Citation

Nand, Shardha and Mohd Su'ud, Mazliham and Shaikh Ali, Siti Haryani and Alam, Muhammad Mansoor (2024) Deep Insights: Elevating Academic Performance Through Facial Expression Classification with Advanced Deep Learning Techniques. In: Proceedings of the International Conference on Advancing and Redesigning Education 2023. Springer Science and Business Media Deutschland GmbH, pp. 26-35. ISBN 978-981-97-4506-7

Full text not available from this repository.

Abstract

Facial expressions play a vital role in academics by influencing student engagement and teacher-student interactions. The identification and classification of facial images during classroom learning offer a promising method to measure students’ academic performance. This system holds significant potential benefits for educators, teachers, policy makers, and parents, enabling them to take early steps to enhance students’ academic progress. Among the four deep learning algorithms, utilized for facial emotion expression extraction and detection, namely CNN, VGG-16, ResNet-50, and MobileNet, CNN stands out as the top-performing method. With an impressive accuracy of 87.56% and a validation score of 61.58%, CNN’s results reinforce its effectiveness in assessing students’ academic achievements through facial expressions. This innovative approach has the potential to revolutionize how academic performance is monitored and supported, fostering better educational outcomes for students.

Item Type:	Book Section
Uncontrolled Keywords:	Convolutional neural network, deep learning
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	28 Feb 2025 02:06
Last Modified:	28 Feb 2025 02:32
URII:	http://shdl.mmu.edu.my/id/eprint/13538

Downloads

Edit (login required)