International Journal on Advanced Science, Engineering and Information Technology, Vol. 9 (2019) No. 2, List of accepted papers, DOI:10.18517/ijaseit.9.2.4986

Backpropagation Neural Network Based on Local Search Strategy and Enhanced Multi-objective Evolutionary Algorithm for Breast Cancer Diagnosis

Ashraf Osman Ibrahim, Siti Mariyam Shamsuddin, Abdulrazak Yahya Saleh, Ali ahmed, Mohd Arfian Ismail

Abstract

The role of intelligence techniques is becoming more significant in detecting and diagnosis of medical data. However, the performance of such methods is based on the algorithms or method. In this paper, we develop an intelligent method using multi-objective evolutionary algorithm hybrid with a local search strategy to enhance the Backpropagation neural network. First, we enhance the well-known multi-objective evolutionary algorithms, which is a non-dominated sorting genetic algorithm (NSGA-II). Then, we hybrid the enhanced algorithm with the local search strategy to accelerate the convergence speed towards the non-dominated front and ensures the solutions attained are well spread over it. Resulting from using a local search strategy, can enhance all individuals in the population and increase the quality of the Pareto optimal solutions. The proposed intelligent method has been experimentally evaluated by applying to the Breast cancer classification problem. The results 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.

Keywords:

Artificial neural networks, Local search, BackPropagation, Non-dominated Sorting Genetic Algorithm

Viewed: 41 times (since Sept 4, 2017)

cite this paper