Abstract: Artificial Neural Networks are ideally suited for forecasting or prediction since they excel at spotting patterns or trends in data. Neural networks are therefore widely used in biological systems.An emphasis is placed on the use of neural networks in kidney stone diagnostics. Neural networks are used to diagnose kidney stone problems using technical ideas like as MLP, SVM, RBF, and BPA. In this paper is to identify kidney stone disease through the application of three distinct neural network algorithms, each with unique design and properties. This paper compares the three neural networks' performance in terms of accuracy, model construction time, and training data set size. Radial basis function (RBF) networks, two layers feed forward perceptron’s trained with the back propagation training algorithm, and learning vector quantization (LVQ) will be used to diagnose kidney stone illness. But figuring out the optimum method for any given diagnostic had always been a difficult undertaking. Neural network approaches have already been used in the diagnosis of kidney stones, much like in many other disorders.
This paper work's primary goal is to suggest the finest medical diagnostic tool—such as kidney stone identification—in order to speed up diagnosis times and increase precision and efficiency.
Keywords: kidney stone, artificial neural network, Radial basis function.
Title: Compare the Performance of Distinct Neural Networks Techniques to diagnose the kidney stone disease
Author: NEETU MOURYA, Dr. NAVEEN TYAGI
International Journal of Interdisciplinary Research and Innovations
ISSN 2348-1218 (print), ISSN 2348-1226 (online)
Vol. 11, Issue 4, October 2023 - December 2023
Page No: 23-28
Research Publish Journals
Website: www.researchpublish.com
Published Date: 27-October-2023
