Browsing by Author "Rambharose, Tricia"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Computational intelligence-based personalization of interactive web systems
    (2011-06-14) Rambharose, Tricia; Nikov, Alexander
    The main Computational Intelligence (CI) models for personalization of interactive web systems are identified as Fuzzy Systems, Genetic Algorithms, Neural Networks, Artificial Immune Systems and Swarm Intelligence which includes Particle Swarm Optimization, Ant Colony Optimization, Bee Colony Optimization and Wasp Colony Optimization. These models are reviewed and compared regarding their inception, functions, performance and application to personalization of interactive web systems. A taxonomy for personalization of interactive web systems based on CI methods is proposed. It uses two approaches to personalize web-based systems as profile generation and profile exploitation. Based on this taxonomy a general procedure and recommendations for personalization of interactive web systems are suggested. Future directions for application of CI modelling for personalization are discussed.
  • Thumbnail Image
    Item
    Personalization of web based interactive systems using computational intelligence techniques
    (2012-10-03) Rambharose, Tricia; Nikov, Alexander
    The research presented in this paper focuses on personalization of WBIS using computational intelligence (CI) methods. The scope of this research is first given and then developments in each aspect are explained. Taxonomy for personalization of WBIS using eight identified CI techniques is presented. Comparison of these eight CI techniques is made and reasons given for selection of a neuro-swarm hybrid CI model for investigation of personalization. A created MATLAB add-in for implementation of this neuro-swarm model is then used to show superior performance of PSO over backpropagation for NN training. A model for personalization of eLearning systems by neuro-swarm determination of learning style is presented. Results of a simulation for the personalization of the structure of a course in Moodle, using the neuro-swarm model, are then given.