An important issue in personalized learning is to provide learners with customized learning according to their learning characteristics. This paper focused attention on scheming learning map as follows. The learning goal can be achieved via different pathways based on alternative materials, which have the relationships of prerequisite, dependence, and sequence. Besides, owing to distinct learner characteristics, different learning materials with various forms have distinct effects on learners, such as learning performance (benefit objective), learning time (cost objective), and so forth. Accordingly, scheming learning map is not only the NP-hard combination problem, but also the tradeoff multiple objectives optimization. More importantly, it is not only impossible for instructors to scheme the fitting learning maps for learners, but also difficult and time-consuming for learners to scheme their fitting learning maps by themselves. Hence, this paper first proposed an innovative approach based on enhanced genetic algorithm (GA) with Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), to facilitate the search for the near-optimal solution of learning map. Moreover, a web-based learning management system based on the proposed approach was developed to help instructors facilitate the customized learning itineraries for learners. The experimental results from simulations showed that, not only in terms of search effectiveness and solution quality the proposed approach significantly is superior to a genetic algorithm and a Random method, but also in terms of search efficiency the proposed approach significantly is superior to a genetic algorithm. That is, the developed system with the proposed approach is able to efficiently scheme the learning map with reliable and high quality. Consequently, the instructors and learners can concentrate on their tasks.
|頁（從 - 到）||142-157|
|期刊||Educational Technology and Society|
|出版狀態||Published - 2016|
All Science Journal Classification (ASJC) codes
- Sociology and Political Science