Yüksek Yoğunluklu ve Çoklu Cihaz Ortamlarında Regresyon Tabanlı Koordinat Tahmini ile Wi-Fi İç Mekan Konumlandırmasının Performans Değerlendirmesi

Abstract

Günümüzde, kapalı bir alanda hareket eden nesnelerin konumunu belirlemek kritik bir ihtiyaç haline gelmiştir. Bu, hastanelerde hayati önem taşırken, müzelerde kültürel etkileşimi daha keyifli hale getirebilir. Hastaneler, alışveriş merkezleri, müzeler ve havaalanları dahil olmak üzere çeşitli kullanım senaryolarına hizmet eder. İnternetin ortaya çıkmasıyla birlikte, neredeyse her binada bulunan Wi-Fi erişim noktalarıyla konum tahmini en yaygın çözümlerden biri haline gelmiştir. Bu çalışma, Wi-Fi ve regresyon tabanlı yöntemlerin iç mekan konum problemlerindeki performansını incelemektedir. Gerçek bir test ortamında gerçekleştirilen deneylerde, XGBoost regresyonu hareketli nesnelerin konumlarını ortalama 1,4 m hata ile belirlemiştir. Ayrıca, test ortamındaki mobil cihazların donanım yapılarından kaynaklanan gürültülü sinyal ölçümlerinin konum sistemlerini nasıl etkileyebileceği incelenmiştir.

Keywords

• Kapalı alan konumlandırma
• Wi-Fi RSSI parmak izi
• Regresyon tabanlı konumlandırma

Performance Evaluation of Wi-Fi Indoor Positioning by Regression-Based Coordinate Estimation in High-Density and Multi-Device Environments

Abstract

Determining the location of moving objects in indoor environments has become a crucial requirement for many application domains. While this could be vital in hospitals, it can also enhance cultural interaction in environments such as museums. It serves a variety of usage scenarios for shopping malls, museums, and airports. Fingerprinting-based location estimation, thanks to the widespread availability of Wi-Fi access points found in nearly every building, has become one of the most common solutions for indoor positioning. This study examines the performance of Wi-Fi RSSI–based regression methods for indoor localization. Using the TUJI1 multi-device dataset, six different regression models were evaluated under Euclidean distance–based performance metrics. Among these models, XGBoost regression determined the locations of moving objects with an average positioning error of 2.07 m on the test dataset and 2.04 m during training, outperforming other linear and nonlinear regression approaches. In addition, we investigated how noisy signal measurements originating from the hardware structures of different mobile devices in the test environment affect localization systems. To analyze device heterogeneity, multiple experimental scenarios were designed, including device-specific and unified models. The findings show that tree-based ensemble models provide robust and competitive performance without requiring complex deep learning architectures.

Keywords

• Indoor positioning
• Wi-Fi RSSI fingerprinting
• Regression-based localization
• Device heterogeneity

Supporting Institution

This research received no external funding.

Ethical Statement

This study does not involve human or animal participants. All procedures followed scientific and ethical principles, and all referenced studies are appropriately cited.

Thanks

The author does not wish to acknowledge any individual or institution.

References

1. Almutiri, T. M., Alomar, K. H., & Alganmi, N. A. (2024). Integrating multi-omics using Bayesian ridge regression with iterative similarity bagging. Applied Sciences, 14(13), Article 5660. https://doi.org/10.3390/app14135660
2. Attar, H., Saber Ismail, W., Hafez, M., Bahaa, S., Deif, M. A., Khosravi, M., & Youssry, H. (2025). Machine learning indoor localization prediction using received signal strength indicator and Wi-Fi network. International Journal of Intelligent Networks, 6, 233–243. https://doi.org/10.1016/j.ijin.2025.10.001
3. Azghadi, S. A. R., Mih, A. N., Kawnine, A., Wachowicz, M., Palma, F., & Cao, H. (2024). An adaptive indoor localization approach using WiFi RSSI fingerprinting with SLAM-enabled robotic platform and deep neural networks. In Proceedings of the 34th International Conference on Collaborative Advances in Software and Computing (CASCON). IEEE. https://doi.org/10.1109/CASCON62161.2024.10838149
4. Bedoui, A., & Lazar, N. A. (2020). Bayesian empirical likelihood for ridge and lasso regressions. Computational Statistics & Data Analysis, 145, Article 106917. https://doi.org/10.1016/j.csda.2020.106917
5. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
6. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). https://doi.org/10.1145/2939672.2939785
7. Cover, T., & Hart, P. (1967). Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 13(1), 21–27. https://doi.org/10.1109/TIT.1967.1053964
8. Duong, T. H., Trinh, A. V., & Hoang, M. K. (2024). Efficient and accurate indoor positioning system: A hybrid approach integrating PCA, WKNN, and linear regression. Journal of Communications, 19(1), 37–43. https://doi.org/10.12720/jcm.19.1.37-43

9. Friedman, J. H., Hastie, T., & Tibshirani, R. (2010). Regularization paths for generalized linear models via coordinate descent. Journal of Statistical Software, 33(1), 1–22. https://doi.org/10.18637/jss.v033.i01
10. Hamayat, F., Abbasi, H. F., Sohail, M., & Ahmad, R. F. (2025). DAELocNet: An ai-enabled indoor localization for accurate positioning in modern buildings using wireless communication technologies. In Proceedings of the 2025 International Conference on Innovation in Artificial Intelligence and Internet of Things (AIIT) (pp. 1-7). IEEE. https://doi.org/10.1109/AIIT63112.2025.11082899
11. Hodson, T. O. (2022). Root mean square error (RMSE) or mean absolute error (MAE): When to use them or not. Geoscientific Model Development, 15(14), 5481–5487. https://doi.org/10.5194/gmd-15-5481-2022
12. Jang, B., Kim, H., & Kim, J. W. (2023). Survey of landmark-based indoor positioning technologies. Information Fusion, 89, 166–188. https://doi.org/10.1016/j.inffus.2022.08.013
13. King, T., Kopf, S., Haenselmann, T., Lubberger, C., & Effelsberg, W. (2008). CRAWDAD dataset mannheim/compass (v. 2008-04-11) [Data set]. CRAWDAD. https://doi.org/10.15783/c7js3p
14. Klus, L., Klus, R., Lohan, E. S., Nurmi, J., Granell, C., Valkama, M., Talvitie, J., Casteleyn, S., & Torres-Sospedra, J. (2024a). TUJI1 dataset: Multi-device dataset for indoor localization with high measurement density. Data in Brief, 54, Article 110356. https://doi.org/10.1016/j.dib.2024.110356
15. Klus, L., Klus, R., Torres-Sospedra, J., Lohan, E. S., Silva, I., Pendao, C., & Valkama, M. (2024b). Enabling dynamic indoor localization by employing intersection over union as a metric. In Proceedings of the 2024 IEEE 100th Vehicular Technology Conference (VTC2024-Fall) (pp. 1-7). IEEE. https://doi.org/10.1109/VTC2024-Fall63153.2024.10758013
16. Loh, W.-Y. (2014). Fifty years of classification and regression trees. International Statistical Review, 82(3), 329–348. https://doi.org/10.1111/insr.12016
17. Mendoza-Silva, G. M., Costa, A. C., Torres-Sospedra, J., Painho, M., & Huerta, J. (2021). Environment-aware regression for indoor localization based on WiFi fingerprinting. IEEE Sensors Journal, 22(6), 4978–4988. https://doi.org/10.1109/JSEN.2021.3073878
18. Mendoza-Silva, G. M., Richter, P., Torres-Sospedra, J., Lohan, E. S., & Huerta, J. (2018). Long-term WiFi fingerprinting dataset for research on robust indoor positioning. Data, 3(1), Article 3. https://doi.org/10.3390/data3010003
19. Obeidat, H., Shuaieb, W., Obeidat, O., & Abd-Alhameed, R. (2021). A review of indoor localization techniques and wireless technologies. Wireless Personal Communications, 119(1), 289–327. https://doi.org/10.1007/s11277-021-08209-5
20. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., VanderPlas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, É. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830.
21. Qin, F., Zuo, T., & Wang, X. (2021). CCpos: WiFi fingerprint indoor positioning system based on CDAE-CNN. Sensors, 21(4), Article 1114. https://doi.org/10.3390/s21041114
22. Saeed, M. T. M., Yousif, M. A. A., & Ozturk, I. (2025). Mitigating device heterogeneity for enhanced indoor positioning system performance using deep feature learning. IEEE Access, 13, 180203–180217. https://doi.org/10.1109/ACCESS.2025.3621505
23. Sheikholeslami, N., & Valaee, S. (2021). Learning K-nearest neighbour regression for noisy dataset with application in indoor localization. In Proceedings of the 2021 IEEE Global Communications Conference (GLOBECOM) (pp. 1–6). IEEE. https://doi.org/10.1109/GLOBECOM46510.2021.9685151
24. Singh, N., Choe, S., & Punmiya, R. (2021). Machine learning based indoor localization using Wi-Fi RSSI fingerprints: An overview. IEEE Access, 9, 127150–127174. https://doi.org/10.1109/ACCESS.2021.3111083
25. Sze, V., Chen, Y.-H., Yang, T.-J., & Emer, J. S. (2017). Efficient processing of deep neural networks: A tutorial and survey. Proceedings of the IEEE, 105(12), 2295–2329. https://doi.org/10.1109/JPROC.2017.2761740
26. Tilwari, V., Pack, S., Maduranga, M., & Lakmal, H. K. I. S. (2024). An improved Wi-Fi RSSI-based indoor localization approach using deep randomized neural network. IEEE Transactions on Vehicular Technology, 73(12), 18593–18604. https://doi.org/10.1109/TVT.2024.3437640
27. Torres-Sospedra, J., Montoliu, R., Martínez-Úso, A., Avariento, J. P., Arnau, T. J., Benedito-Bordonau, M., & Huerta, J. (2014). UJIIndoorLoc: A new multi-building and multi-floor database for WLAN fingerprint-based indoor localization problems. In Proceedings of the International Conference on Indoor Positioning and Indoor Navigation (IPIN) (pp. 261–270). IEEE. https://doi.org/10.1109/IPIN.2014.7275492
28. Turgut, Z. (2025). XDOcc: An explainable artificial intelligence empowered deep framework for occupancy detection and occupant count estimation. IEEE Access, 13, 175386–175409. https://doi.org/10.1109/ACCESS.2025.3619449
29. Ustebay, S., Turgut, Z., Durukan Odabaşı, Ş., Aydın, M. A., & Sertbaş, A. (2024). A machine learning approach based on indoor target positioning by using sensor data fusion and improved cosine similarity. Electrica, 24(1), 218–227. https://doi.org/10.5152/electrica.2023.23080
30. Ustebay, S., Turgut Akgün, Z., Turna, Ö. C., Aydın, M. A., & Berber Atmaca, T. (2019). Analysis of device-free and device-dependent signal filtering approaches for indoor localization based on Earth's magnetic field system. In Proceedings of the 1st International Workshop on Digital Content & Smart Multimedia (DCSMart 2019) (pp. 1–13).
31. Yaman, Ş., Gündoğdu, K., & Çalhan, A. (2021). A New Indoor Positioning System. Düzce University Journal of Science and Technology, 9(2), 636–645. https://doi.org/10.29130/dubited.747445
32. Zafari, F., Gkelias, A., & Leung, K. K. (2019). A survey of indoor localization systems and technologies. IEEE Communications Surveys & Tutorials, 21(3), 2568–2599. https://doi.org/10.1109/COMST.2019.2911558
33. Zou, H., & Hastie, T. (2005). Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society: Series B: Statistical Methodology, 67(2), 301–320. https://doi.org/10.1111/j.1467-9868.2005.00503.x