Neural Network Classifier with Entropy Based Feature Selection on Breast Cancer Diagnosis

• Published in: Journal of medical systems Vol. 34; no. 5; pp. 865 - 873
• Main Authors: Huang, Mei-Ling, Hung, Yung-Hsiang, Chen, Wei-Yu
• Format: Journal Article
• Language: English
• Published: Boston Springer US 01.10.2010; Springer Nature B.V
• Subjects: Accuracy; Algorithms; Artificial Intelligence; Breast cancer; Breast Neoplasms - pathology; Classification; Data Mining; Diagnosis, Computer-Assisted - instrumentation; Female; Health Informatics; Health Sciences; Humans; Medical diagnosis; Medicine; Medicine & Public Health; Neural networks; Neural Networks (Computer); Optimization algorithms; Original Paper; Statistics for Life Sciences; Levenberg–Marquardt (LM); Feature selection; Back-propagation neural network (BPNN); Classification accuracy; Particle Swarm Optimization (PSO)
• ISSN: 0148-5598; 1573-689X
• DOI: 10.1007/s10916-009-9301-x

The aim of this research is to combine the feature selection (FS) and optimization algorithms as the optimal tool to improve the learning performance like predictive accuracy of the Wisconsin Breast Cancer Dataset classification. An ensemble of the reduced data patterns based on FS was used to train a neural network (NN) using the Levenberg–Marquardt (LM) and the Particle Swarm Optimization (PSO) algorithms to devise the appropriate NN training weighting parameters, and then construct an effective Neural Network classifier to improve the Wisconsin Breast Cancers’ classification accuracy and efficiency. Experimental results show that the accuracy and AROC improved emphatically, and the best performance in accuracy and AROC are 98.83% and 0.9971, respectively.