Heart sound signal recovery based on time series signal prediction using a recurrent neural network in the long short-term memory model

In this research, we propose a method for recovering heart sound signals that comprises the long short-term memory prediction model based on the recurrent neuron network architecture. The complete heart sound signal is used to implement a prediction model to recover damaged or incomplete heart sound signals. Root mean square errors (RMSEs) and Pearson’s correlation coefficients are used for numerical evaluation. The signals of 13 out of 15 subjects are considerably improved, with the RMSE being as low as 0.03 ± 0.04. Using the Pearson correlation coefficients to estimate the degree of signal recovery, the highest coefficient of correlation between the original and recovered time-domain waveforms is 0.93, and that between the corresponding spectra is 0.967. Waveforms and spectra are used to compare the results graphically. The recovered signal more closely fits the original signal than the interfered signal. Additionally, excess frequency components in the recovered spectra are found to be filtered out and important features retained. Thus, the proposed method not only recovers incomplete or disturbed signals but also has the effect of a filter.

[1]  Mounya Elhilali,et al.  Computerized Lung Sound Screening for Pediatric Auscultation in Noisy Field Environments , 2018, IEEE Transactions on Biomedical Engineering.

[2]  Babak Mohammadi,et al.  Letter to the editor “Estimation of sodium adsorption ratio indicator using data mining methods: a case study in Urmia Lake basin, Iran” by Mohammad Taghi Sattari, Arya Farkhondeh, and John Patrick Abraham , 2019, Environmental Science and Pollution Research.

[3]  Franz Pernkopf,et al.  Heart Sound Segmentation—An Event Detection Approach Using Deep Recurrent Neural Networks , 2018, IEEE Transactions on Biomedical Engineering.

[4]  Xiangang Li,et al.  Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition , 2014, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[5]  Francesco Renna,et al.  Adaptive Sojourn Time HSMM for Heart Sound Segmentation , 2019, IEEE Journal of Biomedical and Health Informatics.

[6]  B. Mohammadi,et al.  A comparison between the application of empirical and ANN methods for estimation of daily global solar radiation in Iran , 2018, Theoretical and Applied Climatology.

[7]  C. A. Bertrand,et al.  A Study of Heart Sounds and Murmurs by Direct Heart Recordings , 1956, Circulation.

[8]  D. Danford,et al.  Heart Murmur in a Child , 2004 .

[9]  Syed Anas Imtiaz,et al.  An Algorithm for Heart Rate Extraction From Acoustic Recordings at the Neck , 2019, IEEE Transactions on Biomedical Engineering.

[10]  V. Elamaran,et al.  Spectral Fault Recovery Analysis Revisited With Normal and Abnormal Heart Sound Signals , 2018, IEEE Access.

[11]  E. Craige,et al.  Origin of the third heart sound: comparison of ventricular wall dynamics in hyperdynamic and hypodynamic types. , 1985, Journal of the American College of Cardiology.

[12]  Giuliano Armano,et al.  Heart Sound Analysis for Diagnosis of Heart Diseases in Newborns , 2013 .

[13]  M. Sabarimalai Manikandan,et al.  Automatic Identification of S1 and S2 Heart Sounds Using Simultaneous PCG and PPG Recordings , 2018, IEEE Sensors Journal.

[14]  Peter Hult,et al.  Feature Extraction for Systolic Heart Murmur Classification , 2006, Annals of Biomedical Engineering.

[15]  Hava T. Siegelmann,et al.  On the Computational Power of Neural Nets , 1995, J. Comput. Syst. Sci..

[16]  L. N. Sharma,et al.  Heart Sound Extraction From Sternal Seismocardiographic Signal , 2018, IEEE Signal Processing Letters.

[17]  P. Engel,et al.  Late systolic click from isolated tricuspid valve prolapse simulating paradoxical splitting of the second heart sound. , 1985, Journal of the American College of Cardiology.

[18]  Syed Anas Imtiaz,et al.  Algorithms for Automatic Analysis and Classification of Heart Sounds–A Systematic Review , 2019, IEEE Access.

[19]  Rajib Rana,et al.  Phonocardiographic Sensing Using Deep Learning for Abnormal Heartbeat Detection , 2018, IEEE Sensors Journal.

[20]  Roozbeh Moazenzadeh,et al.  Assessment of bio-inspired metaheuristic optimisation algorithms for estimating soil temperature , 2019, Geoderma.

[21]  Gabriel Jimenez-Moreno,et al.  Deep Neural Networks for the Recognition and Classification of Heart Murmurs Using Neuromorphic Auditory Sensors , 2017, IEEE Transactions on Biomedical Circuits and Systems.

[22]  T. Sakamoto,et al.  Noninvasive study of the presystolic component of the first heart sound in mitral stenosis. , 1986, Journal of the American College of Cardiology.

[23]  Hemodynamic Correlates of the Third Heart Sound During the Evolution of Chronic Heart Failure , 1993 .

[24]  Babak Mohammadi.  Letter to the Editor “Design of an integrated climatic assessment indicator (ICAI) for wheat production: A case study in Jiangsu Province, China” by Xiangying Xu, Ping Gao, Xinkai Zhu, Wenshan Guo, Jinfeng Ding, Chunyan Li, Min Zhu, Xuanwei Wu , 2019 .

[25]  Andrew W. Senior,et al.  Long short-term memory recurrent neural network architectures for large scale acoustic modeling , 2014, INTERSPEECH.

[26]  Ashok Mondal,et al.  A Noise Reduction Technique Based on Nonlinear Kernel Function for Heart Sound Analysis , 2018, IEEE Journal of Biomedical and Health Informatics.

[27]  K. P. Soman,et al.  Wavelet-based fundamental heart sound recognition method using morphological and interval features , 2017 .

[28]  Anirban Mukherjee,et al.  Detection of Third Heart Sound Using Variational Mode Decomposition , 2018, IEEE Transactions on Instrumentation and Measurement.