Title: Hybrid automation of student activity records in virtual learning environments in semi-dark scenarios

Authors: Manzoor Ahmed Hashmani; Mehak Maqbool Memon; Kamran Raza; Syed Sajjad Rizvi

Addresses: Department of Computer and Information Sciences, High-Performance Cloud Computing Centre (HPC3), Universiti Teknologi PETRONAS, Seri Iskandar, Malaysia ' Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Seri Iskandar, Malaysia ' Faculty of Engineering Science and Technology, Iqra University, Karachi, Pakistan ' Faculty of Computer Science, SZABIST, Karachi, Pakistan

Abstract: Online learning is raging due to the offered advantages including the ease of information accessibility and flexible learning experiences remotely. However, it still lacks intelligent authentication and validation of users at the other end. Additional questions are raised for the effectiveness of transfer of knowledge, soft skills, and value of education as the student's engagement. Following the hype and crucial need for full-fledged virtual learning environments (VLEs) in recent times, the literature has witnessed a significant increase in the studies targeting the associated problem areas. The existing VLEs in place fail to provide aggregated functionalities of student authentication and activity tracking in dynamic visual environments. To solve the problem by providing interactive functionality, an automated hybrid information activity system (HIAS) based on facial biometrics, facial emotion recognition using computer vision techniques is proposed. The proposed system solves the problem intelligently by analysing the incoming online video from the tutor's computer screen.

Keywords: facial biometrics; emotion recognition; computer-vision; online videos.

DOI: 10.1504/IJBIDM.2023.127348

International Journal of Business Intelligence and Data Mining, 2023 Vol.22 No.1/2, pp.16 - 33

Received: 15 Jul 2021
Accepted: 17 Sep 2021
Published online: 30 Nov 2022 *