Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus ERIC kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

Comparative Analysis of Deep Learning Approach to Identify Usage of Mobile Phone in the Classroom Environment

Title: Comparative Analysis of Deep Learning Approach to Identify Usage of Mobile Phone in the Classroom Environment
Language: English
Authors: Dhatri Pandya; Keyur Rana; Aditi Padhiyar
Source: Education and Information Technologies. 2025 30(10):13105-13128.
Availability: Springer. Available from: Springer Nature. One New York Plaza, Suite 4600, New York, NY 10004. Tel: 800-777-4643; Tel: 212-460-1500; Fax: 212-460-1700; e-mail: customerservice@springernature.com; Web site: https://link.springer.com/
Peer Reviewed: Y
Page Count: 24
Publication Date: 2025
Document Type: Journal Articles; Reports - Research
Descriptors: Technology Uses in Education; Handheld Devices; Telecommunications; Classroom Environment; Student Behavior; Use Studies; Academic Achievement; Identification; Data Collection; Models; Attention
DOI: 10.1007/s10639-025-13351-9
ISSN: 1360-2357; 1573-7608
Abstract: With the advent of closed-circuit television systems (CCTV) in the era of technology, a massive amount of video data is generated daily. CCTV are installed at several educational institutions to monitor students' behavior and ensure their safety. Human activity monitoring is done manually. Abnormal human actions refer to rare or unusual actions in a particular environment. One of the observed abnormal actions in a classroom is the usage of mobile phones by students. The frequent usage of mobile phones in the classroom environment will make students lose their attention and lead to a degradation in their academic performance. There is a high need for a system to monitor the students' abnormal behavior in the classroom environment. To solve this problem, we have proposed a methodology to recognize whether or not the students use mobile phones in the classroom. To achieve the desired results, we have trained the deep learning architecture ResNet50 using the concept of transfer learning on real-time data collected from various educational institutions. We have achieved a remarkable accuracy of 96% with proposed R[subscript TL]Model-Based in the research work. With the proposed methodology, academic institutions can monitor students' attention in the classroom and take necessary actions.
Abstractor: As Provided
Entry Date: 2025
Accession Number: EJ1476394
Database: ERIC