EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LightEdu-Net: Noise-Resilient Multimodal Edge Intelligence for Student-State Monitoring in Resource-Limited Environments

Chenjia Huang, Yanli Chen, Bocheng Zhou, Xiuqi Cai, Ziying Zhai, Jiarui Zhang, Yan Zhan

Sensors · 11.12.2025 · 25 (24) · 7529

DOI: 10.3390/s25247529 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 11.12.2025. Verfasst von Chenjia Huang und 6 weiteren Autor:innen. Beteiligte Einrichtung: National School of Development, Peking University, Beijing 100871, China. Hauptthemen laut MEDLINE: Students. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimodal perception for student-state monitoring is difficult to deploy in rural classrooms because sensors are noisy and computing resources are highly constrained. This work targets these challenges by enabling noise-resilient, multimodal, real-time student-state recognition on low-cost edge devices. We propose LightEdu-Net, a sensor-noise-adaptive Transformer-based multimodal network that integrates visual, physiological, and environmental signals in a unified lightweight architecture. The model incorporates three key components: a sensor noise adaptive module (SNAM) to suppress degraded sensor inputs, a cross-modal attention fusion module (CMAF) to capture complementary temporal dependencies across modalities, and an edge-aware knowledge distillation module (EAKD) to transfer knowledge from high-capacity teachers to an embedded-friendly student network. We construct a multimodal behavioral dataset from several rural schools and formulate student-state recognition as a multimodal classification task with explicit evaluation of noise robustness and edge deployability. Experiments show that LightEdu-Net achieves 92.4% accuracy with an F1-score of 91.4%, outperforming representative lightweight CNN and Transformer baselines. Under a noise level of 0.3, accuracy drops by only 1.1%, indicating strong robustness to sensor degradation. Deployment experiments further show that the model operates in real time on Jetson Nano with a latency of 42.8 ms (23.4 FPS) and maintains stable high accuracy on Raspberry Pi 4B and Intel NUC platforms. Beyond technical performance, the proposed system provides a low-cost and quantifiable mechanism for capturing fine-grained learning process indicators, offering new data support for educational economics studies on instructional efficiency and resource allocation in underdeveloped regions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

StudentsHumansNeural Networks, ComputerSchoolsAlgorithms

Stichwörter der Autor:innen

LightEdu-Netedge-based educational perceptioneducational economicsmultimodal sensor fusionstate recognition

Autor:innen und Institutionen

  • National School of Development, Peking University, Beijing 100871, China.
  • China Agricultural University, Beijing 100083, China.
  • Artificial Intelligence Research Institute, Tsinghua University, Beijing 100084, China.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Huang, C., Chen, Y., Zhou, B., Cai, X., Zhai, Z., Zhang, J., & Zhan, Y. (2025). LightEdu-Net: Noise-Resilient Multimodal Edge Intelligence for Student-State Monitoring in Resource-Limited Environments. Sensors, 25(24), 7529. https://doi.org/10.3390/s25247529

Vancouver

Huang C, Chen Y, Zhou B, Cai X, Zhai Z, Zhang J, et al. LightEdu-Net: Noise-Resilient Multimodal Edge Intelligence for Student-State Monitoring in Resource-Limited Environments. Sensors. 2025;25(24):7529. doi:10.3390/s25247529

BibTeX
@article{Huang2025,
  author = {Huang, Chenjia and Chen, Yanli and Zhou, Bocheng and Cai, Xiuqi and Zhai, Ziying and Zhang, Jiarui and Zhan, Yan},
  title = {LightEdu-Net: Noise-Resilient Multimodal Edge Intelligence for Student-State Monitoring in Resource-Limited Environments},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {24},
  pages = {7529},
  doi = {10.3390/s25247529}
}
Kostenlos starten →