Real-Time Student Behavior Monitoring System Based on Edge–Cloud Collaboration and LSTM Modeling
Bibliographic record
Abstract
To meet the demand for intelligent governance under the "Three-All Education" framework in universities, this study presents the design and implementation of a real-time student behavior monitoring system. Built upon an edge–cloud collaborative architecture, the system integrates multi-source data—such as access control logs, classroom attendance, power usage, library entries, and card transactions. Edge nodes powered by Jetson Nano handle local data preprocessing, feature extraction, and initial classification, significantly reducing latency and bandwidth usage. At its core, an LSTM (Long Short-Term Memory) model is used to capture temporal behavior patterns for anomaly detection. When tested on real campus data, the model achieved a detection accuracy of 94.3% and an F1 score above 0.91, outperforming Random Forest and SVM benchmarks. Deployed at a technical university in Jiangsu Province covering more than 4,000 students, the system processes over 15,000 samples daily, with end-to-end latency under 2 seconds and reliable stability. These results demonstrate the system’s practical viability and strong potential for supporting student management, risk warning, and intelligent governance in smart campus settings.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".