Development of combined back propagation algorithm and radial basis function for diagnosing depression patients
-
2015-02-27 https://doi.org/10.14419/ijet.v4i1.4201
-
Hamilton Rating Scale (HRS) Depression Data, BPA, RBF. -
Abstract
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.
-
References
[1] S. Chattopadhyay, Neurofuzzy models to automate the grading of old-age depression, Expert Sys.: J. of Knowledge Engg., 31, 1, (2014), 48-55.
[2] S.Chattopadhyay, S.Banerjee, F.A.Rabhi, and R.U.Acharya, A Case-based Reasoning System for Complex Medical Diagnoses, Expert Systems: the Journal of Knowledge Engineering, 30, 1, (2013), 12-20.
[3] Subhrangsu Mukherjee, Kumar Ashish, Nirmal BaranHui, Subhagata Chattopadhyay, Modeling Depression Data: Feed Forward Neural Network vs. Radial Basis Function Neural Network, American Journal of Biomedical Sciences, American J. Biomed. Sci., 6, 3, (2014), 166-174; doi: 10.5099/aj140300166. http://dx.doi.org/10.5099/aj140300166.
[4] Jason D. Mielens, R.Matthew, R.Hoffman Michelle, M.Ciucci Timothy, McCulloch, Jack J. Jiang, Application of Classification Models to Pharyngeal High-Resolution Manometry, Journal of Speech, Language, and Hearing Research, 55, (2012), 892-902. http://dx.doi.org/10.1044/1092-4388(2011/11-0088).
[5] Antonio Ciampi, Fulin Zhang, A new approach to training back-propagation artificial neural networks: empirical evaluation on ten data sets from clinical studies, Statistics in Medicine, 21, 9, (2012), 1309–1330.
[6] Jyoti Joshi, AbhinavDhall, Roland Goecke., Michael Breakspear, and Gordon Parker, Neural-Net Classification For Spatio-Temporal Descriptor Based Depression Analysis, 21st International Conference on Pattern Recognition, (2012), Tsukuba International Congress center, Japan.
[7] Victor E. Ekong, Udoinyang G Inyang, Emmanuel A. Onibere, Intelligent Decision Support System for Depression Diagnosis Based on Neuro-fuzzy-CBR Hybrid, Modern Applied Science, Vol.6, No.7. (2012), 79-88.
[8] SubhagataChattopadhyay, Preetisha Kaur, FethiRabhi, Rajendra Acharya U., Neural Network Approaches to Grade Adult Depression, Journal of Medical Systems, 36, 5, (2012), 2803-2815.
[9] Anish Dasari, NirmalBaranHui, Subhagata Chattopadhyay, A Neuro-Fuzzy System for Modeling the Depression Data, International Journal of Computer Applications, 54, 6, (2012),doi:10.5120/8567-2276. http://dx.doi.org/10.5120/8567-2276.
[10] Danuta M. Lisiecka, Angella Carballedo, Andrew J. Fagan, Yolande Ferguson, James Meaney, Thomas Frodl, Recruitment of the left hemispheric emotional attention neural network in risk for and protection from depression, Journal of Psychiatry Neuroscience, 38, 2, (2013), 117-28.
-
Downloads
-
How to Cite
R., B., S., P., R., R., & R.G., B. (2015). Development of combined back propagation algorithm and radial basis function for diagnosing depression patients. International Journal of Engineering & Technology, 4(1), 244-249. https://doi.org/10.14419/ijet.v4i1.4201Received date: 2015-01-18
Accepted date: 2015-02-10
Published date: 2015-02-27