A fuzzy expert system in evaluation for E-learning

Abstract

with the flourish of online education and distance learning, it's become very important to make the evaluation in elearning scientifically and objectively. This paper presents an intelligent fuzzy evaluation system based on our innovative evaluation method where management rules made by the experts are used to help, optimize and decide. On this basis, we develop an evaluation method and algorithm based on the fuzzy logic concepts and new information technologies. Thus, intelligent applications are possible if one wish to automate the management and decision while making an alarm system based on relevant indicators. Finally, we come up with an "expert system" that can provide some solutions to the problems of measurement theory. In addition, we present a concrete example to compare this method with the traditional one then draw conclusions on the effectiveness of this method.

A new expert system for learning management systems evaluation based on neutrosophic sets

“…Different evaluation models for e‐learning quality attributes developed under the condition of complete information availability. Real environment is characterized by imprecise knowledge, incomplete information and uncertain data, this problem leads researchers to use approaches that deals with vagueness like fuzzy logic (Popenţiu‐Vlădecescu & Albeanu, ; Salmi et al, ), and to suggest neutrosophic logic that handle uncertainty for e‐Learning quality evaluation (Albeanu & Vlada, ). Expert system simulates human expert thinking to solve a problem and take decision in a particular domain which is mainly composed of the user interface, knowledge base, and inference engine (Anuradha & Kumar, ).…”

A novel evaluation model based on fuzzy logic for distance learning

“…In the literature, in studies for assessment and evaluation and student performance evaluation, artificial neural networks, deep learning, random forest, logistic regression, multilayer perceptron, naive bayes, support vector machines, C4.5, decision trees, k-means, JRIP, J48, k-NN, image processing, and fuzzy inference methods were used (Abu Bakar et al, 2020;Abubakar and Ahmad, 2017;Annabestani et al, 2019;Azimjonov et al, 2016;Barlybayev et al, 2016;Cebi and Karal, 2017;Dashko et al, 2020;Echauz and Vachtsevanos, 1995;Ghatasheh, 2015;Gocheva-Ilieva et al, 2021;Hassan et al, 2019;Hussain et al, 2018;Ingoley and Bakal, 2012;Ivanova and Zlatanov, 2019;Jamsandekar and Mudholkar, 2013;Jyothi et al, 2014;Khawar et al, 2020;Kotsiantis et al, 2004;Mahboob et al, 2016;Ndukwe et al, 2019;Ölmez, 2010;Raval and Tailor, 2020;Salmi et al, 2014;Silva et al, 2016;Sisovic et al, 2016;Slater and Baker, 2019;Sokkhey and Okazaki, 2019;Turan et al, 2018;Umer et al, 2017;Ünver, 2020;Waheed et al, 2020;Wardoyo and Yuniarti, 2020;Yildiz et al, 2013;Yıldız, 2014). Since fuzzy logic-based work was done within the scope of the study, the studies carried out with this method are detailed below.…”

“…In another fuzzy inference-based study, student answers were represented by 7 linguistic expressions as unanswered, very bad, bad, moderate, not bad, good, very good. The linguistic expressions of very good, good, not bad, moderate, bad, and very bad were used in the output of the fuzzy inference system (Salmi et al, 2014). In studies where fuzzy logic-based performance evaluation was conducted, performance evaluation was conducted using homework, quizzes, midterms, finals, watching videos, reading books, personal development, communication skills, and participation information (Azimjonov et al, 2016;Barlybayev et al, 2016;Kumari et al, 2017).…”

A Novel Student Performance Evaluation Model Based on Fuzzy Logic for Distance Learning

“…In another fuzzy inference-based study, student answers were represented by 7 linguistic expressions as unanswered, very bad, bad, moderate, not bad, good, very good. The linguistic expressions of very good, good, not bad, moderate, bad, and very bad were used in the output of the fuzzy inference system [22]. In studies where fuzzy logic-based performance evaluation was conducted, performance evaluation was conducted using homework, quizzes, midterms, finals, watching videos, reading books, personal development, communication skills, and participation information [25], [26], [50].…”