Group development is an initial step and an important influence on learning collaborative problem solving (CPS) based on the digital learning environment (DLE). Group development based on the Myers-Briggs types indicators (MBTI) rule proved successful for the educational and industrial environment. The MBTI ideal group rules are reached when a group leader has the highest level of leadership and compatibility between group members. The level of leadership and suitability of group members is determined based on the MBTI learning style (LS). Problems arise when the population of MBTI LS with the highest level of leadership is over. This will lead to dual leadership problems and have an impact on group disharmony. This study proposes an intelligent agent software for the development of the ideal group of MBTI, using the Fuzzy algorithm. The intelligent agent was developed on the SKACI platform. SKACI is a DLE for CPS learning. Fuzzy algorithm for solving dual leadership problems in a group. Fuzzy algorithm is used to increase the population of MBTI LS to 3 levels, namely low, medium and high. Increasing the population of MBTI LS can increase the probability of forming an ideal group of MBTI. Intelligent agents are tested based on a quantitative analysis between experimental classes (applying intelligent agents), and control classes (without intelligent agents). Experiment results show an increase in performance and productivity is better in the experimental class than in the control class. It was concluded that the development of intelligent agents had a positive impact on group development based on the MBTI LS.


    Access

    Download


    Export, share and cite



    Title :

    Development of online learning groups based on MBTI learning style and fuzzy algorithm


    Contributors:

    Publication date :

    2020-02-01


    Remarks:

    doi:10.12928/telkomnika.v18i1.14922
    TELKOMNIKA (Telecommunication Computing Electronics and Control); Vol 18, No 1: February 2020; 199-207 ; 2302-9293 ; 1693-6930 ; 10.12928/telkomnika.v18i1



    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    006 / 629




    Online driving style recognition using fuzzy logic

    Dorr, Dominik / Grabengiesser, David / Gauterin, Frank | IEEE | 2014



    Driving style identification algorithm based on factor analysis and machine learning

    ZHAO JIAN / CHEN ZHICHENG / ZHU BING | European Patent Office | 2020

    Free access

    AUTONOMOUS DRIVING STYLE LEARNING

    ENGELMAN GERALD H / MILLER ALEX MAURICE / PILUTTI THOMAS EDWARD et al. | European Patent Office | 2015

    Free access

    Autonomous driving style learning

    ENGELMAN GERALD H / MILLER ALEX MAURICE / PILUTTI THOMAS EDWARD et al. | European Patent Office | 2015

    Free access