文章基本信息

标题：Employing Gradient Based Techniques of Neural Network for Predicting Heart Disease
本地全文：下载
作者：Parveen Sehgal ; Manisha Sharma
期刊名称：International Journal of Research in Management, Science & Technology
印刷版ISSN：2321-3264
出版年度：2016
卷号：4
期号：2
出版社：Prannath Parnami Institute of Management & Technology, Hisar
摘要：In recent years, artificial neural networks and other intelligent techniques have been proved as a powerful tool for predictive data mining and worked well as a classifier in field of medical diagnosis for an early detection of the problem. In this paper, we focus on the development of gradient based techniques of neural networks for predicting heart disease. ANN based models for prediction of heart disease have been developed using neural network toolbox available in MATLAB. Multilayer perceptron architecture of neural networks with error back propagation along with important gradient based methods has been employed to develop the disease prediction models. Algorithms have been compared for their performance. A comparative study employing various important training methods has also been provided. Our objectives are to provide a framework, which is expected to be more effective and acceptable for predicting the heart disease and its diagnosis
关键词：Artificial neural networks; back propagation algorithm; hard disease prediction; gradient descent; conjugate gradient descent; gradient based techniques.