Open AccessDevelopment of combined back propagation algorithm and radial basis function for diagnosing depression patients
Author(s) -
Bhuvana Ramabhadran,
S. Purushothaman,
R. Rajeswari,
Rakesh Balaji
Publication year - 2015
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v4i1.4201
Subject(s) - artificial neural network , radial basis function , depression (economics) , algorithm , function (biology) , computer science , backpropagation , mean squared error , variable (mathematics) , artificial intelligence , radial basis function network , test data , machine learning , mathematics , statistics , mathematical analysis , evolutionary biology , biology , economics , macroeconomics , programming language
Depression is a severe and well-known public health challenge. Depression is one of the most common psychological problems affecting nearly everyone either personally or through a family member. This paper proposes neural network algorithm for faster learning of depression data and classifying the depression. Implementation of neural networks methods for depression data mining using Back Propagation Algorithm (BPA) and Radial Basis Function (RBF) are presented. Experimental data were collected with 21 depression variables used as inputs for artificial neural network (ANN) and one desired category of depression as the output variable for training and testing proposed BPA/RBF algorithms. Using the data collected, the training patterns, and test patterns are obtained. The input patterns are pre-processed and presented to the input layer of BPA/RBF. The optimum number of nodes required in the hidden layer of BPA/RBF is obtained, based on the change in the mean squared error dynamically, during the successive sets of iterations. The output of BPA is given as input to RBF. Through the combined topology, the work proves to be an efficient system for diagnosis of depression.