Team Members:

Mourad Ahmed Nabawy {CV}
Youssef Mohamed Khalifa {CV}
HabebaElrahman Hesham {CV}
Ola Mohamed Safwat {CV}


Dr. Ammar
Eng. Haytham


Document: Proposal Document

Presentation: Proposal Presentation

Software Requirement Specification:

Document: SRS Document

Presentation: SRS Presentation

Software Diagram Document:

Document: SDD Document

Presentation: SDD Presentation

Final Thesis:

Document: Final Thesis Document

Presentation: Final Thesis Presentation



User Feedback:


Project Description:

Our proposed system is designed to detect the next educational level of the learner while taking the exam by capturing his facial expressions during the exam, and then predict the next level for the learner after finishing the exam. The main goal is to help learners to have the most accurate level by an automated system without an evaluation from the instructor.

Field of Knowledge: Machine Learning and Web Application. 

Tools: Python for creating Models , PHP for connection to database from python and building System back end which is web application e-learning system model, MySQL for database creation and Flask for combining between modules. 

Papers submitted and published:

  • Proc. of the 2nd International Conference on Electrical, Communication and Computer Engineering (ICECCE) 12-13 June 2020, Istanbul, Turkey.

Abstract: With the growth rate of modern technologies, Computer-based learning environment receives attention for academic goals. In this environment, a computer provides learners with a set of learning contents divided into learning levels. Usually, Computer-based learning environment research efforts detect the next level of the learner automatically based on the correct responses of the learner on a test at the end of every learning level. Different efforts use fuzzy approaches to handle the uncertainly in the learning environment. In this paper, a machine learning approach is proposed to detect the current education level of the learner based on a recorded facial expressions of the learners as well as important features of the learning environment. Several classifiers are employed to recognize the education level. The evaluation of the proposed approach on a real dataset shows that Support Vector Machine (SVM) outperforms the other classifiers and achieves accuracy of 87%. The paper also presents a regression method to detect the learning level as a continuous value. The evaluation of the regression methods shows that the Linear Regression with mean squared error of 0.0048 outperform SVR.

Publish URL: IEEE xplore

Paper Draft: Draft