Diagnosis of psychosomatic disorders using radial basis functions network

Authors:
P. Aruna;N. Puviarasan;B. Palaniappan;R. Shanmugam
Affiliations:
Faculty of Engineering and Technology, Dept. of Computer Science & Engineering, Annamalai University, Chidambaram, Tamil Nadu, India;Faculty of Engineering and Technology, Dept. of Computer Science & Engineering, Annamalai University, Chidambaram, Tamil Nadu, India;Faculty of Engineering and Technology, Dept. of Computer Science & Engineering, Annamalai University, Chidambaram, Tamil Nadu, India;Faculty of Engineering and Technology, Dept. of Computer Science & Engineering, Annamalai University, Chidambaram, Tamil Nadu, India
Venue:
EHAC'05 Proceedings of the 4th WSEAS International Conference on Electronics, Hardware, Wireless and Optical Communications
Year:
2005

Citing 6
Cited 0

Fuzzy set theory in medical diagnosis

IEEE Transactions on Systems, Man and Cybernetics
Using neural networks to aid the diagnosis of breast implant rupture

Computers and Operations Research
Knowledge-based approach to septic shock patient data using a neural network with trapezoidal activation functions

Artificial Intelligence in Medicine
A combined neural network and decision trees model for prognosis of breast cancer relapse

Artificial Intelligence in Medicine
Fuzzy neural network in case-based diagnostic system

IEEE Transactions on Fuzzy Systems
On the construction and training of reformulated radial basis function neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a model specific for medical diagnosis developed with Neurofuzzy techniques based on Radial Basis Functions (RBF) network. The model provides a user-friendly interface, to the experts in the medical domain with the possibility to design diagnostic applications without deep background knowledge on Neuro networks and fuzzy logic. Given a set of symptoms and test results, assess pathological situations identifying which diseases justify the particular findings. Systematic approach for constructing RBF neural networks, which was developed to facilitate their training by supervised learning algorithms based on K-means clustering algorithm. The key point in design of RBF networks is to specify the number and the locations of the centers. Several learning methods, which apply a clustering algorithm for locating the centers and subsequently a least means squares algorithm for the linear weights. The combinatorial neuro- fuzzy model based on RBF for the diagnosis of psychosomatic disorder can achieve the performance similar to that of the human expert.