Federated Learning for WiFi Fingerprinting
Bibliographic record
Abstract
Channel State Information (CSI) based fingerprinting is surfacing as an accurate and robust method of indoor localization. However, the high-dimensional nature of CSI data impedes its adoption in multi access point (AP) systems. To reap the rewards of cooperative localization with privacy and limited system complexity in mind, we propose a federated learning (FL) architecture. Each AP has an individual model and a shared model, where the individual model parameters are unique to each AP and the shared model parameters are communicated to a central server for aggregation. The server averages the models and sends them back to each AP, which use this joint model as a regularization term. To capture the spatio-temporal characteristics of CSI, we propose a convolutional neural network (CNN) as each AP’s individual model and a multi layer perceptron (MLP) as the shared model. Extensive experimental studies verify the superiority of the proposed edge computing approach compared to the exiting methods in the literature. We use commercial off-the-shelf APs collecting CSI data in multiple indoor environments and compare the proposed system to a state-of-the-art deep learning model. Our approach shows significant improvement in the localization accuracy for both individual APs and aggregate predictions.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".