In this paper, heart sound and its research methods are discussed. The traditional methods and the novel deep learning algorithm methods of heart sound research are introduced respectively. For traditional methods, there are short-time Fourier transform, Wavelet transform, Wigner-Ville Distribution and Hilbert analysis. For novel deep learning algorithm methods, CNN, RNN and U-net framework are mainly introduced. Their characteristics and applications are compared through comparative analysis, and the main research direction and significance of heart sound signal analysis and processing are comprehensively explained.

Linbo Qin. A Review of Heart Sound and Its Research Methods. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 3: 84-91. https://doi.org/10.25236/AJCIS.2023.060311.

[1] D. Gabor. Theory of communication [J]. J. IEE, 1946, 93: 429~457.

[2] VIKHE P S, NEHE N S, THOOL V R, et al. Heart sound abnormality detection using short time Fourier transform and continuous wavelet transform [C]. Second Intemational Conference on Emerging Trends in Engineering & Technology. 2009.

[3] Li S, Li F, Tang S, et al. A Review of Computer-Aided Heart Sound Detection Techniques[J]. BioMed Research International, 2020, 2020:1-10.

[4] BABAEI S, GERANMAYEH A. Heart sound reproduction based on neural network classification of cardiac valve disorders using wavelet transforms of PCG signals [J]. Comput Biol Med, 2009, 39(1): 8-15.

[5] DOKUR Z, OLMEZ T. Heart sound classification using wavelet transfom and incremental self - organizing map [J]. Digit Signal Process, 2008, 18(6): 951-959.

[6] FATEMEH S, SHYAMALA D, AZREENA, et al. Multi-level basis selection of wavelet packet decomposition tree for heart sound classification [J]. Computers in Biology and medicine, 2013, 43(10): 1407-1414.

[7] GAVROVSKA A, BOGDANOVIC V, RELJIN I, et al. Automatic heart sound detection in pediatric patients without electrocardiogram reference via pseudo-affine Wigner-Ville distribution and Haar wavelet lifting [J]. Comput Methods Programs Biomed, 2014, 113(2): 515-528.

[8] DJEBBARI A, BEREKSI-EGUIG F. Detection of the valvular split within the second heart sound using the reassigned smoothed pseudo Wigner-Ville distribution [J]. Biomed Eng Online, 2013, 12(1): 37.

[9] LOZANO M, FIZ J, ANTONIO J R. Performance evaluation of the Hilbert-Huang transform for respiratory sound analysis and its application to continuous adventitious sound characterization [C]. Elsevier North-Holland, Inc., 2016: 99-116.

[10] TSENGYL, KO PY, JAW F S. Detection of the third and fourth heart sounds using Hilbert-Huang transform [J]. Biomed Eng Online, 2012, 11(1): 8.

[11] HUNG T H, CHOU C C, FANG W C, et al. Time-frequency analysis of heart sound signals based on Hilbert-Huang transfomation [C]. IEEE Intermational Symposium on Consumer Electronics. 2012.

[12] ABDUHZ, NEHARYEA, WAHED MA, et al. Classification of heart sounds using fractional fourier transform based Mel-frequency spectral coefficients and traditional classifiers [J]. Biomedical Signal Processing and Control, 2020, 57 (101788): 1-11.

[13] Gu XX, Zhu ML, Wang L, et al. Feature extraction of ECG signal based on wavelet transform [J]. Software Guide, 2021, 20(5): 77-81.

[14] Abdolrahman P, Sadasivan P. DENS-ECG: a deep learning approach for ECG signal delineation [J]. Expert Syst Appl, 2021, 165: 1-15.

[15] UGUZ H. A biomedical system based on artificial neural network and principal component analysis for diagnosis of the heart valve diseases [J]. J Med Syst, 2012, 36(1): 61-72.

[16] SPRINGERD B, LIONEL T, CLIFFORDG D. Logistic regression-HSMM-based heart sound segmentation L [J]. IEEE Transactions on Bio-medical Engineering, 2016, 63(4): 822 -832.

[17] SUMETH Y, AKINORI N, WAREEK, et al. A framework for automatic heart sound analysis without segmentation. [J]. Biomedical engineering online, 2011, 10 (1): 13-36.

[18] Hu S, Cai W, Gao T, et al. Robust wave-feature adaptive heartbeat classification based on self-attention mechanism using a transformer model [J]. Physiol Meas, 2021, 42(12): 125001.

[19] Maknickas V, Maknickas A. Recognition of normal-abnormal phonocardiographic signals using deep convolutional neural networks and mel-frequency spectral coefficients [J]. Physiological Measurement, 2017, 38(8): 1671-1684

[20] WHITAKERB M, ANDERSOND V. Heart sound classification via sparse coding [C] //2016 computing in Cardiology Conference (CinC), IEEE, 2016: 805 -808.

[21] Cheng X F, Fu N T. A Review of Heart Sound Identification Recognition[J]. Journal of Shanghai Jiaotong University, 2014, 48(12):1745-1750.

[22] Viktor M, Nikolai Z, Grigory O. Deep learning for ECG segmentation [C]//Neuroinformatics 2019, Cham: Springer International Publishing, 2020: 246-254.

[23] Aspuru J, Ochoa-Brust A, Felix RA, et al. Segmentation of the ECG signal by means of a linear regression algorithm [J]. Sensors, 2019, 19(4): 775.

[24] Vijayakumar V, Ummar S, Varghese T J, et al. ECG noise classification using deep learning with feature extraction[J]. Signal Image Video Proces, 2022, 1: 1-7

[25] Yan G, Liang S, Zhang Y, et al. Fusing transformer model with temporal features for ECG heartbeat classification[C]//2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 2019.

[26] Ma H, Chen C, Zhu Q, et al. An ECG signal classification method based on dilated causal convolution [J]. Comput Math Method Med, 2021, 2021(3): 1-10.

[27] Li T, Zhou M. ECG classification using wavelet packet entropy and random forests [J]. Entropy, 2016, 18(8): 285.

[28] Nurmaini S, Darmawahyuni A, Rachmatullah MN, et al. Beat-to-beat electrocardiogram waveform classification based on a stacked convolutional and bidirectional long short-term memory [J]. IEEE Access, 2021, 99: 1.

[29] Kalyakulina AI, Yusipov II, Moskalenko VA, et al. LUDB: a new open-access validation tool for electrocardiogram delineation algorithms [J]. IEEE Access, 2020, 8: 186181-186190.

[30] Kumar A, Tomar H, Mehla VK, et al. Stationary wavelet transform based ECG signal denoising method [J]. ISA Trans, 2021, 114: 251-262.

[31] ARI S, HEMBRAM K, SAHA G. Detection of cardiac abnormality from PCG signal using LMS based least square SVM classifier L. Expert Systems with Applications, 2010, 37(12):8019-8026.

[32] Do E, Boynton J, Lee BS, et al. Data augmentation for 12-lead ECG beat classification [J]. SN Comput Sci, 2022, 3(1): 1-17.

[33] MA Jing, CAI Wenjie, YANG Li. Analysis of heart sound signals [J]. Chinese Journal of Medical Physics, 2017, 34(11): 1172-1175. doi: 10.3969/j.issn.1005-202X. 2017.11.017.