A hybrid feature selection approach based on ensemble method for high-dimensional data

Nowadays, with the emergence of high-dimensional data, feature selection plays an important role in the domain of machine learning, particularly, classification problems, such that feature selection can be known as its vital and irremovable component. With the increase in the number of data dimensions, simple traditional methods show poor performance and cannot be used for effective and proper feature selection. Using embedded methods, this study first discusses data dimension reduction using a filter based approach. Two state-of-the-art meta-heuristic methods are then applied on the selected features and final desirable features are selected from the aggregation of their selected features. The proposed method is evaluated on 5 high-dimensional micro-array datasets and results are compared with several state-of-the-art feature selection approaches for high-dimensional data. Experimental results confirm the efficiency of the proposed method.