A Hybrid Approach for Identification of Coronary Heart Disease using PSO-DEFS

Conference: Recent Trends in Information Processing, Computing, Electrical and Electronics
Author(s): J.Kowsalya Devi, P.Geetha Year: 2017
Grenze ID: 02.IPCEE.2017.1.111 Page: 273-283

Abstract

Coronary Heart disease (CHD) is a major cause of morbidity and mortality in the modern society. Medical\ndiagnosis is an complicated task that should be performed accurately and efficiently. This study analyzes the Behavioral Risk\nFactor Surveillance System, survey to test whether self-reported cardiovascular disease rates are higher. Cardiovascular\ndisease (CVD) can be classified into (1) chest pain (2) stroke and (3) heart attack. Heart care study specifies 13 attributes to\npredict the morbidity. Besides regular attributes other attributes such as BMI (Body Mass Index), physician supply, age,\nethnicity, education, income, and others are used for prediction. An automated system for medical diagnosis would enhance\nmedical care and reduce costs. Many existing methods found out the CHD affected patients by estimating the plaque\nthickness. These methods have the issues of lower accuracy and higher time complexity. In order to overcome the above\nlimitations, hybrid approach based CHD detection is introduced in the proposed work. At first, the input image is\npreprocessed using green channel extraction and median filter. Subsequently, the features are extracted by gradient based\nfeatures like HOG with CLBP. The texture features are concentrated with various rotations to calculate the edges. We present\na hybrid feature selection which combines the PSO and DEFS for minimizing the time complexity. A binary SVM classifier\ncategorizes the normal and abnormal images of patients. Finally, the patients affected by CHD are further classified by MLP.\nThe effectiveness of the system is measured with the parameters such as accuracy, specificity and sensitivity.

<< BACK

IPCEE - 2017