Proximity Estimation with BLE RSSI and UWB Range Using Machine Learning Algorithm
Bibliographic record
Abstract
Measuring the distance between two indoor mobile phones has recently become important in the context of pandemic contact tracing. Mobile phone location has improved as new technologies are added to smartphones. Ultra-wideband (UWB) ranging radios capable of centimetre-level ranging accuracies have been included in some flagship smartphone models beginning in 2019 but remain uncommon. The ranging radios compute distances using two-way time of flight approaches, providing up to centimetre-level accuracy in line-of-sight (LOS) conditions. Other mobile phones in the market today use Bluetooth Low Energy (BLE) to estimate proximity between two Bluetooth-enabled devices using the Received Signal Strength Indicator (RSSI). However, this technology suffers from drawbacks since the varying propagation environment inhibits stable RSSI. This paper presents a method where a subset of users are carrying high-end UWB-enabled smartphones. These users collect precise UWB ranges in addition to BLE RSSI. A classical machine learning (ML) algorithm is then trained with UWB ranges as truth values to estimate distances based on RSSI. A random forest ML technique is described for RSSI to distance modeling. The majority of the users, with only BLE, then estimate their relative distances using the trained model. The model was trained using UWB and BLE observations collected in an empty room environment. The model was then tested using RSSI measurements from the same empty and a second room containing typical office furniture. When testing on the training environment, 213 test samples were used. In the second office environment 200 RSSI samples were used to estimate distance in various locations.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".