LPWAN Localization via RSSI/SNR Fingerprinting and Lightweight Machine Learning
DOI:
https://doi.org/10.4108/eetiot.10888Keywords:
LPWAN, LoRA, Localization, Fingerprinting, RSSI, SNR, IoT, Machine LearningAbstract
Accurate geolocation for low-power wide-area (LPWAN) devices is desirable when GNSS is unavailable or too energy-expensive, yet RSSI-/TDoA-based approaches are often fragile under channel variability, collisions and cross-device heterogeneity. We address this gap with a reproducible, tabular pipeline that maps LoRa RSSI/SNR/ToA and PHY metadata to 2D positions, compares strong tabular baselines (k-NN, Random Forest, LightGBM, XGBoost), and crucially evaluates them under group-aware (device-wise) splits to avoid identity leakage. On an ns-3-generated LoRa dataset of about 3.3 × 104 labeled receptions, Random Forest attains the tightest distribution with p50 ≈ 0 m and p95 < 1 m, whereas k-NN, despite a low median, exhibits a much heavier tail (p95 ≈ 187 m), underscoring the need to report both central and tail metrics. These results indicate that simple, edge-feasible models can perform gateway-side inference with robust accuracy when fed cleaned features and evaluated with realistic splits, making the approach attractive for practical LPWAN/IoT deployments.
Downloads
References
[1] F. Zafari, A. Gkelias, and K. K. Leung. “A Survey of Indoor Localization Systems and Technologies”. In: IEEE Communications Surveys & Tutorials 21.3 (2017), pages 2568– 2599. issn: 2373-745X. doi: 10.1109/comst.2019.2911558.
[2] A. Nessa, B. Adhikari, F. Hussain, and X. N. Fernando. “A Survey of Machine Learning for Indoor Positioning”. In: IEEE Access 8 (2020), pages 214945–214965. issn: 2169-3536. doi: 10.1109/access.2020.3039271.
[3] Z. Farid, R. Nordin, and M. Ismail. “Recent Advances in Wireless Indoor Localization Techniques and System”. In: Journal of Computer Networks and Communications 2013 (2013), pages 1–12. issn: 2090-715X. doi: 10.1155/2013/185138.
[4] E. Svertoka, A. Rusu-Casandra, R. Burget, I. Marghescu, J. Hosek, and A. Ometov. “LoRaWAN: Lost for Localization?” In: IEEE Sensors Journal 22.23 (Dec. 2022), pages 23307–23319. issn: 2379-9153. doi: 10.1109/jsen.2022.3212319.
[5] K. Lam, C. Cheung, and W. Lee. “RSSI-Based LoRa Localization Systems for Large-Scale Indoor and Outdoor Environments”. In: IEEE Trans. Veh. Technol. 68.12 (2019), pages 11778–11791. doi: 10.1109/TVT.2019.2940272.
[6] H. Kwasme and S. Ekin. “RSSI-Based Localization Using LoRaWAN Technology”. In: IEEE Access 7 (2019), pages 99856– 99866. doi: 10.1109/ACCESS.2019.2929212.
[7] K. Whitehouse, C. Karlof, and D. Culler. “A practical evaluation of radio signal strength for ranging-based localization”. In: ACM SIGMOBILE Mobile Computing and Communications Review 11.1 (Jan. 2007), pages 41–52. issn: 1931-1222. doi: 10. 1145/1234822.1234829.
[8] S. Sadowski and P. Spachos. “RSSI-Based Indoor Localization With the Internet of Things”. In: IEEE access 6 (2018), pages 30149–30161. issn: 2169-3536. doi: 10.1109/access. 2018.2843325.
[9] T. Yang, A. Cabani, and H. Chafouk. “A survey of recent indoor localization scenarios and methodologies”. In: Sensors 21.23 (Dec. 2021), page 8086. issn: 1424-8220. doi: 10.3390/ s21238086.
[10] A. A. Ghany, B. Uguen, and D. Lemur. “A Parametric TDoA Technique in the IoT Localization Context”. In: 2019 16th Workshop on Positioning, Navigation and Communications (WPNC). IEEE, Oct. 2019, pages 1–6. doi: 10 . 1109 / wpnc47567.2019.8970254.
[11] E. H. Yoshitome, J. V. R. da Cruz, M. E. P. Monteiro, and J. L. Rebelatto. “LoRa-aided outdoor localization system: RSSI or TDoA?” In: Internet Technol. Lett. 5.2 (2022). doi: 10.1002/ ITL2.319.
[12] S.-H. Lee, C.-H. Cheng, T.-H. Huang, and Y.-F. Huang. “Machine Learning-based Indoor Positioning Systems Using Multi-Channel Information”. In: Journal of Engineering and Technological Sciences 55.4 (Oct. 2023), pages 373–383. issn: 2337-5779. doi: 10.5614/j.eng.technol.sci.2023.55.4.2.
[13] T. Perković , L. Dujić Rodić, J. Šabić , and P. Šolić . “Machine Learning Approach towards LoRaWAN Indoor Localization”. In: Electronics 12.2 (Jan. 2023), page 457. issn: 2079-9292. doi: 10.3390/electronics12020457.
[14] H. Vo, V. H. L. Nguyen, V. L. Tran, F. Ferrero, F. Lee, and M. Tsai. “Advance Path Loss Model for Distance Estimation Using LoRaWAN Network’s Received Signal Strength Indicator (RSSI)”. In: IEEE Access 12 (2024), pages 83205–83216. doi: 10. 1109/ACCESS.2024.3412849.
[15] A. Haghighat, Z. Sirous, A. Moradbeikie, A. Keshavarz, and S. I. Lopes. “Improving LoRaWAN Fingerprint-Based Localization by Detecting and Eliminating Noisy RSSI Measurements”. In: 9th IEEE World Forum on Internet of Things, WF-IoT 2023, Aveiro, Portugal, October 12-27, 2023. IEEE, 2023, pages 1–7. doi: 10.1109/WF-IOT58464.2023.10539415.
[16] A. S. Lutakamale, H. C. Myburgh, and A. D. Freitas. “RSSIbased fingerprint localization in LoRaWAN networks using CNNs with squeeze and excitation blocks”. In: Ad Hoc Networks 159 (2024), page 103486. doi: 10.1016/J.ADHOC.2024.103486.
[17] O. G. Serbetci, D. Burghal, and A. F. Molisch. “Wireless Channel Aware Data Augmentation Methods for Deep Learning-Based Indoor Localization”. In: (2024). doi: 10 . 48550/arXiv.2408.06452.
[18] IEEE DataPort. Indoor Localization Data based on SNR and RSSI within Multistory Round Building Scenario. year.
[19] A. Achroufene. “RSSI-based Hybrid Centroid-K-Nearest Neighbors localization method”. In: Telecommunication Systems 82.1 (Nov. 2022), pages 101–114. issn: 1572-9451. doi: 10.1007/s11235-022-00977-0.
[20] K. Ibwe, S. Pande, A. T. Abdalla, and G. M. Gadiel. “Indoor positioning using circle expansion-based adaptive trilateration algorithm”. In: Journal of Electrical Systems and Information Technology 10.1 (Feb. 2023). issn: 2314-7172. doi: 10 . 1186 / s43067-023-00075-4.
[21] M. Simka and L. Polak. “On the RSSI-Based Indoor Localization Employing LoRa in the 2.4 GHz ISM Band”. In: Radioengineering 31.1 (2022), pages 135–143. doi: 10.13164/ re.2022.0135.
[22] J. A. Micheletti, E. P. Godoy, and R. T. Lopes. “Improved Indoor 3D Localization Using LoRa Wireless Communication”. In: IEEE Latin America Transactions 20.9 (2022), pages 1476–1483. doi: 10.1109/TLA.2022.1234567.+ S. Mazuelas, A. Bahillo, R. M. Lorenzo, P. Fernandez, F. A. Lago, E. Garcia, J. Blas, and E. J. Abril. “Robust Indoor Positioning Provided by Real-Time RSSI Values in Unmodified WLAN Networks”. In: IEEE Journal of Selected Topics in Signal Processing 3.5 (Oct. 2009), pages 821–831. issn: 1932-4553. doi: 10.1109/jstsp.2009.2029191.
[24] Y. Lin, C. Sun, and K. Huang. “RSSI Measurement with Channel Model Estimating for IoT Wide Range Localization using LoRa Communication”. In: 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019, Taipei, Taiwan, December 3-6, 2019. IEEE, 2019, pages 1–2. doi: 10.1109/ISPACS48206.2019.8986229.
[25] R. Muppala. “Feasibility of GNSS-free Localization: A TDoAbased Approach Using LoRaWAN”. In: (2021).
[26] K. Wu, J. Xiao, Y. Yi, D. Chen, X. Luo, and L. M. Ni. “CSIBased Indoor Localization”. In: IEEE Transactions on Parallel and Distributed Systems 24.7 (July 2013), pages 1300–1309. issn: 1045-9219. doi: 10.1109/tpds.2012.214.
[27] A. Aksoy, O. Yildiz, and S. E. Karlik. “Comparative Analysis of End Device and Field Test Device Measurements for RSSI, SNR and SF Performance Parameters in an Indoor LoRaWAN Network”. In: Wirel. Pers. Commun. 134.1 (2024), pages 339– 360. doi: 10.1007/S11277-024-10911-Z.
[28] E. Goldoni, L. Prando, A. Vizziello, P. Savazzi, and P. Gamba. “Experimental data set analysis of RSSI-based indoor and outdoor localization in LoRa networks”. In: Internet Technology Letters 2.1 (Oct. 2018), e75. doi: 10.1002/itl2.75.
[29] J. Spišić, A. Pejković, M. Zrnić, V. Križanović, K. Grgić and D. Žagar, “LoRaWAN Parameters Optimization For E cient Communication”. In: 2022 International Confer-ence on Smart Systems and Technologies (SST). IEEE, Oct. 2022, pages 335– 339. doi: 10.1109/sst55530.2022.9954704.
[30] W. Shin, Y. Lee, J. Cho, J. Jang, Y. Seo, and S. Kahng. “RSSI Improved for LoRa Wireless Communication, Field-Tested in the Wide-Open Area”. In: IEEE Access 11 (2023), pages 80172– 80180. doi: 10.1109/ACCESS.2023.3241485.
[31] Z. Shen, T. Zhang, A. Tagami, and J. Jin. “When RSSI encounters deep learning: An area localization scheme for pervasive sensing systems”. In: Journal of Network and Computer Applications 173 (Jan. 2021), page 102852. issn: 1084-8045. doi: 10.1016/j.jnca.2020.102852.
[32] W. Ingabire, H. Larijani, and R. M. Gibson. “LoRa RSSI Based Outdoor Localization in an Urban Area Using Random Neural Networks”. In: Intelligent Computing. Springer International Publishing, 2021, pages 1032–1043. isbn: 9783030801267. doi: 10.1007/978-3-030-80126-7_72.
[33] H. S. Fahama, K. Ansari-Asl, Y. S. Kavian, and M. N. Soorki. “An Experimental Comparison of RSSI-Based Indoor Localization Techniques Using ZigBee Technology”. In: IEEE Access 11 (2023), pages 87985–87996. issn: 2169-3536. doi: 10. 1109/access.2023.3305396.
[34] H. Vo, V. Hoang Long Nguyen, V. L. Tran, F. Ferrero, F.-Y. Lee, and M.-H. Tsai. “Advance Path Loss Model for Distance Estimation Using LoRaWAN Network’s Received Signal Strength Indicator (RSSI)”. In: IEEE Access 12 (2024), pages 83205–83216. issn: 2169-3536. doi: 10.1109/access. 2024.3412849.
[35] S.-H. Lee, C.-H. Cheng, K.-H. Lu, Y.-L. Shiue, and Y.-F. Huang. “A K-NN based Area Positioning System in Wireless Sensor Networks”. In: 2023 12th International Conference on Awareness Science and Technology (iCAST). IEEE, Nov. 2023, pages 46–49. doi: 10.1109/icast57874.2023.10359293.
[36] I. S. Mohamad Hashim, A. Al-Hourani, and W. S. T. Rowe. “Machine Learning Performance for Radio Localization under Correlated Shadowing”. In: 2020 14th International Conference on Signal Processing and Communication Systems (ICSPCS). Volume 1. IEEE, Dec. 2020, pages 1–7. doi: 10 . 1109 / icspcs50536.2020.9310009.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Désiré Guel, Flavien Hervé Somda, P. Justin Kouraogo, Boureima Zerbo, Oumarou Sié
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
