LEARNING PATH MODEL BASED ON COGNITIVE CLASSIFICATION USING HYBRID DISCRETE PARTICLE SWARM OPTIMIZATION

摘要

Revised Blooms Taxonomy (RBT) brings up taxonomic tables which are interrelations between cognitive processes and knowledge. Taxonomic tables can measure the depth and breadth of learning goals to be achieved. The variety of characteristics of students' abilities in a class has always been a problem that is often faced by a teacher. Unfortunately, cognitive classification to develop student knowledge towards Higher Order Thinking Skills has not been used to plan the learning path model. The purpose of this study is to determine the learning path recommendation that is appropriate to students' cognitive abilities based on the revised Bloom Taxonomy and ontology learning objects. The cognitive classification of students uses the Learning Vector Quantization (LVQ) method to get three cognitive classes (Cognitive Low, Cognitive Medium, and Cognitive High). Whereas to determine the learning path using the Hybrid Discrete Particle Swarm Optimization (HDPSO) method to overcome combinatorial problems, namely the learning object ontology with discrete PSO that is controlled by cognitive classes using binary PSO. The determination of the learning path is based on testing the RBT connection quality between LO and the ontology of a subject controlled by the student's cognitive class. The RBT cognitive classification results of the developed model can identify student cognitive with very high accuracy through determining the appropriate learning rate on the LVQ network. While the Hybrid Discrete Particle Swarm Optimization (HDPSO) method applied can overcome combinatorial problems more practically and regularly in determining the learning path. Experimental studies show that the models and techniques presented are suitable for finding a learning path that fits a student's cognitive class.