Prediction of Liver Disease using Rprop, SAG and CNN
Deepa H Belavigi1, Veena G S2, Divakar Harekal3
1Deepa H Belavigi, student in Computer Science Department of Ramaiah Institute of Technology.
2Veena G.S, working as an Assistant Professor in Computer Science Department of Ramaiah Institute of Technology.
3Divakar Harekal is working as an Assistant Professor in Computer Science Department of Ramaiah Institute of Technology.
Manuscript received on 02 June 2019 | Revised Manuscript received on 10 June 2019 | Manuscript published on 30 June 2019 | PP: 3290-3295 | Volume-8 Issue-8, June 2019 | Retrieval Number: H6889068819/19©BEIESP
Open Access | Ethics and 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: Early prognosis of liver disease is very important to save human life and take legitimate precautions to control the disease. The computer cooperated diagnosis of liver disease plays and significant job in convenient detection and medication of liver. Quick and precise prophecy of liver disorder permits early and viable treatments. Experience cleared that numerous patients anguishing from liver disease die day by day because of misdiagnosis of the sicknesses. The work delve into the early prediction of liver disease using deep learning techniques. Artificial neural network model such as Resilient Back propagation Neural Network (Rprop), Stochastic Average Gradient (SAG) model and Convolutional Neural Network (CNN) models are utilized to take care of the issues that are been faced by doctors in diagnosis of liver maladies. The text and image datasets of liver are taken as inputs for the three algorithms. The results of the models are compared, and the accuracy is obtained. Comparison emphasis on the type of aspects and models, that one has to rely on for early prediction of defect and medication of the liver. Results using image dataset are more factual than the text datasets.
Keyword: Liver Disorder, Deep learning algorithms, Rprop, SAG, CNN, K-fold validation.
Scope of the Article: Healthcare Informatics.