Title :
Detection of heart disease using binary particle swarm optimization
Author :
Elbedwehy, Mona Nagy ; Zawbaa, Hossam M. ; Ghali, Neveen ; Hassanien, Aboul Ella
Author_Institution :
Math. Dept., Mansoura Univ. Egypt, Damietta, Egypt
Abstract :
This article introduces a computer-aided diagnosis system of the heart valve disease using binary particle swarm optimization and support vector machine, in conjunction with K-nearest neighbor and with leave-one-out cross-validation. The system was applied in a representative heart dataset of 198 heart sound signals, which come both from healthy medical cases and from cases suffering from the four most usual heart valve diseases: aortic stenosis (AS), aortic regurgitation (AR), mitral stenosis (MS) and mitral regurgitation (MR). The introduced approach starts with an algorithm based on binary particle swarm optimization to select the most weighted features. This is followed by performing support vector machine to classify the heart signals into two outcome: healthy or having a heart valve disease, then its classified the having a heart valve disease into four outcomes: aortic stenosis (AS), aortic regurgitation (AR), mitral stenosis (MS) and mitral regurgitation (MR). The experimental results obtained, show that the overall accuracy offered by the employed approach is high compared with other techniques.
Keywords :
cardiology; diseases; medical signal processing; nonparametric statistics; particle swarm optimisation; patient diagnosis; signal classification; support vector machines; AR; AS; MR; MS; aortic regurgitation; aortic stenosis; binary particle swarm optimization; computer-aided diagnosis system; healthy heart sound signal classification; heart dataset; heart valve disease detection; k-nearest neighbor; leave-one-out cross-validation; mitral regurgitation; mitral stenosis; support vector machine; Accuracy; Diseases; Heart; Kernel; Particle swarm optimization; Support vector machines; Valves; Binary particle swarm optimization; Heart sounds; Heart valve diseases; Support vector machine;
Conference_Titel :
Computer Science and Information Systems (FedCSIS), 2012 Federated Conference on
Conference_Location :
Wroclaw
Print_ISBN :
978-1-4673-0708-6
Electronic_ISBN :
978-83-60810-51-4