FEDge-HAR: An Optimized Private Mobile Edge-Enabled IoT Paradigm for Privacy of Human Activity Recognition
Bibliographic record
Abstract
Federated learning (FL) has emerged as a pivotal technology for the Internet of Things (IoT) that models distributed client data without compromising privacy. The IoT-based wearable generates data and FL running on a private edge performing human activity recognition (HAR). In this article, we proposed a novel technique to protect sensitive data during the training process and ensure the confidentiality of model updates before transmission to the edge server. The proposed technique integrates the El-Gamal encryption technique for data protection, and the FL process is rigorously optimized using pruning, quantization, and network slicing. Pruning removes redundant connections, which reduces model complexity and communication delays. On the other hand, quantization decreases the bit precision of model parameters, and network slicing strategically allocates resources solely for FL resulting in low latency and optimal bandwidth utilization. The results are evaluated in terms of accuracy and communication overhead, which is highly required in real-world applications. Furthermore, the HAR system within PEC shows better results by achieving an accuracy of 99% at 300 epochs that outperformed existing machine learning (ML) algorithms.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 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".