ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM BASED UBIQUITOUS LEARNING MIDDLEWARE FOR NORMAL AND HANDICAPPED LEARNERS

Abstract

Lack of standard learning infrastructures in tertiary and secondary institutions in most developing countries has made learning cumbersome as most available learning environments were designed to cater mainly for normal users with little or no consideration for users with learning disabilities, thereby resulting in poor academic performance among these affected groups. Hence, this work proposes an ANFIS (Adaptive Neuro-Fuzzy Inference System) based Ubiquitous Learning Middleware to support both normal learners and those with learning disabilities by providing suitable learning contents. The Ubiquitous environments were set up with RFID readers mounted in strategic places (library, lecture hall, laboratory, and student union building) in the institution. RFID tags were attached to mobile devices to serve as authentication component to the developed ubiquitous mobile learning system, while the Adaptive Neuro-Fuzzy Inference System (ANFIS) is used to make the suggestion of the most suitable learning content possible using parameters such as Noise level, learner attribute, network bandwidth, and processing speed as input. The developed ubiquitous mobile learning system was evaluated using two standard metrics namely: ISO/IEC 9126 standard metrics and the Usability and User experience (UX) measurement instruments. The evaluation carried out shows the effectiveness of the developed ANFIS-based U-Learning system in proffering solution to some of the challenges faced by learners with learning disabilities as the system attained 94% Correctness, 88% Satisfaction, 78% Validation, 78% System Simplicity, 88% System Feedback, and 94% Efficiency.