You are in:Home/Publications/Inbarani HH, Kumar SS, Azar AT, Hassanien AE (2014) Soft Rough Sets For Heart Valve Disease Diagnosis. In: A.E. Hassanien, M.F. Tolba, A.T. Azar (eds.), Advanced Machine Learning Technologies and Applications, Communications in Computer and Information Science, Vol. 488, pp. 347-356, Springer-Verlag GmbH Berlin/Heidelberg. DOI: 10.1007/978-3-319-13461-1_33

Dr. Assoc. Prof. Ahmad Taher Azar :: Publications:

Title:
Inbarani HH, Kumar SS, Azar AT, Hassanien AE (2014) Soft Rough Sets For Heart Valve Disease Diagnosis. In: A.E. Hassanien, M.F. Tolba, A.T. Azar (eds.), Advanced Machine Learning Technologies and Applications, Communications in Computer and Information Science, Vol. 488, pp. 347-356, Springer-Verlag GmbH Berlin/Heidelberg. DOI: 10.1007/978-3-319-13461-1_33
Authors: Not Available
Year: 2014
Keywords: Not Available
Journal: Not Available
Volume: Not Available
Issue: Not Available
Pages: Not Available
Publisher: Not Available
Local/International: International
Paper Link:
Full paper Not Available
Supplementary materials Not Available
Abstract:

Heart murmur (systolic and diastolic) is the result of different cardiac valve disorders. The auscultation of the heart is still the first basic analysis tool used to calculate the functional state of the heart, as well as the first pointer used to submit the patient to a cardiologist. In order to develop the diagnosis capabilities of auscultation, pattern recognition algorithms are currently being technologically advanced to assist the physician at primary care centers for adult and pediatric residents. A basic task for the diagnosis from the phonocardiogram is to detect the events (heart sounds and murmurs) present in the cardiac cycle. Four common murmurs were considered including aortic stenosis, aortic regurgitation, mitral stenosis, and mitral regurgitation. In this work modified soft rough set is used as a classifier in the classification of three heart valve data sets. Four types of classification approaches were compared to evaluate the discriminatory power of the classification such as (Decision table, MultiLayer Perceptron (MLP), Back Propagation Network (BPN) and Navie Bayes). The best results were achieved by soft rough sets. The favorable results demonstrate the effectiveness of the proposed approach for heart sounds’ classification.

Google ScholarAcdemia.eduResearch GateLinkedinFacebookTwitterGoogle PlusYoutubeWordpressInstagramMendeleyZoteroEvernoteORCIDScopus