A Bald Eagle Search Optimization Based Weighted Rank Aggregation Method for Microarray Data Classification

Wei Li, Tengfei Shi, Linjie Wang, Weidong Xie

Abstract: The rapid development of microarray technology has generated a large amount of microarray data, and the classification of these data is meaningful for cancer diagnosis, treatment and prognosis. The classification of high-dimensional microarray data with small samples is a challenging problem, which usually requires feature selection methods to reduce the data dimensionality first. However, different feature selection methods usually generate different feature lists for the same data. Researchers need to choose among many feature selection methods, which reduces the research efficiency. Therefore, rank aggregation method is used to generate a optimal list by aggregating all ordered feature lists generated by different feature selection methods. It can combine the advantages of multiple feature selection methods and does not prefer a particular method, so it is more robust to outliers, noises and errors. In this paper, we propose a weighted rank aggregation method based on the Bald Eagle Search optimization. A positional weight is designed to emphasize the importance of the top features in the list, so that the distance between lists can be measured more accurately. In addition, we improve the Bald Eagle Search algorithm for optimizing rank aggregation method to obtain a optimal ordered list. The experimental results on six public microarray datasets indicate that the features selected by our method can significantly improve the classification performance.