ADAPTIVE CONVOLUTIONAL NEURAL NETWORK AND FEATURE SELECTION BASED HEART DISEASE PREDICTION
Mr. S.Sankar Assistant Professor & Dhirajlal Gandhi College of Technology
Mr.R.Keerthivasan Computer Science and Engineering & Dhirajlal Gandhi College of Technology
Mr.K.Narendraprasath Computer Science and Engineering & Dhirajlal Gandhi College of Technology
Mr.K.Navinsankar Computer Science and Engineering & Dhirajlal Gandhi College of Technology |
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Nowadays, heart diseases are currently a major cause of death in the world. It can be mitigated by early heart disease diagnosis. A heart disease predicted at earlier stages not only helps the patients prevent it, but it can also help the medical practitioners learn the major causes of a heart attack and avoid it before its actual occurrence in patient. There are many traditional methods of prediction for such illness but they are not looking sufficient. There is an urgent need of medical diagnosis system that can predict the heart diagnosis at an early stage and offers more accurate diagnosis than traditional methods. In this project, to address this problem to proposes an Adaptive Convolutional Neural Network (ACNN) method is used to design an early stage prediction and medical diagnosis system. We propose a heart disease prediction algorithm that combines the embedded pre-processing and feature selection process. Pre-processing is used to remove unwanted records and feature selection is used to choose a subset of features significantly associated with heart disease. These features are fed into the Adaptive Convolutional Neural Network (ACNN) we built. The proposed ACNN method is concerned with temporal data modeling by utilizing CNN for Heart Failure (HF) prediction at its earliest stage. Cardiovascular disease (CVD), despite major advances in diagnosis and treatment, and is still a major cause of morbidity and mortality around the world.