Intelligent Breast Cancer Diagnosis Based on Enhanced Pareto Optimal and Multilayer Perceptron Neural Network
by Ashraf Osman Ibrahim; Siti Mariyam Shamsuddin
International Journal of Computer Aided Engineering and Technology (IJCAET), Vol. 10, No. 5, 2018

Abstract: Among the common cancer diseases is a breast cancer. Diagnosis of this disease depends on the human experience. It is time consuming and having an element of human error in the results. The Pareto optimal evolutionary multi-objective optimisation is used to obtain multiple final results in a single run for simultaneous parameter optimisation of artificial neural networks (ANNs). In this paper, a computer-based method of an automatic classifier for the breast cancer disease diagnosis task is proposed. The proposed method applied a multilayer perceptron (MLP) neural network based on enhanced non-dominated sorting genetic algorithm (NSGA-II) to achieve an accurate classification result for the breast cancer diseases diagnosed. Moreover, it is also used to optimise the network structure and reduce the error rate of the MLP neural network simultaneously. Compared to other methods found in the literature, the proposed method is viable in breast cancer disease diagnosis.

Online publication date: Thu, 30-Aug-2018

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computer Aided Engineering and Technology (IJCAET):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email