Feature selection using improved lion optimisation algorithm for breast cancer classification

Abstract

Feature selection plays an important role in breast cancer classification. Feature selection identifies the most informative feature subset from feature set that can accurately classify the given data. The texture features, intensity histogram features, shape features and radial distance features have been extracted from mammogram image and the optimal feature set has been obtained using improved lion optimisation algorithm (ILOA). The overall accuracy of a classifier is used as a fitness value for ILOA. In the proposed work minimum distance classifier, K-nearest neighbour classifier and support vector machine have been used. The proposed ILOA technique can efficiently find small feature subsets and able to classify the breast cancer data set with a very excellent accuracy. The performance of the ILOA is compared with the cuckoo search and harmony search. Experimental result shows that the result obtained from minimum distance classifier through ILOA is more accurate than the other algorithm. These algorithms can provide valuable information to the physician in medical pathology.