Complementary Architecture of E-Learning Path Personalization and Optimization

Using computing algorithms to generate personalized learning resources provide the needs and improve capabilities, preferences, academic performance of diverse learners is creating preferred environments. As more resources, strategies techniques are frequently added these e-learning systems, input data personalize path has been growing exponentially making swift responses learner’s requests difficult. This study proposed a complementary personalization architecture using ant colony (ACO) with nearest neighbour technique genetic algorithm (GA) extend functions Spark framework purposely develop robust evolutionary algorithm. Experimental results indicate that complementing ACO, GA frameworks improved generation best-fitted-optimized paths. Spark-ACO took less computational time than standalone ACO. Combining ACO likelihood an being trapped at local optimum, Spark-ACO-GA significantly enhanced accuracy solutions.