Open Access

ARTICLE

Transfer Learning Model to Indicate Heart Health Status Using Phonocardiogram

by Vinay Arora¹, Karun Verma¹, Rohan Singh Leekha², Kyungroul Lee³, Chang Choi^4,*, Takshi Gupta⁵, Kashish Bhatia⁶

1 Department of Computer Science and Engineering, Thapar Institute of Engineering and Technology, Patiala, Punjab, India
2 Associate Application, IT, Concentrix, Gurugram, Haryana, India
3 School of Computer Software, Daegu Catholic University, Gyeongsan, Korea
4 Department of Computer Engineering, Gachon University, Seongnam, 13120, Korea
5 Information Security Engineering, Soonchunhyang University, Korea
6 Department of Computer Engineering, University College of Engineering, Punjabi University, Patiala, Punjab, India

* Corresponding Author: Chang Choi. Email:

(This article belongs to the Special Issue: Emerging Applications of Artificial Intelligence, Machine learning and Data Science)

Computers, Materials & Continua 2021, 69(3), 4151-4168. https://doi.org/10.32604/cmc.2021.019178

Received 05 April 2021; Accepted 10 May 2021; Issue published 24 August 2021

Abstract

The early diagnosis of pre-existing coronary disorders helps to control complications such as pulmonary hypertension, irregular cardiac functioning, and heart failure. Machine-based learning of heart sound is an {efficient} technology which can help minimize the workload of manual auscultation by automatically identifying irregular cardiac sounds. Phonocardiogram (PCG) and electrocardiogram (ECG) waveforms provide the much-needed information for the diagnosis of these diseases. In this work, the researchers have converted the heart sound signal into its corresponding repeating pattern-based spectrogram. PhysioNet 2016 and PASCAL 2011 have been taken as the benchmark datasets to perform experimentation. The existing models, viz. MobileNet, Xception, Visual Geometry Group (VGG16), ResNet, DenseNet, and InceptionV3 of Transfer Learning have been used for classifying the heart sound signals as normal and abnormal. For PhysioNet 2016, DenseNet has outperformed its peer models with an accuracy of 89.04 percent, whereas for PASCAL 2011, VGG has outperformed its peer approaches with an accuracy of 92.96 percent.

---

Keywords

---

Citations