A Novel Grid Ann for Prediction of Heart Disease

The prediction of Heart attack is one of the burning problems in the medical field. There are various attributes tresultults in the stress and health of the human being. Existing researchers concentrated on the attributes based on the tests related to heart attacks like restECG, echo and others but along with these metrics like weight, gender, working hours and others plays a vital role. The proposed model studies the importance of features by varying the layers of neural networks with different possibilities of activation functions because out of the different estimators available for the neural network, these functions are the one that transforms the behavior of the network rapidly with fewer resources utilization. The model has considered 9 activation functions and designed a 4-layered neural network and the hidden layers are customized with a grid search selection of activation functions. The main advantage of grid search optimization is it constructs a complete problem search space by considering every minute detail. The input and output layers are static with standard ReLu for input layer and sigmoid for the output layer because the dataset is a binary classification problem. The model compared the proposed model with static layers of network on the same 61 records has got training accuracy of 95.67% but the validation accuracy is 79% which is less when compared to the validation accuracy of the proposed is 81.9%.