Detection of Murmur from Time Domain Features of Heart Sounds – an Investigation
P. Careena1, M. Mary Synthuja Jain Preetha2, P. Arun3

1P. Careena, Department of Electronics and Communication Engineering, Amal Jyothi College of Engineering, Kanjirapally (Kerala), India.
2M. Mary Synthuja Jain Preetha, Department of Electronics & Communication Engineering, Noorul Islam University, Nagercoil (Tamil Nadu), India.
3P. Arun, Department of Electronics and Communication Engineering, St. Joseph’s College of Engineering and Technology, Palai (Kerala), India.
Manuscript received on 05 June 2019 | Revised Manuscript received on 30 June 2019 | Manuscript Published on 04 July 2019 | PP: 716-723 | Volume-8 Issue-1S4 June 2019 | Retrieval Number: A11360681S419/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Automated identification of valve disorders from heart sounds is a competent task in cardiology. Time domain features like variance (µ), standard deviation (SD), entropy (E), peak amplitude (PA), RMS, crest factor (CRF), impulse factor (IF), shape factor (SHF), energy and clearance factor (CLF) are extensively used in Artificial Intelligence (AI) to reflect the physical attributes of signals. Time domain features are analytically simple and easy to compute. In this paper, the reliability of employing time domain features for the detection of murmur from heart sound is investigated. It is found that energy of the signal is able to detect the murmur from PCG signal with an accuracy of 98.87 %, sensitivity of 99.70 % and specificity of 98.09 %.
Keywords: Energy, Heart Abnormality, Murmur, PCG Signal, Statistical Significance, Type of Heart Signal, Time Domain Features.
Scope of the Article: Software Domain Modelling and Analysis