Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/77572
Title: Automated face analytics system for smart learning
Authors: Fan, Xiaofeng
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2019
Abstract: The digital revolution has enabled knowledge and skills to be more efficiently and effectively delivered via E-Learning systems. Many educational and training institutions are adopting the strategy of Flipped Classroom where the instructional content is often delivered online. This has caused difficulties of obtaining teaching feedbacks, which are useful in elaborating on the teaching content, for teachers since there is no direct face-to-face interaction between the teachers and the students. Therefore, it is critical for educational and training institutions to develop Smart Learning platforms to monitor and evaluate students’ learning process. Machine Learning, which has recently been proven to work effectively on task execution and automation, has great potential in developing technologies that meet the needs of Smart Learning. This project studies the fundamentals of facial analytics using Machine Learning including facial landmarks detection, head pose estimation, emotion classification, and gaze tracking. This project aims to explore the correlation between those statistics and students’ learning process to design a system for automating the analysis of learning process, in order to aid course administrators in improving their course content based on the analysis. Lastly, this report also gives recommendations on future works to further improve the submodules as well as to better interpret the analytical statistics.
URI: http://hdl.handle.net/10356/77572
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
FYP_Report_Final.pdf
  Restricted Access
1.88 MBAdobe PDFView/Open

Page view(s) 20

55
checked on Oct 26, 2020

Download(s) 20

29
checked on Oct 26, 2020

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.