Identification of Normal and Abnormal Heart Sounds by Prominent Peak Analysis

This paper presents an automatic method of segmenting normal and abnormal Phonocardiography (PCG) signals by analyzing prominent peak distances, amplitudes, area, and cardiac cycle durations. Principal Component Analysis (PCA) is used to reduce the dimensions of the calculated prominent peak ratios. Subsequently, Artificial Neural Networks (ANNs) are used to identify the boundary between normal and abnormal heart sounds. PhysioNet/CinC normal and abnormal data recordings are used in this proposed method to segment S1 and S2. The segmentation results are used to differentiate normal and abnormal heart sound signals. The identification of normal and abnormal heart sounds achieved 90% accuracy. The results and observations of this paper are verified with some clinical examination observations.

[1]  Aggelos K. Katsaggelos,et al.  Heart sound anomaly and quality detection using ensemble of neural networks without segmentation , 2016, 2016 Computing in Cardiology Conference (CinC).

[2]  Jan Gieraltowski,et al.  PCG classification using a neural network approach , 2016, 2016 Computing in Cardiology Conference (CinC).

[3]  Xiuju Fu,et al.  Artificial Neural Networks , 2009, Wiley Encyclopedia of Computer Science and Engineering.

[4]  Qiao Li,et al.  An open access database for the evaluation of heart sound algorithms , 2016, Physiological measurement.

[5]  Ronald W. Schafer,et al.  Design of digital filter banks for speech analysis , 1971 .

[6]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[7]  Sumiyuki Koizumi.  ON THE HILBERT TRANSFORM I , 1959 .

[8]  Kumar Sricharan,et al.  Classifying heart sound recordings using deep convolutional neural networks and mel-frequency cepstral coefficients , 2016, 2016 Computing in Cardiology Conference (CinC).

[9]  Yan Liu,et al.  Normal / abnormal heart sound recordings classification using convolutional neural network , 2016, 2016 Computing in Cardiology Conference (CinC).

[10]  J. Bendat,et al.  The Hilbert Transform , 2012 .

[11]  Chen Chen,et al.  A Novel Cardiac Auscultation Monitoring System Based on Wireless Sensing for Healthcare , 2018, IEEE Journal of Translational Engineering in Health and Medicine.

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

[13]  A. Roli.  Artificial Neural Networks , 2012, Lecture Notes in Computer Science.