An Evolutionary Artificial Neural Network for Medical Pattern Classification

Authors:
Shing Chiang Tan;Chee Peng Lim;Kay Sin Tan;Jose C. Navarro
Affiliations:
Faculty of Information Science & Technology, Multimedia University, Melaka, Malaysia 75450;School of Electrical & Electronic Engineering, University of Science Malaysia, Nibong Tebal, Malaysia 14300;Department of Medicine, Faculty of Medicine, University of Malaya, Kuala Lumpur, Malaysia 50603;University of Santo Tomas Hospital, Manila, Philippines
Venue:
ICONIP '09 Proceedings of the 16th International Conference on Neural Information Processing: Part II
Year:
2009

Citing 6
Cited 0

A massively parallel architecture for a self-organizing neural pattern recognition machine

Computer Vision, Graphics, and Image Processing
Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system

Neural Networks
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
A multilayer perceptron-based medical decision support system for heart disease diagnosis

Expert Systems with Applications: An International Journal
Hybridization of evolutionary algorithms and local search by means of a clustering method

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
An evolutionary artificial neural networks approach for breast cancer diagnosis

Artificial Intelligence in Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a novel evolutionary artificial neural network based on the integration between Fuzzy ARTMAP (FAM) and a Hybrid Genetic Algorithm (HGA) is proposed for tackling medical pattern classification tasks. To assess the effectiveness of the proposed FAM-HGA model, the Ripley artificial data set is first used, and the results are compared with those of FAM-GA and FAM. A real medical data set comprising anonymous stroke patient records is then employed for further experimentation. The performance of FAM-HGA is assessed using three indicators; accuracy, sensitivity and specificity, and the results are compared with those of FAM-GA and FAM. Overall, FAM-HGA yields better classification performances than FAM-GA and FAM. The study reveals the potential of FAM-HGA as a computerized decision support tool for medical pattern classification tasks.