Efficient Diagnosis and Analysis of Cardiovascular Disease Through Computational Intelligence

Abstract

The unhealthy life style and the dynamic conditions of environmental changes has newlinerapidly increased the chances of heart diseases. An early diagnosis of heart newlinediseases can minimize the future critical effects and fatal conditions. The need of newlineautomation in medical domain has increased in many folds in recent time. The newlineautomation systems are primarily targeted for early monitoring of diseases. The newlineautomation has a great help at the time of diagnosing and criticality in diagnosis newlineof a disease. With advancement of new technologies in learning system, the newlineprocessing and classification of observing data has attained speed and accuracy in newlineit. However, the difficulty in observing data and its dependency on the newlineclassification process resulted into a large data processing. This limits the newlineapplication of automation system in different critical usage. The objective of newlinespeedy processing and infallible accuracy with low processing overhead for early newlinediagnosis of heart diseases is focused in the proposed research work. newlineThe presented approach developed a new data representation based on the newlinecharacteristic representation of the monitoring parameters. Fourteen monitoring newlineparameters referred for heart disease diagnosis from the standard Cleveland data newlineset. The said parameters were used in the processing of heart disease diagnosis. A newlineweighted clustering approach based on distance and gain parameters in clustering newlineis presented. The proposed data sub clustering approach enhances the learning newlineperformance and it resulted into a faster and accurate decision system as compared newlineto present approaches. newlineIn order to enhance the decision accuracy in addition to separate data monitoring, newlinea continuous observation from ECG signal is proposed. Twelve descriptive features of ECG signal that defines the characteristic and variations related to heart operation are developed. The feature overhead is addressed to minimize by a fusion approach, newlinewhere a selective approach of feature vector for a learning approach using neural newlinenetwork is presented. The pro