Browsing by Author "Syzdykov R."

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Development of an Exam application using Adaptive Learning algorithms
    (2013) Syzdykov R.
    Web-based exams are becoming increasingly popular in the last years; however, most of the exams developed using static exam content, so that students access to the same content irrespective of different learning backgrounds, learning styles, knowledge levels and abilities. It's a challenge to develop advanced Web-based exam application that can offer both adaptivity and intelligence. This study presents a novel approach to design an exam application which includes major adaptive features. The student, domain and exam content are separately designed to support adaptive learning. Application tracks students’ answers during the exam phase. The results are analyzed according to the Item Response Theory (IRT) in order to calculate students’ abilities. The student model is updated based on exam results. The updated student model is used to generate learning style and knowledge level of each learner.
  • Thumbnail Image
    ItemOpen Access
    Development of an Exam application using Adaptive Learning algorithms
    (Faculty of Engineering and Natural Science, 2013) Syzdykov R.
    Web-based exams are becoming increasingly popular in the last years; however, most of the exams developed using static exam content, so that students access to the same content irrespective of different learning backgrounds, learning styles, knowledge levels and abilities. It's a challenge to develop advanced Web-based exam application that can offer both adaptivity and intelligence. This study presents a novel approach to design an exam application which includes major adaptive features. The student, domain and exam content are separately designed to support adaptive learning. Application tracks students’ answers during the exam phase. The results are analyzed according to the Item Response Theory (IRT) in order to calculate students” abilities. The student model is updated based on exam results. The updated student model is used to generate learning style and knowledge level of each learner.