Feature selection is a critical and prominent task in machine learning. To reduce the dimension of the feature set while maintaining the accuracy of the performance is the main aim of the feature selection problem. Various methods have been developed to classify the datasets. However, metaheuristic algorithms have achieved great attention in solving numerous optimization problem. Therefore, this paper presents an extensive literature review on solving feature selection problem using metaheuristic algorithms which are developed in the ten years (2009-2019). Further, metaheuristic algorithms have been classified into four categories based on their behaviour. Moreover, a categorical list of more than a hundred metaheuristic algorithms is presented. To solve the feature selection problem, only binary variants of metaheuristic algorithms have been reviewed and corresponding to their categories, a detailed description of them explained. The metaheuristic algorithms in solving feature selection problem are given with their binary classification, name of the classifier used, datasets and the evaluation metrics. After reviewing the papers, challenges and issues are also identified in obtaining the best feature subset using different metaheuristic algorithms. Finally, some research gaps are also highlighted for the researchers who want to pursue their research in developing or modifying metaheuristic algorithms for classification. For an application, a case study is presented in which datasets are adopted from the UCI repository and numerous metaheuristic algorithms are employed to obtain the optimal feature subset.

To improve the optimization performance of LSHADE algorithm, an alternative adaptation approach for the selection of control parameters is proposed. The proposed algorithm, named LSHADE-SPA, uses a new semi-parameter adaptation approach to effectively adapt the values of the scaling factor of the Differential evolution algorithm. The proposed approach consists of two different settings for two control parameters F and Cr. The benefit of this approach is to prove that the semi-adaptive algorithm is better than pure random algorithm or fully adaptive or self-adaptive algorithm. To enhance the performance of our algorithm, we also introduced a hybridization framework named LSHADE-SPACMA between LSHADE-SPA and a modified version of CMA-ES. The modified version of CMA-ES undergoes the crossover operation to improve the exploration capability of the proposed framework. In LSHADE-SPACMA both algorithms will work simultaneously on the same population, but more populations will be assigned gradually to the better performance algorithm. In order to verify and analyze the performance of both LSHADE-SPA and LSHADE-SPACMA, Numerical experiments on a set of 30 test problems from the CEC2017 benchmark for 10, 30, 50 and 100 dimensions, including a comparison with LSHADE algorithm are executed. Experimental results indicate that in terms of robustness, stability, and quality of the solution obtained, of both LSHADE-SPA and LSHADE-SPACMA are better than LSHADE algorithm, especially as the dimension increases.