Open AccessClassification of the Third and Fourth Heart Sounds using Intrinsic Time-Scale Decomposition and Support Vector Machine Technique
Author(s) -
Sai Bharadwaj B.,
Ch. Sumanth Kumar
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.a4500.119119
Subject(s) - phonocardiogram , support vector machine , heart sounds , classifier (uml) , speech recognition , computer science , artificial intelligence , pattern recognition (psychology) , hilbert–huang transform , mel frequency cepstrum , feature extraction , cardiology , medicine , telecommunications , white noise
The two diastolic heart sounds reflecting the malfunctionality of heart are third and fourth heartsounds(S3 and S4). Early detection of heart failures can decrease the risk by identifying the abnormal heart sounds through Phonocardiogram (PCG) signal analysis. In this paper abnormal heart sounds are identified and classified using Intrinsic time scale decomposition (ITD) and Support vector machine (SVM). The proposed framework has been tested on authenticated database signals under abnormal conditions. The success rate is really conquering for the SVM classifier with an accuracy over 94% in the S3 detection and 91% for the S4, which reveals the effectiveness and high efficiency of the proposed work
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom