Recommended System for Cognitive Assessment Evaluation Based on Two-Phase Blue-Red Tree of Rule-Space Model: A Case Study of MTA Course

Having more than one professional certification is one of the various indicators for the Ministry of Education to promote and evaluate their competencies that the vocational education system students in Taiwan. This is also one way to find the ideal jobs that enhance their competitiveness for vocational students on-the-job. As a result, it is very important for students in vocational education systems to obtain professional certifications. In particular, the more professional licenses they have, the more job opportunities for them. Therefore, we propose a RS (Recommended System) that combines two-phase Blue-Red trees of Rule-Space Model and the best learning path, and it is used to remedy and analyze the learning situation of MTA courses and enhance the pass rate of MTA licenses for students. We classify three SGs (Skill Groups) from the Certiport of Microsoft certification center in the first phase, and the three SGs (Skill Groups) can be produced as a concept map and Blue-Red trees. In the second phase, The ten chapters of MTA course are classified within the three SGs (Skill Groups) of phase one according to the most similarity in contents between ten chapters and three SGs (Skill Groups). That is, three groups will be created in a MTA course from previous ten chapters. The three groups result in three concept maps and three groups of Blue-Red trees. After that, it is based on the analysis of Rule-Space Mode for all learning objects in each skill group of phase two. We can define the RW (Relation Weight) of every learning object associated with the other learning objects, and separately calculate the Confidence Level values of between two adjacent learning objects from all learning paths. Finally, the optimal learning path can be obtained by the inferred optimal learning path algorithm from the combination of RW (Relation Weight) and CL (Confidence Level). The proposed method can be used to OCLS (Online Course Learning System) that recommended the best learning path of learning objects for learners to online self-learning, or to RS (Recommended System) that provides the basis of self-learning remedies for RFRC (Recommended Form of Remedial Course).