ABSTRACT

Despite of an increased global effort to end breast cancer, it continues to be most common cancer deaths in women. This problem reminds that new therapeutic approaches are desperately needed to improve patient survival rate. This requires proper diagnosis of disease and classification of tumor type based on genomic information according to which proper treatment can be provided to the patient. There exists a no. of classification techniques to classify the tumor types. In this paper we have focused on three different classification techniques: BPN, FLANN and PSO-FLANN and found that the integrated approach of Functional Link Artificial Neural Network (FLANN) and Particle Swarm Optimization (PSO) can better predict the disease as compared to other method.