Using Intelligent Techniques for Breast Cancer Classification

Attribute reduction is an important issue in rough set theory. It is necessary to investigate fast and effective approximate algorithms to generate a set of discriminatory features. The main objective of this paper is investigating a strategy based on Rough Set Theory (RST) with Particle Swarm Optimization (PSO) to be used. Rough Set Theory has been recognized to be one of the powerful tools in the medical feature selection .The supplementary part which will be used is Particle Swarm Optimization (PSO) that is defined as a subfield of swarm intelligence that studies the emergent collective intelligence of groups of simple agents and based on social behavior that can be observed in nature, such as flocks of birds and fish schools where a number of individuals with limited capabilities are able to achieve intelligent solutions for complex problems. Particle Swarm Optimization is widely used and rapidly developed for its easy implementation and few particles required to be tuned. This hybrid approach embodies an adaptive feature selection procedure which dynamically accounts for the relevance and dependence of the features .The relevance selected feature subsets are used to generate decision rules for the breast cancer classification task to differentiate the benign cases from the malignant cases by assigning classes to objects. The proposed hybrid approach can help in improving classification accuracy and also in finding more robust features to improve classifier performance.