Back close

Anomaly Detection in Phonocardiogram Employing Deep Learning

Publication Type : Conference Paper

Publisher : Advances in Intelligent Systems and Computing

Source : Advances in Intelligent Systems and Computing, Springer Verlag, Volume 711, p.525-534 (2019)

Url : https://www.scopus.com/inward/record.uri?eid=2-s2.0-85049936748&doi=10.1007%2f978-981-10-8055-5_47&partnerID=40&md5=48a2a7f819fcfbb09077824184450396

ISBN : 9789811080548

Keywords : Anomaly detection, Cardiology, Data mining, Deep learning, Heart, heart disease, Heart sounds, Learning algorithms, Learning models, Learning systems, Long short-term memory, Phonocardiograms, Phonocardiography, Pre-processing method, Raw signals, remote health monitoring

Campus : Amritapuri, Coimbatore

School : School of Engineering

Center : Computational Engineering and Networking

Department : Electronics and Communication

Year : 2019

Abstract : Phonocardiogram (PCG) is the recording of heart sounds and murmurs. PCG compliments electrocardiogram in detection of heart diseases especially in the initial screenings due to its simplicity and low cost. Detecting abnormal heart sounds by algorithms is important for remote health monitoring and other scenarios where having an experienced physician is not possible. While several studies exist, we explore the possibility of detecting anomalies in heart sounds and murmurs using Deep-learning algorithms on well-known Physionet Dataset. We performed the experiments by employing various algorithms such as RNN, LSTM, GRU, B-RNN, B-LSTM and CNN. We achieved 80% accuracy in CNN 3 layer Deep learning model on the raw signals without performing any preprocessing methods. To our knowledge this is the highest reported accuracy that employs analyzing the raw PCG data. © 2019, Springer Nature Singapore Pte Ltd.

Cite this Research Publication : V. G. Sujadevi, Dr. Soman K. P., Vinayakumar, R., and Sankar, A. U. Prem, “Anomaly Detection in Phonocardiogram Employing Deep Learning”, in Advances in Intelligent Systems and Computing, 2019, vol. 711, pp. 525-534.

Admissions Apply Now