Abstract

The creation of an automated system for heart disease detection was once one of the more commonundertakings in the healthcare industries. For this purpose, the different types of big data analytics technologies aredeveloped in the conventional works to predict the heart disease. Still, it limits with the problems associated to theelements of high complexity, time consumption, over fitting, and mis-prediction results. Because the previousmethods did not optimize the best features, they did not give accurate results in heart attack detection, so thesystem is needed to control the death ratio.Therefore, the proposed work objects to implement a novel Mine BlastOptimization (MBO) based Multi-Layer Perceptron Neural Network (MLPNN) technique to predict the heartattack from the given datasets. The proposed detection framework includes the stages of preprocessing, featureoptimization, and classification. Here, the regression based preprocessing model is implemented to normalize theattributes for increasing the quality. Then, the MBO technique is also used to choose the relevant features based onthe best optimal solution. It also helps to reduce the increase the training of classifier with reduced timeconsumption and high detection accuracy. Finally, the MLPNN technique is utilized to predict the classified labelas whether normal or disease affected. During analysis, the results of the proposed MBO-MLPNN technique isvalidated and compared by using various measures. Here the proposed method achieved 98% accuracyperformance for heart attack detection than former methods.

Keywords

The article was added to IASJ on 2023-04-26

30 Total full text downloads since the date of addition