An Efficient System for the Prediction of Coronary Artery Disease using Dense Neural Network with Hyper Parameter Tuning
Debabrata Swain1, Santosh Kumar Pani2, Debabala Swai3
1Debabrata Swain, PHD Scholar, School of Computer Engineering, Kalinga Institute of Industrial Technology Information Centre, University Bhubaneshwar.
2Santosh Kumar Pani, Associate Professor, School of Computer Engineering, Kalinga Institute of Industrial Technology Information Centre, University Bhubaneshwar.
3Debabala Swain, Associate Professor, Department of Computer Science, Ramadevi Women’s University, Bhubaneshwar
Manuscript received on 08 April 2019 | Revised Manuscript received on 15 April 2019 | Manuscript Published on 26 April 2019 | PP: 689-695 | Volume-8 Issue-6S April 2019 | Retrieval Number: F61520486S19/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Diagnosis of heart disease is considered as one of the challenging problems in medical science in the current decade. Coronary artery disease is a type of heart disease in which the arteries of the heart gets affected. Hence many researchers propose a number of intelligent solutions to improve the predictability towards the identification of Coronary artery disease. If the disease can be identified at an early stage, then precautions can be taken for its recovery. In the proposed system, an efficient deep learning technique is used for improving accuracy towards the identification of the disease. The proposed system is built using a Dense Neural Network which is a type of deep learning network. Here the experimentation is done using Cleveland Heart disease data set present in the UCI repository. The system has three stages. In the first stage data cleaning and feature selection is performed. In the second stage model training is done using hyper parameter tuning. In the last stage, the trained model is used for prediction of coronary artery disease using test data set. The proposed model results in the classification accuracy of 96.03% during training and an accuracy of 94.91% during testing, which is best among all the discussed methods.
Keywords: KNN Method, Random Forest, Fuzzy Logic, SVM, PCA, ANFIS.
Scope of the Article: Fuzzy Logic