Local Search Based Enhanced Multi-objective Genetic Algorithm of Training Backpropagation Neural Network for Breast Cancer Diagnosis

Ashraf Osman, Ibrahim and Siti Mariyam, Shamsuddin and Abdulrazak Yahya, Saleh (2017) Local Search Based Enhanced Multi-objective Genetic Algorithm of Training Backpropagation Neural Network for Breast Cancer Diagnosis. In: Recent Trends in Information and Communication Technology. IRICT 2017. Lecture Notes on Data Engineering and Communications Technologies, 5 . Springer International Publishing, pp. 587-594. ISBN 9783-319594279

PDF Local Search Based Enhanced Multi-objective Genetic Algorithm of Training Backpropagation Neural Network for Breast Cancer Diagnosis (full) - Copy (abstrak).pdf Download (99MB)

Abstract

Recently, several evolutionary algorithms have been proposed on the basis of preference in literature. Most of multi-objective evolutionary algorithms used NSGA-II due to a good performance in comparison with other multi-objective evolutionary algorithms. Our research is focused on enhancement of a well-known evolutionary algorithm NSGA-II by combining a local search method for solving Breast cancer classification problem based on Backpropagation neural network. The use of local search within the enhanced NSGA II operating can accelerate the convergence speed towards the non-dominated front and ensures the solutions attained are well spread over it. The proposed hybrid method has been experimentally evaluated by applying to the Breast cancer classification problem. It has been experimentally shown that the combination of the local search method has a positive impact to the final solution and thus increased the classification accuracy of the results.

Actions (For repository members only: login required)

View Item