Artificial nero fuzzy inference model for location and time aware m-learning system - an empirical investigation. (17th February 2021)

• Record Type: Journal Article
• Authors: Deshpande, Sudhindra Balwant; Mangalwede, Shrinivas R.
• Is Part Of: International journal of intelligence and sustainable computing. Volume 1:Number 2(2021)
• Page Start: 115
• Page End: 127
• Publication Date: 2021-02-17
• Subjects: m-learning -- ANFIS -- fuzzy system -- neural networks -- context awareness -- personalisation -- content adaption -- e-learning; Computer science -- Periodicals; Computational intelligence -- Periodicals; Computer networks -- Environmental aspects -- Periodicals; 004
• Languages: English
• ISSNs: 2517-763X

Abstract

Use of smart devices in education has facilitating anywhere and anytime learning, providing access to the contents through mobile devices, is called as 'mobile learning (m-learning)'. Learning styles have been evolved with advancements in mobile technology and mobile networks. Personalisation and context awareness of a learner play a vital role in delivering suitable content, based on the context of a learner. There is a need of a content delivery system that takes care of dynamically changing learner needs. Artificial nero fuzzy inference system (ANFIS) can be used to model such an adaptive content delivery system for an m-learning environment. In this paper, two models have been built and compared for their performance. The first model uses grid partitioning algorithm and second, subtractive clustering. Firstly, in both models the behaviour of the two optimisation methods-hybrid and back propagation; against various membership functions are compared for their exclusive performance against various datasets. Secondly, behaviours of both models are compared to find out which model performs better against various datasets.