An automation of the course design based on mathematical modeling and genetic algorithms

Abstract

This work in progress describes a technique of course design in the form of learning objects (LO) sequences. We defined the distance between LOs (metric of learning objects space based on revised Blooms Taxonomy) and used it to design an objective function. This function is a sum of distances between LOs in the given sequence learning prerequisites of a course and its learning outcomes. In addition, the function contains penalties for the violations of the learning sequence, when, for example, one or more learning prerequisites for the given LO are absent in learning outcomes of previous LOs and course's prerequisites. A genetic algorithm was used to find LOs sequences complied with the given requirements of the course. To provide the series of experiments, this algorithm was realized as a computer-aided application in the development environment Microsoft Visual Studio 12. These series showed that the suggested technique is suitable for automated course design based on big amount LOs. Several suggestions to develop the technique are given at the end of this paper.

Sequence generation for learning: a transformation from past to future

“…This type of teaching strategy will not help students who believe that learning is learner-centered. Dukhanov et al (2015) and Shmelev et al (2015), both works of the same user, use two different variants of the genetic algorithm to generate learning sequences. A course (sequence of LOs) is presented as an individual with one chromosome, and each gene is an LO.…”

Learning Path Recommendation using Hybrid Particle Swarm Optimization

“…Genetic Algorithm (GA) is a metaheuristic method which is famous because it has good performance for various types of optimization problems. There have been many GA studies in the CS domain including [8]- [11].…”