Improved fuzzy modelling to predict the academic performance of distance education students

Abstract

It is essential to predict distance education students' year-end academic performance early during the course of the semester and to take precautions using such predictionbased information. This will, in particular, help enhance their academic performance and, therefore, improve the overall educational quality. The present study was on the development of a mathematical model intended to predict distance education students' year-end academic performance using the first eight-week data on the learning management system. First, two fuzzy models were constructed, namely the classical fuzzy model and the expert fuzzy model, the latter being based on expert opinion.Afterwards, a gene-fuzzy model was developed optimizing membership functions through genetic algorithm. The data on distance education were collected throughMoodle, an open source learning management system. The data were on a total of 218 students who enrolled in Basic Computer Sciences in 2012. The input data consisted of the following variables: When a student logged on to the system for the last time after the content of a lesson was uploaded, how often he/she logged on to the system, how long he/she stayed online in the last login, what score he/she got in the quiz taken in Week 4, and what score he/she got in the midterm exam taken in Week 8. A comparison was made among the predictions of the three models concerning the students' year-end academic performance.

Meta-analysis of Student Performance Assessment Using Fuzzy Logic

“…Based on these findings, it turns out that the application of fuzzy logic is more widely used in predicting student academic performance. This is because the fuzzy logic method is a practical method for evaluating academic students and is very helpful in evaluating types of subjective answers (Ingoley and Bakal, 2012;Yadav and Singh, 2011;Oyelade et al, 2010;Yadav et al, 2014;Sakthivel et al, 2013;Yildiz et al, 2013;Arora and Saini, 2013;Inyang and Joshua, 2013;Rusli et al, 2008;Do and Chen, 2013;Hidayah et al, 2013;Borkar and Rajeswari, 2013).…”

“…Input is adjusted to the rule table. The third stage is defuzzification, involving the transformation of fuzzy values to actual values (Yildiz et al, 2013). In the past decade, fuzzy logic has not only been used in engineering and science but has also been widely applied in education (Sripan and Suksawat, 2010).…”

“…• behavior (Vesely et al, 2016), • e-learning (Herrera-Viedma et al, 2009;Dias and Diniz, 2013;Almohammadi and Hagras, 2013;Deborah et al, 2015;Arguedas et al, 2018), • intelligent tutoring system (Chrysafiadi and Virvou, 2012;Machado et al, 2016), • laboratory application (Gokmen et al, 2010; Yıldız and Baba, 2014), • library service quality (Jamali and Sayyadi Tooranloo, 2009), • presentation skills (Daud et al, 2011; Ozdemir and Tekin, 2016), • problem solving (Voskoglou, 2012;Voskoglou, 2013;Owais, 2009), • student academic performance (Ingoley and Bakal, 2012;Yadav and Singh, 2011;Oyelade et al, 2010;Yadav et al, 2014;Sakthivel et al, 2013;Yildiz et al, 2013;Arora and Saini, 2013;Inyang and Joshua, 2013;Rusli et al, 2008;Do and Chen, 2013;Hidayah et al, 2013;Borkar and Rajeswari, 2013), • student learning assessment (Sripan and Suksawat, 2010), • student performance assessment (Barlybayev et al, 2016;Darwish, 2016;Baba et al, 2012;Bhatt and Bhatt, 2011;Prokhorov and Kulikovskikh, 2015;Patil et al, 2012;Pöysä-Tarhonen et al, 2016), and • students' choice (Henriques, et al, 2018;Kabra and Bichkar, 2011).…”

“…• case studies (Machado et al, 2016), • comparative analysis (Daud et al, 2011;Ingoley and Bakal, 2012;Barlybayev et al, 2016;Gokmen et al, 2010;Yadav and Singh, 2011;Darwish, 2016;Oyelade et al, 2010;Sakthivel et al, 2013;Bhatt and Bhatt, 2011;Rusli et al, 2008;Ozdemir and Tekin, 2016;Owais, 2009;Do and Chen, 2013), • experiment (Arora and Saini, 2013;Prokhorov and Kulikovskikh, 2015;Herrera-Viedma et al, 2009;Dias and Diniz, 2013;Almohammadi and Hagras, 2013;Deborah et al, 2015;Arguedas et al, 2018;Voskoglou, 2013;Borkar and Rajeswari, 2013), • mix methods (Henriques et al, 2018;Baba et al, 2012;Yadav et al, 2014;Yildiz et al, 2013;Sripan and Suksawat, 2010;Voskoglou, 2012;Inyang and Joshua, 2013;Vesely et al, 2016;Chrysafiadi and Virvou, 2012;Patil et al, 2012;Pöysä-Tarhonen et al, 2016;Kabra and Bichkar, 2011), and • questionnaire (Yıldız and Baba, 2014;Jamali and Sayyadi Tooranloo, 2009;Hidayah et al, 2013).…”

Mamdani Fuzzy Model for Learning Activities Evaluation

“…Some of the parameters used for the attitude and behaviour in this context include percentages of class attendance, regularity of assignment submissions and quality of participation in class activities among others. These observed behaviours are great contributors to students test and evaluation [12]. The challenges with the conventional approaches in the area of data gathering, objective data analysis and application limit its adoption and usefulness.…”