Wrapper feature selection methods aim to reduce the number of features from the original feature set to and improve the classification accuracy simultaneously. In this paper, a wrapper-feature selection algorithm based on the binary dragonfly algorithm is proposed. Dragonfly algorithm is a recent swarm intelligence algorithm that mimics the behavior of the dragonflies. Eighteen UCI datasets are used to evaluate the performance of the proposed approach. The results of the proposed method are compared with those of Particle Swarm Optimization (PSO), Genetic Algorithms (GAs) in terms of classification accuracy and number of selected attributes. The results show the ability of Binary Dragonfly Algorithm (BDA) in searching the feature space and selecting the most informative features for classification tasks.

This paper proposes a new meta-heuristic algorithm named tornado optimizer with Coriolis force (TOC) which is applied to solve global optimization and constrained engineering problems in continuous search spaces. The fundamental concepts and ideas beyond the proposed TOC Optimizer are inspired by nature based on the observation of the cycle process of tornadoes and how thunderstorms and windstorms evolve into tornadoes using Coriolis force. The Coriolis force is applied to windstorms that directly evolve to form tornadoes based on the developed optimization method. The proposed TOC algorithm mathematically models and implements the behavioral steps of tornado formation by windstorms and thunderstorms and then dissipation of tornadoes on the ground. These steps ultimately lead to feasible solutions when applied to solve optimization problems. These behavioral steps are mathematically represented along with the Coriolis force to allow for a proper balance between exploration and exploitation during the optimization process, as well as to allow search agents to explore and exploit every possible area of the search space. The performance of the proposed TOC optimizer was thoroughly examined on a simple benchmark set of 23 test functions, and a set of 29 well-known benchmark functions from the CEC-2017 test for a variety of dimensions. A comparative study of the computational and convergence analysis results was carried out to clarify the efficacy and stability levels of the proposed TOC optimizer compared to other well-known optimizers. The TOC optimizer outperformed other comparative algorithms using the mean ranks of Friedman’s test by 20.75%, 27.248%, and 25.85% on the 10-, 30-, and 50-dimensional CEC 2017 test set, respectively. The reliability and appropriateness of the TOC optimizer were examined by solving real-world problems including eight engineering design problems and one industrial process. The proposed optimizer divulged satisfactory performance over other competing optimizers regarding solution quality and global optimality as per statistical test methods.