Multi-Swarm Optimization for Extracting Multiple-Choice Tests From Question Banks

In this study, a novel method for generating multiple-choice tests is presented, which extracts the required number of same levels difficulty in single attempt and approximates level requirement given by users. We propose an approach using parallelism Pareto optimization multi-swarm migration particle swarm (PSO) algorithm. Multi-PSO proposed shortening computing time. The PSOs increases diversity controls overlap extracted tests. experimental results show that can generate many from question banks satisfying predefined difficulty. Additionally, developed shown to be effective terms criteria when compared with other methods such as manually tests, simulated annealing algorithm (SA), random PSO-based approaches successful solutions, accuracy, standard deviation, search speed, questions overlapping between exam questions, well changing space, individuals, swarms, requirements.