Proceeding of

NCAICN National Conference 2013

(NCAICN-2013)

on

Advances in

Computing & Networking

as

A Special Issue of

International Journal of Computer Science and Applications

(ISSN:0974-1011)

Patron

Hon. Shri Sundeepji Meghe

(Chairman, Vidarbha Youth Welfare Society, Amravati)

 

Advisor

Dr. V.T. Ingole (FIE, FIETE, Professor Emeritus)

 

Organizing Committee

Chairman

Dr. D.T. Ingole (FIE, FIETE)

(Principal PRMIT & R, Badnera and  Chairman IEI  Amravati Center).

Secretary

 Er. A.W. Jawanjal

(Honorary Secretary IEI, Amravati Center)

Conveners

Dr. G.R. Bamnote ((FIE, FIETE)

(H.O.D. Computer Science & Engineering)

Dr. A.S. Alvi (MIE)

(H.O.D. Information Technology))

Prof. Mrs. M.D. Ingole (FIE.MIETE)

(H.O.D. Electronics & Telecommunication)

Coordinators

Prof. S.V. Dhopte ((FIE, FIETE)

Prof. Ms. V.M. Deshmukh (FIE, FIETE)

Dr. S.W. Mohod  (FIE,FIETE)

Co-Coordinators

Dr. S.R. Gupta (MIE, MIETE)

Prof. S.V. Pattalwar ((FIE, FIETE)

Prof. M.D. Damahe

Members

Prof. Mrs. M.S. Joshi                

Dr. S.M. Deshmukh

Prof. V.U. Kale

Prof. S.S. Kulkarni

Prof. Ms. R.R. Tuteja

Prof. Ms. J.N. Ingole

Prof. V.R. Raut

Prof. C.N. Deshmukh

Prof. Ms. M.S. Deshmukh

Prof. S.P. Akarte

Prof. Mrs. A.P. Deshmukh

Prof. Mrs. S.S. Sikchi

Prof. N.N. Khalsa

Department of Information and Computer Science and Engineering

Prof. Ram Meghe Institute of Technology and Research, Badnera Distt. Amravati

 

Editor

Prof. K. H. Walse

M.S.India
 

 

 

   
   
   
   
 
  
 
  
 
  
 
  
 
  
 
  
 
  
 
  
 
  
 
  
 
  
 
  
 
  
 
  
  
IJCSA ISSN: 0974-1011 (Online) >>    
Title:

Comparison of performance of ANN to classify the type of Erythemato-Squamous Disease

Author:
 Dr. Mrs. S. N. Kale and Dr. S.V. Dudul
 
Abstract

Neural network architectures are configured to perform optimally based on the various dataset. In this paper, various NN architectures are built with different parameters. Here the dataset used is the benchmark dataset of erythemato-squamous diseases. The differential diagnosis of erythemato-squamous diseases is a difficult problem in dermatology. Artificial Neural Network (ANN) classifies the given samples when trained and nearly 98% classification accuracy is achieved. Generalized Feed Forward Neural Network (FFNN) can solve the multivariable classification problem of determination of skin disease. The performance of MLPNN, RBFNN, Modular NN, SOFM and Recurrent ANN are also studied to determine the type of Erythemato-Squamous Disease, which all share the clinical features of erythema and scaling, with very little differences. The diseases are classified into six classes, namely psoriasis, seboreic dermatitis, lichen planus, pityriasis rosea, chronic dermatitis, and pityriasis rubra pilaris.

©2013 International Journal of Computer Science and Applications 

Published by Research Publications, India