DBLoc: A Lightweight and Universal BFI-Enabled Deep Learning Framework for Wi-Fi Localization
Bibliographic record
Abstract
WiFi-based passive indoor localization has gained prominence owing to its high accuracy and ease of deployment in GPS-denied environments. However, Channel State Information (CSI)-based systems face challenges, including high data acquisition requirements, significant computational overhead, and limited transferability. In this paper, we introduce DBLoc, a WiFi localization system that leverages beamforming feedback information (BFI), a novel attribute provided by modern WiFi hardware. BFI’s clear-text transmission and stable characteristics make it an ideal choice for localization tasks. We prove that BFI provides a lightweight alternative to CSI, significantly reducing both data acquisition and storage requirements. Compared with traditional deep learning frameworks using convolutional networks, DBLoc employs a pruning-based residual architecture to reduce computational overhead, achieving an inference cost of only 175.7 MFLOPs, thus optimizing performance within an edge-deployment budget. To enable transferability that surpasses current meta-learning approaches, DBLoc incorporates a virtual-domain-based meta-learning algorithm, ensuring robust performance with minimal target-domain data. Additionally, a spatial-encryption mechanism is proposed to safeguard the BFI-based model from eavesdropping. Extensive evaluations demonstrate that DBLoc achieves a median localization error of approximately 0.5 m, while significantly reducing localization accuracy for unauthorized attackers.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".