Personalized Exercise Group Assembly Using a Two Archive Evolutionary Algorithm

Abstract

Traditional exercise recommendation algorithms generate exercise groups according to the features of exercises for all students. However, as different students may have different knowledge proficiencies, this article focuses on the personalized exercises group assembly (PEGA) to select exercises for each student based on their knowledge proficiencies, which is formulated as a constrained multi-objective problem. In order to solve the constrained multi-objective PEGA problem efficiently, this paper proposes a two archives evolutionary algorithm (TAEA) with three novel designs. Firstly, as the number of exercises is very large in PEGA, the traditional binary-number encoding method will result in high consumption in both memory and computation. To this end, a new integer-number encoding (INE) method is designed for solution representation. It saves memory for exercise subset representation, speeds up evaluations, and generates solutions that satisfy some constraints. Secondly, based on the INE method, the TAEA adopts two archives name convergence-oriented archive (CA) and diversity-oriented archive (DA). The CA ensures the convergence, driving force, and feasibility of the solutions. The DA aims to provide as diverse a solution as possible, including exploration of infeasible regions. Thirdly, a classification-based offspring co-reproduction strategy is proposed to solve the issue of too much infeasible space exploration. Experimental results show that our INE method can help to reduce the running time and improve the optimization results. The effectiveness of the TAEA is demonstrated by comparing it with some recent existing algorithms.