Rules Optimization Based Fuzzy Model for Predicting Distance Education Students' Grades

 Abstract—Distance education has been rapidly becoming widespread all around the world. This rapid growth brings along both success and failure. One of the causes of failure in distance education is the lack of student observation, which is a part of traditional education. We can overcome this deficit through an analysis of logs kept in the learning management system. These logs make it possible to estimate academic performance of a student attending to distance education. The instructor having such information can take precautions in order to prevent failure. In this study, a mathematical model has been formed by using Fuzzy Logic. In order to enhance the success of model, fuzzy logic rules have been optimized by using genetic algorithm. Three different variableshave been introduced to the proposed model. These are recency, stating the number of days that pass from the date of registering course contents until the date of student's admission to the system; frequency, stating the frequency of logging on to the system and monetary, stating the period of time spent online on the system. End of term scores of students have been estimated on the basis of the first 6-week data and then the results have been verified by the real scores.

[1]  Dorothea Heiss-Czedik,et al.  An Introduction to Genetic Algorithms. , 1997, Artificial Life.

[2]  Rogelio Lozano,et al.  Modeling and Control of a Small Autonomous Aircraft Having Two Tilting Rotors , 2005, IEEE Transactions on Robotics.

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

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

[5]  Abdullah Bal,et al.  A Genetic-Fuzzy Based Mathematical Model to Evaluate The Distance Education Students’ Academic Performance , 2012 .

[6]  Chang Wook Ahn,et al.  On the practical genetic algorithms , 2005, GECCO '05.

[7]  Frank L. Lewis,et al.  Dynamic inversion with zero-dynamics stabilisation for quadrotor control , 2009 .

[8]  Daewon Lee,et al.  Build Your Own Quadrotor: Open-Source Projects on Unmanned Aerial Vehicles , 2012, IEEE Robotics & Automation Magazine.

[9]  Mahmut Faruk Aksit,et al.  Dynamic model and control of a new quadrotor unmanned aerial vehicle with tilt-wing mechanism , 2008 .

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

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

[12]  Vassilis Loumos,et al.  Early and dynamic student achievement prediction in e-learning courses using neural networks , 2009, J. Assoc. Inf. Sci. Technol..

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

[14]  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.