Feature Selection using Binary Moth Flame Optimization with Time Varying Flames Strategies

In this paper, a new feature selection (FS) approach is proposed based on the Moth Flame Optimization (MFO) algorithm with time-varying flames number strategies. FS is a data preprocessing technique that is applied to minimize the number of features in a data set to enhance the performance of the learning algorithm (e.g classifier) and reduce the learning time. Finding the best feature subset is a challenging search process that requires exponential running time if the complete search space is generated. Meta-heuristics algorithms are promising alternative solutions that have proven their performance in finding approximated optimal solutions within a reasonable time. The MFO algorithm is a recently developed Swarm Intelligence (SI) algorithm that has demonstrated effective performance in solving various optimization problems. This is due to its spiral update strategy that enhances the convergence trends of the algorithm. The number of flames is an important parameter in the MFO algorithm that controls the balance between the exploration and exploitation phases during the optimization process. In the standard MFO, the number of flames linearly decreases throughout the iterations. This paper proposes different time-varying strategies to update the number of flames and analyzes their impact on the performance of MFO when used to solve the FS problem. Seventeen medical benchmark data sets were used to evaluate the performance of the proposed approach. The proposed approach is compared with other well-regarded meta-heuristics and the results show promising performance in tackling the FS problem.