On-device Detection of Wearer-induced NLOS on Chest-worn UWB Tags: Machine Learning, Link Indicators, or Both?
Organizations: Institute of Technical Informatics, Graz University of Technology, Graz, Austria · Dept. of Information Eng. and Computer Science, University of Trento, Trento, Italy
Abstract
Ultra-wideband (UWB) enables high-accuracy distance estimation (ranging), but performance degrades in non-line-of-sight (NLOS) conditions. When UWB tags are worn, the human body inevitably causes a wearer-induced NLOS (WNLOS), yielding significant errors; still, despite its relevance, WNLOS remains understudied. Moreover, WNLOS detection typically must occur on-device at the tag, requiring classification accuracy to be balanced against tight runtime and energy constraints often hard to meet with machine learning (ML) -- the dominating NLOS classification approach. Meanwhile, UWB radio link indicators (LI) offer a faster and lightweight alternative that has rarely been explored. We study existing on-device ML and LI classifiers when applied to WNLOS, and propose novel hybrid ones exploiting their complementarity. We focus on chest-worn tags and analyze 21 classifiers on a dataset of 1.5 million samples across channels, PHY settings, environments, subjects, and orientations. Results show that while all of them achieve good classification accuracy, relative performance, including ranging errors due to misclassification, depends heavily on channel and PHY configuration. Runtime and energy efficiency also vary dramatically; some techniques offer marginal accuracy gains while consuming up to 39.6x more energy. Therefore, we also introduce a recommender tool to identify optimal classifiers under user-defined constraints, publicly released with our dataset.
Figures & tables
| Parameter | pose | mobile |
|---|---|---|
| Tag positions | 4, fixed | many, variable |
| # of subjects | 2 | 3 |
| Environments | office , warehouse | |
| UWB channels | ch2 , ch4 , ch5 | |
| Radio optimizations | c los , c los 1024 , c nlos | |
| ID | Dataset | Gender | Height | Weight | BMI |
|---|---|---|---|---|---|
| 1 | pose | M | 1.84 m | 100 kg | 29.5 |
| 2 | M | 1.74 m | 70 kg | 23.1 | |
| 3 | mobile | F | 1.54 m | 52 kg | 21.9 |
| 4 | M | 1.69 m | 55 kg | 20.2 | |
| 5 | M | 1.90 m | 105 kg | 29.1 |
| LOS and WNLOS | LOS only | WNLOS only | |||||||||||
| Radio settings | Dataset | distance | error | ratio | distance | error | ratio | distance | error | ||||
| mean | mean | mean | |||||||||||
| (m) | (m) | (m) | (%) | (m) | (m) | (m) | (%) | (m) | (m) | (m) | |||
| c los | ch2 | pose | 4.88 | 1.57 | 9.47 | 58.3 | 4.84 | 0.17 | 0.34 | 41.7 | 4.94 | 4.91 | 10.54 |
| mobile | 4.32 | 0.53 | 5.91 | 57.9 | 4.29 | 0.21 | 0.45 | 42.1 | 4.36 | 1.40 | 8.85 | ||
| ch4 | pose | 4.88 | 1.05 | 7.01 | 58.3 | 4.84 | 0.15 | 0.35 | 41.7 | 4.94 | 3.92 | 9.37 | |
| Type | Short name | Description |
|---|---|---|
| LI | , , | LI whose value is normalized in ; values = 0.5 denote WNLOS, else LOS. |
| ML | , | ML approaches in ( Gallacher et al., 2023 ) and ( Angarano et al., 2021 ) , adapted to run on-device. They take as input a portion of the CIR around the first path. |
| Hybrid | , , | Same as , except this time the threshold is determined via . |
| trained by using and as features instead of the CIR. | ||
| \mathsf{{\color[rgb]{0,0,0}\mathsf{if}}_{\mathsf{PD,XGB}}} , \mathsf{{\color[rgb]{0,0,0}\mathsf{if}}_{\mathsf{PD,REM}}} , \mathsf{{\color[rgb]{0,0,0}\mathsf{if}}_{\mathsf{CL,XGB}}} , \mathsf{{\color[rgb]{0,0,0}\mathsf{if}}_{\mathsf{CL,REM}}} , \mathsf{{\color[rgb]{0,0,0}\mathsf{if}}_{\mathsf{CL^{*},XGB}}} , \mathsf{{\color[rgb]{0,0,0}\mathsf{if}}_{\mathsf{CL^{*},REM}}} | Conditional classifiers , composed of a LI- and ML-based classifier. If the former yields a high confidence value based on the manufacturer’s definition ( §2.2 ), this is used; else, the ML classifier is used. | |
| \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{PD,XGB}}} , \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{PD,REM}}} , \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{CL,XGB}}} , \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{CL,REM}}} , \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{CL^{*},XGB}}} , \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{CL^{*},REM}}} | Consensus classifiers , in which a link is classified as LOS only if both classifiers yield this output; otherwise, it is WNLOS. |
| Channel | Classifier | c los | c los 1024 | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| pose | mobile | pose | mobile | ||||||||||||||
| error | LOS | error | LOS | error | LOS | error | LOS | ||||||||||
| 0.5m | 1m | 0.5m | 1m | 0.5m | 1m | 0.5m | 1m | ||||||||||
| (%) | (%) | (m) | (%) | (%) | (%) | (m) | (%) | (%) | (%) | (m) | (%) | (%) | (%) | (m) | (%) | ||
| ch2 | \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{CL,REM}}} | 100.0 | 0.0 | 0.29 | 53.9 | 99.4 | 0.0 | 0.47 | 57.9 | 99.9 | 0.0 | 0.38 | 54.5 | 99.6 | 0.0 | 0.44 | 57.7 |
| \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{CL,XGB}}} | 100.0 | 0.0 | 0.29 | 54.2 | 99.3 | 0.0 | 0.47 | 58.2 | 99.9 | 0.0 | 0.38 | 54.5 | 99.5 | 0.0 | 0.44 | 58.5 | |
| Energy ( J) | 2.29 | 3.27 | 15.68 | 18.60 | 87.36 |
| Runtime ( s) | 140 | 200 | 900 | 917 | 3629 |
| (Q1) What is the accuracy of LI and ML classifiers under identical settings? How do they compare? |
|---|
| Both LI and ML classifiers exhibit high accuracy up to %, always % in pose and % in mobile . Their accuracy is comparable; relative differences depend on the classifiers compared but are always %. Among LI classifiers, generally has the highest accuracy, and generally outperforms . Among ML classifiers, always outperforms or performs similarly to it; moreover, it is the best choice across all classifiers in ch5 . ML classifiers generally outperform LI ones in pose , i.e., the dataset on which they are trained. However, their accuracy decreases in mobile , where LI are often preferable, confirming that ML classifiers are negatively affected by unseen environments. |
| (Q2) Are LI and ML classifiers complementary? If so, can they be integrated effectively? |
| Yes, combining LI and ML approaches can improve accuracy. Especially in ch2, ch4 | mobile , consensus classifiers involving and either ML achieve a higher accuracy than using any of the pure LI or ML classifiers in isolation. -inferred thresholds for LI ( ) and training on LI ( ) generally have negligible impact on accuracy. Conditional classifiers do not achieve higher accuracy, but help bridging the gap between pure LI and ML classifiers in pose at a fraction of the runtime and energy overhead of ML ones. |
| (Q3) Does the amount of body occlusion affect classification? |
| Yes: all classifiers experience the lowest accuracy ( – %) within a 30 ∘ transitional area around the angle chosen for labeling LOS/WNLOS. However, ranging errors in this area are small, cm on average, therefore misclassifications have a reduced impact. Instead, outside this area, when WNLOS detection matters the most as prominent occlusions cause very large ranging errors, all classifiers yield % accuracy. |
| (Q4) What is the ranging error of samples classified as LOS? |
| Radio settings | Accuracy % | Classification accuracy % and % for the other metric | |||||||||
| Energy consumption | Runtime | error (LOS) | |||||||||
| Classifier | Classifier | [%] | [ ] | Classifier | [%] | [ ] | Classifier | [%] | [cm] | ||
| ch2 | c los | \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{PD,REM}}} (93.10%) | \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{PD,XGB}}} | -0.20 | -69 (-21.82%) | \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{PD,XGB}}} | -0.20 | -2712 (-57.88%) | \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{PD,REM}}} | - | - |
| c los 1024 | \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{PD,REM}}} (92.54%) | \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{PD,XGB}}} | -0.34 | -69 (-7.27%) | \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{PD,XGB}}} | -0.34 | -2712 (-42.26%) | \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{PD,REM}}} | - | - | |
| ch4 | c los | \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{PD,REM}}} (92.65%) | \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{PD,XGB}}} | -0.37 | -69 (-21.82%) | \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{PD,XGB}}} | -0.37 | -2712 (-57.88%) | \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{PD,REM}}} | - | - |
| c los 1024 | \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{PD,REM}}} (93.01%) | \mathsf{{\color[rgb]{0,0,0}\mathsf{if}}_{\mathsf{PD,REM}}} | -0.50 | -79 (-8.38%) | \mathsf{{\color[rgb]{0,0,0}\mathsf{if}}_{\mathsf{PD,REM}}} | -0.50 | -3291 (-51.28%) | \mathsf{{\color[rgb]{0,0,0}\mathsf{\wedge}}_{\mathsf{PD,REM}}} | - | - | |
| Radio settings | Runtime % | Runtime % and % for the other metric | |||||||||
| Energy consumption | Classification accuracy | error (LOS) | |||||||||
| Classifier | Classifier | [ ] | [ ] | Classifier | [ ] | [%] | Classifier | [ ] | [cm] | ||
| ch2 | c los | / (996 µs) | \mathsf{{\color[rgb]{0,0,0}\mathsf{if}}_{\mathsf{CL^{*},XGB}}} | +16 (+1.59%) | +0.3 (+0.14%) | +60 (+6.02%) | +1.22 / +1.18 | \mathsf{{\color[rgb]{0,0,0}\mathsf{if}}_{\mathsf{PD,XGB}}} | +150 (+15.06%) | -1.7 / -2.2 (-3.27% / -4.26%) | |
| c los 1024 | / (2728 µs) | \mathsf{{\color[rgb]{0,0,0}\mathsf{if}}_{\mathsf{CL^{*},XGB}}} | +18 (+0.64%) | +0.4 (+0.04%) | +60 (+2.20%) | +1.22 / +1.10 | +60 (+2.20%) | -0.69 / -0.70 (-1.51% / -1.53%) | |||
| ch4 | c los | / (996 µs) | \mathsf{{\color[rgb]{0,0,0}\mathsf{if}}_{\mathsf{CL^{*},XGB}}} | +4 (+0.44%) | +0.1 (+0.04%) | +60 (+6.02%) | +1.54 / +1.63 | \mathsf{{\color[rgb]{0,0,0}\mathsf{if}}_{\mathsf{PD,REM}}} | +405 (+40.62%) | -0.6 / -0.7 (-1.43% / -1.54%) | |
| \mathsf{{\color[rgb]{0,0,0}\mathsf{if}}_{\mathsf{CL^{*},REM}}} | +17 (+1.73%) | +0.4 (+0.18%) | |||||||||
Wireless Communications
Wireless communications studies how information is sent over radio links and how networks manage signals, spectrum, and resources reliably.
See all 431 papers