scholarly journals Generalized Regression Neural Network and Radial Basis Function for Heart Disease Diagnosis

2010 ◽  
Vol 7 (13) ◽  
pp. 7-13 ◽  
Author(s):  
Shaikh Abdul Hannan ◽  
R. R. Manza ◽  
R. J. Ramteke
Keyword(s):  
Neural Network ◽  
Heart Disease ◽  
Radial Basis Function ◽  
Basis Function ◽  
Disease Diagnosis ◽  
Generalized Regression Neural Network ◽  
Radial Basis ◽  
Generalized Regression ◽  
Heart Disease Diagnosis

Modeling of heavy ion collisions using radial basis function and generalized regression neural networks

2011 ◽  
Vol 89 (10) ◽  
pp. 1051-1060
Author(s):  
El-Sayed A. El-Dahshan
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Radial Basis Function ◽  
Basis Function ◽  
Heavy Ion Collisions ◽  
Heavy Ion ◽  
Generalized Regression Neural Network ◽  
Ion Collisions ◽  
Radial Basis ◽  
Generalized Regression

Artificial neural networks (ANNs) have been applied to heavy ion collisions. In the present work, the possibility of using ANN methods for modeling the multiplicity distributions, P(ns), of shower particles produced from p, d, 4He, 6Li, 7Li, 12C, 16O, and 24Mg interactions with light (CNO) as well as heavy (AgBr) emulsions at 4.5 A GeV/c was investigated. Two different ANN approaches, namely radial basis function neural network (RBFNN) and generalized regression neural network (GRNN), were employed to obtain a mathematical formula describing these collisions. The results from RBFNN and GRNN models showed good agreement with the experimental data. GRNN models have a better performance than the RBFNN models. This study showed that the RBFNN and GRNN models are capable of accurately predicting the P(ns) of shower particles in the training and testing phases.

Sign in / Sign up

Export Citation Format

Share Document