Accurate and Fast Diagnosis of Heart Disease using Hybrid Differential Neural Network Algorithm
O. Bhaskaru1, M.Sree Devi2
1O. Bhaskaru, Research Scholar, Department of CSE, Koneru Lakshmaiah Education Foundation, Green Fields, Guntur Vaddeswaram (Andhra Pradesh), India.
2Dr. M. Sree Devi, Professor, Department of CSE, Koneru Lakshmaiah Education Foundation, Green Fields, Guntur Vaddeswaram (Andhra Pradesh), India.
Manuscript received on 25 May 2019 | Revised Manuscript received on 03 June 2019 | Manuscript Published on 22 June 2019 | PP: 452-457 | Volume-8 Issue-3S, February 2019 | Retrieval Number: C10950283S19/19©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: Heart disease is the most threatened issues which is more dangerous than the other kind of diseases. The most of the people in world is causes by heart disease which increases the death rate of humans considerably. The detection of heart disease is the more trivial task of medical researchers which cannot be done more accurately. And also manual prediction of heart disease is most complex task, thus it is required to implement the automated system by considering the recent computer technologies which can help medical researchers to diagnosis heart disease fastly and accurately. This is done in this research method by introducing the new method namely Hybrid Differential Evolution based Fuzzy Neural Network (HDEFNN) for heart disease diagnosis. In this method DE is hybridized with the FNN algorithm to ensure the better performance of heart disease diagnosis. The proposed method guarantees the accurate and reliable identification of heart disease with the help of neural network based learning. Here the performance of neural network is enhanced by introducing the genetic algorithm which will update the initial weight values hidden layers, thus the learning prediction accuracy can be improvised. Here the genetic algorithm ensures the 10% performance improvement of neural network. The simulation evaluation of the proposed method HDEFNN is carried out on dataset namely Cleveland heart disease dataset which is collected from the University of California at Irvine (UCI) machine learning repository. The performance evaluation of the proposed method is done in the matlab simulation environment under kfold cross validation procedure which proves that the proposed method shows better performance in terms of accurate disease diagnosis within less execution time.
Keywords: Heart Disease, Differential Evolution, Fuzzy Neural Network, Genetic Algorithm, Accuracy.
Scope of the Article: Algorithm Engineering