A Genetic-Fuzzy Based Mathematical Model to Evaluate The Distance Education Students’ Academic Performance

Abstract In distance education systems, it is very important to predict academic performance for both instructors and students during the course of the semester. If an instructor can properly assess and predict student performance early at the beginning of the semester, then the instructor can take action and arrange both the course content and the teaching style. This, in turn, contributes greatly to the success of students. In order to make such a prediction, constructing mathematical models is one of the most effective and efficient methods. Among many approaches, fuzzy logic-based models have the most appropriate topology. In this study, fuzzy logic model is used to model data of distance education and predict students’ academic performances. In order to increase the success of fuzzy logic model, fuzzy membership functions are optimized by using genetic algorithms. As distance education data, when students enrolled in learning management system, how frequently they log on, and how long they stay online are used. By using this model and data of a 6 week-long study, students’ success level at the end of the semester is predicted and the results are compared with the ground truth data.

[1]  Hui-Chu Chang.  Developing EL-RFM model for quantification learner's learning behavior in distance learning , 2010, 2010 2nd International Conference on Education Technology and Computer.

[2]  Sotiris B. Kotsiantis,et al.  Predicting students marks in Hellenic Open University , 2005, Fifth IEEE International Conference on Advanced Learning Technologies (ICALT'05).

[3]  Nadine Meskens,et al.  Predicting Academic Performance by Data Mining Methods , 2007 .

[4]  Sebastián Ventura,et al.  Predicting Student Grades in Learning Management Systems with Multiple Instance Genetic Programming. , 2009, EDM 2009.

[5]  Arthur Middleton Hughes,et al.  Strategic database marketing , 2005 .

[6]  Osman Taylan,et al.  An adaptive neuro-fuzzy model for prediction of student's academic performance , 2009, Comput. Ind. Eng..

[7]  F. Gomide,et al.  Ten years of genetic fuzzy systems: current framework and new trends , 2001, Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference (Cat. No. 01TH8569).

[8]  Dimitrios Kalles,et al.  ANALYZING STUDENT PERFORMANCE IN DISTANCE LEARNING WITH GENETIC ALGORITHMS AND DECISION TREES , 2006, Appl. Artif. Intell..

[9]  Ioanna Lykourentzou,et al.  Early and dynamic student achievement prediction in e-learning courses using neural networks , 2009 .

[10]  Hyun-Joon Cho,et al.  Fuzzy-PID hybrid control: Automatic rule generation using genetic algorithms , 1997, Fuzzy Sets Syst..

[11]  Norazah Yusof,et al.  Evaluation of Student's Performance and Learning Efficiency Based on ANFIS , 2009, 2009 International Conference of Soft Computing and Pattern Recognition.

[12]  Frederick Newell.  The New Rules of Marketing: How to Use One-To-One Relationship Marketing to Be the Leader in Your Industry , 1997 .

[13]  Randy L. Haupt,et al.  Practical Genetic Algorithms , 1998 .