EUVIMEDEUVIMED entdecken
Crossref

An Intelligent Multi Modal Classroom Monitoring System Using Deep Learning for Secure Attendance, Engagement Analysis and Predictive Analytics

Mohammed Omer Farooq, Mohammed Saad, Mohammed Mueez Gous, Mir Mushtaq Ali, Mohazzeba Tanveer Raza

International Journal of Innovative Science and Research Technology · 12.06.2026 · 4124

DOI: 10.38124/ijisrt/26may1752 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Innovative Science and Research Technology, online erschienen am 12.06.2026. Verfasst von Mohammed Omer Farooq und 4 weiteren Autor:innen. Die Arbeit nennt 16 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automated attendance management has emerged as a critical area of research in the domains of computer vision and artificial intelligence, offering efficient, contactless, and proxy-free alternatives to conventional manual methods. This survey presents a comprehensive review of face recognitionbased automated attendance systems, covering classical machine learning approaches such as Haar Cascade, Local Binary Pattern Histograms (LBPH), and Histogram of Oriented Gradients (HOG), as well as advanced deep learning methods including Multi-task Cascaded Convolutional Networks (MTCNN), FaceNet, ResNet-50, YOLOFace, and RetinaFace. The paper systematically examines fifteen recent works, analyzing their architectures, datasets, evaluation metrics (accuracy, precision, recall, F1-score, and inference time), and deployment environments ranging from classroom settings to corporate contexts. Key challenges including variable illumination, occlusion, multi-face detection, and real-time processing are discussed. A comparative analysis reveals that deep learning-based systems, particularly those integrating MTCNN for detection and FaceNet or ResNet- 50 for recognition, consistently outperform classical methods, with accuracies exceeding 98% under normal conditions. Cloudbased solutions leveraging AWS Rekognition demonstrate 100% detection accuracy in controlled scenarios. The survey concludes by identifying open research gaps and future directions including edge deployment, liveness detection, multi-modal biometrics, and privacy-preserving attendance systems.

Zitieren

APA

Farooq, M. O., Saad, M., Gous, M. M., Ali, M. M., & Raza, M. T. (2026). An Intelligent Multi Modal Classroom Monitoring System Using Deep Learning for Secure Attendance, Engagement Analysis and Predictive Analytics. International Journal of Innovative Science and Research Technology, 4124. https://doi.org/10.38124/ijisrt/26may1752

Vancouver

Farooq MO, Saad M, Gous MM, Ali MM, Raza MT. An Intelligent Multi Modal Classroom Monitoring System Using Deep Learning for Secure Attendance, Engagement Analysis and Predictive Analytics. International Journal of Innovative Science and Research Technology. 2026:4124. doi:10.38124/ijisrt/26may1752

BibTeX
@article{Farooq2026,
  author = {Farooq, Mohammed Omer and Saad, Mohammed and Gous, Mohammed Mueez and Ali, Mir Mushtaq and Raza, Mohazzeba Tanveer},
  title = {An Intelligent Multi Modal Classroom Monitoring System Using Deep Learning for Secure Attendance, Engagement Analysis and Predictive Analytics},
  journal = {International Journal of Innovative Science and Research Technology},
  year = {2026},
  pages = {4124},
  doi = {10.38124/ijisrt/26may1752}
}
Kostenlos starten →