Multiobjective sparrow search feature selection with sparrow ranking and preference information and its applications for high-dimensional data

To reduce the dimensionality of high-dimensional data and enhance its classification accuracy, feature selection can be regarded as a multiobjective optimization problem that can be addressed by evolutionary computation algorithms with promising results. However, balancing the convergence and diversity of nondominated solutions remains challenging. To address these issues, this paper proposes a multiobjective sparrow search feature selection approach with sparrow ranking and preference information and its applications for high-dimensional data. First, during the population updating process, the updating formula of observers is combined with the mutualism phase of the symbiotic organisms search algorithm to design a location updating formula of observers in the sparrow search algorithm, balancing the local development ability and global search ability of sparrow search algorithm and increasing the possibility of moving closer to the optimal solution. Second, based on the dominant and nondominated sparrow individuals of each sparrow, the dominant and nondominated distances are defined, and the sparrow ranking is proposed. The feature ranking is then designed by using the definition of sparrow ranking. Following the definition of sparrow ranking and feature ranking, the selection strategy and location updating formula of the producers in the sparrow search algorithm are proposed. Finally, a preference information-based mutation algorithm is designed to augment the diversity of the nondominated solutions and more effectively guide the whole sparrow population to a better solution. The experimental results on 14 high-dimensional datasets show that the proposed algorithm outperforms different single-objective and multiobjective optimization feature selection algorithms in terms of classification efficiency and diversity of solutions.