학술논문

On Simulation of Adaptive Learner Control Considering Students' Cognitive Styles Using Artificial Neural Networks (ANNs)
Document Type
Conference
Author
Source
International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC'06) Computational Intelligence for Modelling, Control and Automation, 2005 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, International Conference on. 2:415-421 2005
Subject
Robotics and Control Systems
Computing and Processing
Programmable control
Adaptive control
Artificial neural networks
Computational modeling
Educational technology
Computer aided instruction
Application software
Computer applications
Unsupervised learning
Process control
Language
Abstract
The field of the learning sciences is represented by a growing community internationally. Many experts now recognize that conventional ways of conceiving knowledge, educational systems and technology-mediated learning are facing increasing challenges in this time of rapid technological and social changes. Herein, a suggested innovative, challenging trend at the field of the learning sciences is adopted. This trend deals with complex issues associated to deferent educational/learning phenomena. This paper presents a novel realistic simulation of some observed educational phenomena using ANNs modeling. Results obtained after practical application of a computer assisted instructional program are mainly motivating our realistic ANNs computer models. In some details, suggested ANNs models simulate realistically students' learning behavioral phenomena for two different cognitive styles. These styles are field dependent (FD) style and field independent (FI) one. Both were simulated via two types of ANNs models obeying two learning paradigms. That is supervised and unsupervised learning paradigms simulating FD and FI cognitive styles respectively. Moreover, both models simulate adaptive performance of learner control as learning process proceeds. That is fulfilled after following of suggested deferent learner control indices to simulate deferent levels of learner control. Interestingly, obtained results shown to be agree well with results obtained by practical educational experimental work. Additionally, our results give a valuable interpretation to some other results obtained after some educational studies. Conclusively, this paper, in few words, classified as an interdisciplinary research work dealing with some complex challenging educational issues. In practice, these issues arise recently due to excessive progress in computer and information technologies. That applied in educational practical field aiming to reach non traditional (non classical) solutions for confronted issues.