EUVIMEDEUVIMED entdecken
Crossref

Big Data Analytics- A Key Initiative for Identification of Student Behaviour System in Modern Academics

K. Laxmi, Chandramouli H, I Manimozhi, Halavath Balaji

International Journal of Emerging Technologies and Innovative Research · 11.04.2026 · 306

DOI: 10.48175/ijetir-9245 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Emerging Technologies and Innovative Research, online erschienen am 11.04.2026. Verfasst von K. Laxmi und 3 weiteren Autor:innen. Die Arbeit nennt 8 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Student performance prediction plays a vital role in modern education by identifying students who may need additional support. This project combines machine learning (ML) models with facial behavior analysis to provide a more comprehensive evaluation of student engagement and academic success. The ML model trains various academic and behavioural factors, including attendance, learning ease, project completion, internet constraints, and knowledge retention, to classify students into high, medium, or low performance categories. Simultaneously, a facial analysis system using Dlib's frontal face detector and 68-face landmark predictor tracks key engagement metrics such as blinks, yawns, and face angle changes to determine whether a student is engaged or not engaged during learning activities. A modern practice to enhance and acknowledge the student activities from stress to active learning process. The final prediction integrates both performance-based data and engagement insights to classify students performance effectively. If a student has low academic performance and poor engagement, they are flagged as high priority: "At Risk," while engaged high-performing students are classified as "Excellent Performers." This hybrid approach enhances the accuracy of performance evaluation by not only considering academic metrics but also behavioural engagement. The system dynamically updates engagement statistics and adjusts predictions in real-time, helping educators make informed interventions and improving overall learning outcomes

Zitieren

APA

Laxmi, K., H, C., Manimozhi, I., & Balaji, H. (2026). Big Data Analytics- A Key Initiative for Identification of Student Behaviour System in Modern Academics. International Journal of Emerging Technologies and Innovative Research, 306. https://doi.org/10.48175/ijetir-9245

Vancouver

Laxmi K, H C, Manimozhi I, Balaji H. Big Data Analytics- A Key Initiative for Identification of Student Behaviour System in Modern Academics. International Journal of Emerging Technologies and Innovative Research. 2026:306. doi:10.48175/ijetir-9245

BibTeX
@article{Laxmi2026,
  author = {Laxmi, K. and H, Chandramouli and Manimozhi, I and Balaji, Halavath},
  title = {Big Data Analytics- A Key Initiative for Identification of Student Behaviour System in Modern Academics},
  journal = {International Journal of Emerging Technologies and Innovative Research},
  year = {2026},
  pages = {306},
  doi = {10.48175/ijetir-9245}
}
Kostenlos starten →