Multi-strategy enhanced artificial rabbits optimization for prediction of grades in tourism service communication courses.

Abstract

Predicting students' grades through their classroom behavior has been a longstanding concern in education. Recently, artificial intelligence has demonstrated remarkable potential in this area. In this study, the Artificial Rabbits Optimization Algorithm is selected to enhance the predictor's capabilities. This algorithm, a recently proposed and popular metaheuristic method, is known for its simple and straightforward structure. However, like other metaheuristic algorithms, it often falls into local optima, and as iterations increase, the convergence speed slows down, leading to reduced convergence accuracy. To address this issue, a Multi-Strategy Enhanced Artificial Rabbits Optimization Algorithm (MEARO) is introduced. MEARO first employs a Nonlinear Exploration and Exploitation Transition Factor (NL) to improve the balance between exploration and exploitation. Additionally, a Stochastic Centroid Backward Learning approach (SOBL) is applied to enhance both the quality and diversity of the population, ensuring a broader optimization of the search area and increasing the chances of locating the global optimum. Finally, a Dynamic Changing Step Length Development strategy is incorporated to enhance the randomness and development capability. The efficiency of MEARO is confirmed by comparing its performance with eight other sophisticated algorithms using the CEC2017 benchmark. The number of wins/Ties/losses in the three dimensions of cec2017 are (223/0/17), (221/0/19) and (230/0/10) respectively. Results indicate that MEARO outperforms these algorithms. Furthermore, MEARO is used to optimize two critical parameters of the Kernel Extreme Learning Machine (KELM), significantly improving its classification performance. Experimental results on the collected student performance dataset demonstrate that the KELM model optimized by MEARO surpasses other benchmark models across various metrics. Additionally, factors such as interest in the course, frequency of classroom discussion, and access to supplementary knowledge and information related to the course are identified as significant contributors to performance.