Advanced search
2 files | 6.63 MB Add to list

Transfer learning for UWB error correction and (N)LOS classification in multiple environments

(2024) IEEE INTERNET OF THINGS JOURNAL. 11(3). p.4085-4101
Author
Organization
Project
Abstract
Ultra wideband (UWB) is a popular technology to address the need for high-precision indoor positioning systems in challenging industry 4.0 use cases. In line-of-sight (LOS) environments, UWB positioning errors in the order of 1-10 cm can be achieved. However, in non-line-of-sight (NLOS) conditions, this precision drops significantly, with errors typically >30 cm. Machine learning (ML) has been proposed to improve the precision in such NLOS conditions, but is typically environment-specific and lacks generalization to new environments and UWB configurations. As such, it is necessary to collect large data sets to train a neural network (NN) for each new environment or UWB configuration. To remedy this, this article proposes automatic optimizations for transfer learning (TL) deep NNs toward new environments and UWB configurations. We analyze error correction and (N)LOS classification models, using either feature- or channel impulse response (CIR)-based input data. Our TL solutions show a 50% error improvement and 15% (N)LOS classification accuracy improvement (for both feature- and CIR-based approaches) compared to a model trained in a different environment. We also analyze the impact on TL using a limited number of samples (25 to 400 samples). The highest accuracy is typically achieved by the CIR-based approach, where with only 50 samples from the new mixed (N)LOS environment, we show +/- 10 cm precision after error correction with 93% (N)LOS detection. The presented results demonstrate high-precision UWB localization (from 643 to 245 mm) through ML with minimal data collection effort in challenging NLOS environments.
Keywords
Error correction, Feature extraction, Artificial neural networks, Training, IP networks, Transfer learning, Internet of Things, localization systems, (N)LOS classification, transfer learning (TL), ultra wideband (UWB), IDENTIFICATION, LOCALIZATION, MITIGATION

Downloads

  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 4.67 MB
  • 8477 acc.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 1.97 MB

Citation

Please use this url to cite or link to this publication:

MLA
Fontaine, Jaron, et al. “Transfer Learning for UWB Error Correction and (N)LOS Classification in Multiple Environments.” IEEE INTERNET OF THINGS JOURNAL, vol. 11, no. 3, 2024, pp. 4085–101, doi:10.1109/JIOT.2023.3299319.
APA
Fontaine, J., Che, F., Shahid, A., Van Herbruggen, B., Ahmed, Q. Z., Bin Abbas, W., & De Poorter, E. (2024). Transfer learning for UWB error correction and (N)LOS classification in multiple environments. IEEE INTERNET OF THINGS JOURNAL, 11(3), 4085–4101. https://doi.org/10.1109/JIOT.2023.3299319
Chicago author-date
Fontaine, Jaron, Fuhu Che, Adnan Shahid, Ben Van Herbruggen, Qasim Zeeshan Ahmed, Waqas Bin Abbas, and Eli De Poorter. 2024. “Transfer Learning for UWB Error Correction and (N)LOS Classification in Multiple Environments.” IEEE INTERNET OF THINGS JOURNAL 11 (3): 4085–4101. https://doi.org/10.1109/JIOT.2023.3299319.
Chicago author-date (all authors)
Fontaine, Jaron, Fuhu Che, Adnan Shahid, Ben Van Herbruggen, Qasim Zeeshan Ahmed, Waqas Bin Abbas, and Eli De Poorter. 2024. “Transfer Learning for UWB Error Correction and (N)LOS Classification in Multiple Environments.” IEEE INTERNET OF THINGS JOURNAL 11 (3): 4085–4101. doi:10.1109/JIOT.2023.3299319.
Vancouver
1.
Fontaine J, Che F, Shahid A, Van Herbruggen B, Ahmed QZ, Bin Abbas W, et al. Transfer learning for UWB error correction and (N)LOS classification in multiple environments. IEEE INTERNET OF THINGS JOURNAL. 2024;11(3):4085–101.
IEEE
[1]
J. Fontaine et al., “Transfer learning for UWB error correction and (N)LOS classification in multiple environments,” IEEE INTERNET OF THINGS JOURNAL, vol. 11, no. 3, pp. 4085–4101, 2024.
@article{01HVGFVZGWHSRJNN1RJVW2Y5MC,
  abstract     = {{Ultra wideband (UWB) is a popular technology to address the need for high-precision indoor positioning systems in challenging industry 4.0 use cases. In line-of-sight (LOS) environments, UWB positioning errors in the order of 1-10 cm can be achieved. However, in non-line-of-sight (NLOS) conditions, this precision drops significantly, with errors typically >30 cm. Machine learning (ML) has been proposed to improve the precision in such NLOS conditions, but is typically environment-specific and lacks generalization to new environments and UWB configurations. As such, it is necessary to collect large data sets to train a neural network (NN) for each new environment or UWB configuration. To remedy this, this article proposes automatic optimizations for transfer learning (TL) deep NNs toward new environments and UWB configurations. We analyze error correction and (N)LOS classification models, using either feature- or channel impulse response (CIR)-based input data. Our TL solutions show a 50% error improvement and 15% (N)LOS classification accuracy improvement (for both feature- and CIR-based approaches) compared to a model trained in a different environment. We also analyze the impact on TL using a limited number of samples (25 to 400 samples). The highest accuracy is typically achieved by the CIR-based approach, where with only 50 samples from the new mixed (N)LOS environment, we show +/- 10 cm precision after error correction with 93% (N)LOS detection. The presented results demonstrate high-precision UWB localization (from 643 to 245 mm) through ML with minimal data collection effort in challenging NLOS environments.}},
  author       = {{Fontaine, Jaron and Che, Fuhu and Shahid, Adnan and Van Herbruggen, Ben and Ahmed, Qasim Zeeshan and Bin Abbas, Waqas and De Poorter, Eli}},
  issn         = {{2327-4662}},
  journal      = {{IEEE INTERNET OF THINGS JOURNAL}},
  keywords     = {{Error correction,Feature extraction,Artificial neural networks,Training,IP networks,Transfer learning,Internet of Things,localization systems,(N)LOS classification,transfer learning (TL),ultra wideband (UWB),IDENTIFICATION,LOCALIZATION,MITIGATION}},
  language     = {{eng}},
  number       = {{3}},
  pages        = {{4085--4101}},
  title        = {{Transfer learning for UWB error correction and (N)LOS classification in multiple environments}},
  url          = {{http://doi.org/10.1109/JIOT.2023.3299319}},
  volume       = {{11}},
  year         = {{2024}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: