Please use this identifier to cite or link to this item:
http://repository.aaup.edu/jspui/handle/123456789/2656
Title: | Evaluation and Forecasting of University Students Performance Using Neural Networks and Fuzzy Logic Models رسالة ماجستير |
Authors: | Attieh, Mahmoud Emad Mahmoud$AAUP$Palestinian |
Keywords: | computer skills,computer system engineering,data coding |
Issue Date: | 2020 |
Publisher: | AAUP |
Abstract: | The quality of education is the most important objective for the higher educational institutions. It can be evaluated by learning and teaching process. The education quality has many definitions which differe based on the culture, one of these defintions is an all- inclusive term in which environments as well a slearners for education are content is 1 healthy, hing is student- d and ٥١ that itud. knowledge and skills which are linked to national goals for education. The quality of the learning and teaching process depends on different parameters, some of these parameters are teaching methods, content, learning environment etc. There are many of metrics used to measure and track academic progress and achievement, like GPA and rank in class. One of these important metrics is the student’s academic performance, where through this metric when it is predicted early, more information about the class or the major can be gathered and then analyzed to detect the reasons for low student’s performance which may be from student, teacher, content, learning environment or teaching methods. After gathering this information, the specialists can handle and improve the reasons which will lead to improvement in the education quality. The low academic performance of university students whether they are newly admitted students or current university students is a problem that higher education institutions must assess to avoid the disapproval of the courses, which affect the education level on; wasting time, money, and effort. Artificial intelligence techniques can be applied to forecast the academic performance of university students, to detect the factors that influence their learning process and allow instructors and universities administration to take more effective actions of counseling the students that require it. The process of forecasting the university student’s performance can focus on the first year student and on the performance of the current students.So, identifying the performance of students will identify the quality of education which will be through analyzing and forecasting the student performance at the course level using many of factors like, attendance, exam marks and project marks, for the course and the student level one semester to forecast the performance in the whole degree. In these two stages, a hybrid Adaptive Neuro Fuzzy Inference System (ANFIS) model, and a Fuzzy Logic model are used to perform the forecasting process. In this way, based on the datasets from the first examinations collected from the Arab American University selected courses, or from the dataset collected of the gineering degree. Future results can be forecasted and suggestions can be made to carry out a corrective exercise to improve the final results. On the other hand, K-means clustering and fuzzy c-means clustering methods are used to optimize the best distribution of the course grades from percentage grades to letter grades, to generate the optimal and efficient scale fairly. The experiments result of the applied models performed that the Adaptive Neuro Fuzzy Inference System (ANFIS) outperforms the Fuzzy Logic model in most cases, especially the ANFIS-Grid, wherein each model it gets the lowest error; in FRM dataset the Model get 0.7% where it just fails in one sample from thirteen samples, while the ANFIS-Cluster after modification it gets 0.15%. Where Fuzzy Logic is suitable for models of courses which contain only two inputs. Also, a graphical user interface application using python prc ing 1 developed. Also, a promising result of using clustering methods for distributing students’ grades for a course. |
Description: | Master's Degree in Computer Science. |
URI: | http://repository.aaup.edu/jspui/handle/123456789/2656 |
Appears in Collections: | Master Theses and Ph.D. Dissertations |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
محمود عطيه.pdf | 16.8 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
Admin Tools