiang Z, Wang H, and Fang Y Automatic moment segmentation and peak detection analysis of heart sound pattern via short-time modified Hilbert transform Comput. Methods Programs Biomed. 2014 114 3 219-230
[24]
Yaseen G-Y and Son S Kwon, Classification of heart sound signal using multiple features Appl. Sci. 2018 8 12 2344
[25]
Yuenyong S, Nishihara A, Kongprawechnon W, and Tungpimolrut K A framework for automatic heart sound analysis without segmentation Biomed. Eng. Online 2011 10 1-23
Recommendations
Heart Sound Classification Using Deep Learning Techniques Based on Log-mel Spectrogram
AbstractIn this study, two models for classifying heart rate sounds are proposed to classify heart sound by deep learning techniques based on the log-mel spectrogram of heart sound signals. The heart sound dataset comprises five classes, one normal class ...
Automatic pediatric congenital heart disease classification based on heart sound signal
AbstractCongenital heart diseases (CHD) are the most common birth defects, and the early diagnosis of CHD is crucial for CHD therapy. However, there are relatively few studies on intelligent auscultation for pediatric CHD, due to the fact that ...
Highlights- A database of heart sounds in CHD is established using electronic stethoscopes and is proposed to be made publicly available online.
Classification of heart sound signals using a novel deep WaveNet model
Highlights- Automated detection of five heart sounds: normal, aortic stenosis, mitral valve prolapse, mitral stenosis, mitral regurgitation.
- Novel deep WaveNet model is proposed.
- Obtained average training classification accuracy of 97%.
- ...
Abstract Background and objectivesThe high mortality rate and increasing prevalence of heart valve diseases globally warrant the need for rapid and accurate diagnosis of such diseases. Phonocardiogram (PCG) signals are used in this study due to the low ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Publisher
Birkhauser Boston Inc.
United States
Publication History
Published: 12 March 2024
Accepted: 15 December 2023
Revision received: 13 December 2023
Received: 01 June 2023
Author Tags
Qualifiers
- Research-article
Funding Sources
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 06 Jan 2025