Applying Intelligent Systems for Modeling Students' Learning Styles Used for Mobile and Web-Based Systems

The identification of the best learning style in an Intelligent Tutoring System must be considered essential as part of the success in the teaching process. This research work presents a set of three different approaches applying intelligent systems for automatic identification of learning styles in order to provide an adapted learning scheme under different software platforms. The first approach uses a neuro-fuzzy network (NFN) to select the best learning style. The second approach combines a NFN to classify learning styles with a genetic algorithm for weight optimization. The learning styles are based on Gardner’s Pedagogical Model of Multiple Intelligences. The last approach implements a self-organising feature map (SOM) for identifying learning styles under the Felder-Silverman Model. The three approaches are used by an author tool for building Intelligent Tutoring Systems running under a Web 2.0 collaborative learning platform. The tutoring systems together with the neural networks can also be exported to mobile devices. We present results of three different tutoring systems produced by three implemented authoring tools.