Improving buried object localization accuracy in heterogeneous environments using TOA-based IR-UWB and machine learning
40 viewsDOI:
https://doi.org/10.54939/1859-1043.j.mst.113.2026.3-11Keywords:
IR-UWB technology; Ground penetrating radar; TOA; Random Forest; XGBoost; LGBM.Abstract
This paper proposes a buried-object localization method in heterogeneous environments using time of arrival (TOA)-based IR-UWB radar and machine learning techniques. A propagation model is developed to generate a TOA dataset for buried-object locations under multipath and noisy conditions. To improve TOA estimation, a matched-filtering and adaptive-thresholding (MFAT) technique is proposed to enhance reflected pulse detection at low SNR. The extracted TOA features are then used to train Random Forest (RF), XGBoost, and LightGBM (LGBM) models for object localization. Experimental results show that the proposed LGBM-MFAT approach achieves the best performance, with an MAE of 1.26 cm, an RMSE of 2.37 cm, and an R2 value of 0.999. The results demonstrate that combining adaptive TOA processing with gradient-boosting models significantly improves localization accuracy and provides an effective solution for penetrating IR-UWB radar systems operating in heterogeneous environments.
References
REFERENCES
[1]. Groves, P. “Principles of GNSS, Inertial, and Multisensor Integrated Navigation Systems”. 2nd ed.; Artech House: Boston, MA, USA, (2013).
[2]. Li, M.-G.; Zhu, H.; You, S.-Z.; Tang, C.-Q. “UWB-Based Localization System Aided With Inertial Sensor for Underground Coal Mine Applications”. IEEE Sens. J., vol. 20, pp. 6652–6669, (2020). DOI: https://doi.org/10.1109/JSEN.2020.2976097
[3]. Al-Okby, Mohammed Faeik Ruzaij, et al. “UWB-based real-time indoor positioning systems: A comprehensive review”. Applied Sciences, vol. 14, no. 23, 11005, (2024). DOI: https://doi.org/10.3390/app142311005
[4]. Kia, Ghazaleh, Laura Ruotsalainen, and Jukka Talvitie. “Toward accurate indoor positioning: An RSS-based fusion of UWB and machine-learning-enhanced WiFi”. Sensors, vol. 22, no. 9, (2022). DOI: https://doi.org/10.3390/s22093204
[5]. Ma, Weimin, et al. “Research on indoor positioning system algorithm based on UWB technology”. Measurement: Sensors, vol. 33, 101121, (2024). DOI: https://doi.org/10.1016/j.measen.2024.101121
[6]. Kocur, et al. “Through-the-wall localization of a moving target by two independent ultra wideband (UWB) radar systems”. Sensors, vol. 13, no. 9, pp. 11969-11997, (2013). DOI: https://doi.org/10.3390/s130911969
[7]. Ouadfeul, et al. “Multiscale analysis of 3D GPR data using the continuous wavelet transform”. Proceedings of the XIII International Conference on Ground Penetrating Radar, Lecce, Italy, 21–25 June 2010. DOI: https://doi.org/10.1109/ICGPR.2010.5550177
[8]. Hart, P.E. “How the Hough transform was invented”. IEEE Signal Process. Mag., vol. 26, pp. 18–22, (2009). DOI: https://doi.org/10.1109/MSP.2009.934181
[9]. Dumin, O.; Plakhtii, V.; Pryshchenko, O.; Pochanin, G. “Comparison of ANN and Cross-Correlation Approaches for Ultra Short Pulse Subsurface Survey”. Proceedings of the 15th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET), Lviv-Slavske, Ukraine, pp. 381–386, (2020). DOI: https://doi.org/10.1109/TCSET49122.2020.235459
[10]. Huyen, N. T., Ha, D. D., & Hiep, P. T. “Buried objects detection in heterogeneous environment using UWB systems combined with curve fitting method”. ICT Express, vol. 6, no. 4, pp. 348-352, (2020). DOI: https://doi.org/10.1016/j.icte.2020.06.006
[11]. Rathnayake, R. M. M. R., et al. “RSSI and machine learning-based indoor localization systems for smart cities”. Eng, vol. 4, no. 2, pp. 1468-1494, (2023). DOI: https://doi.org/10.3390/eng4020085
[12]. Díez-González, Javier, et al. “Time-based UWB localization architectures analysis for UAVs positioning in industry”. Ad Hoc Networks, vol. 157, 103419, (2024). DOI: https://doi.org/10.1016/j.adhoc.2024.103419
[13]. Zhang, Y., Wang, H., Liu, J., et al. “Deep learning-enhanced UWB localization in complex environments: A survey”. IEEE Access, vol. 13, pp. 12543–12568, (2025).
[14]. Kim, S., Lee, J., and Park, H. “Hybrid UWB positioning using machine learning for GNSS-denied environments”. Sensors, vol. 25, no. 4, Art. no. 1187, (2025). DOI: https://doi.org/10.3390/s25247569
[15]. Wang, H.; Liu, Q.; Zhou, L. “Underground target localization method for ground penetrating radar based on deep learning”. Measurement, vol. 253, Art. no. 117647, (2025). DOI: https://doi.org/10.1016/j.measurement.2025.117647
[16]. Thien, Nguyen Thanh, et al. “Broadband signal source localization using convolutional neural networks combined with coherent signal subspace methods”. Journal of Military Science and Technology IITE, pp. 115-122, (2025). DOI: https://doi.org/10.54939/1859-1043.j.mst.IITE.2025.115-122
[17]. Saad, Mohamed, et al. “Development of an IR-UWB radar system for high-resolution through-wall imaging”. Prog. Electromagn. Res. C, vol. 124, pp. 81-96, (2022). DOI: https://doi.org/10.2528/PIERC22060206
[18]. X. Chen and S. Kiaei. “Monocycle shapes for ultra wideband system”. 2002 IEEE International Symposium on Circuits and Systems. Proceedings (Cat. No. 02CH37353), vol. 1, (2002).
[19]. Gavin, Henri P. “The Levenberg-Marquardt algorithm for nonlinear least squares curve-fitting problems”. Department of Civil and Environmental Engineering Duke University, (2019).
[20]. Li, Jingxia and Guo, Tian and Leung, Henry and Xu, Hang and Liu, Li and Wang, Bingjie and Liu, Yang. “Locating Underground pipe using wideband chaotic ground penetrating radar”. Sensors, Multidisciplinary Digital Publishing Institute, vol. 19, no. 13, p. 2913, (2019). DOI: https://doi.org/10.3390/s19132913
[21]. Qiao, Lihong and Qin, Yao and Ren, Xiaozhen and Wang, Qifu. “Identification of buried objects in GPR using amplitude modulated signals extracted from multiresolution monogenic signal analysis”. Multidisciplinary Digital Publishing Institute, Sensors, vol. 15, no. 12, pp. 30340–30350, (2015). DOI: https://doi.org/10.3390/s151229801
