A hierarchical positioning model for WiFi-based indoor localization in large-scale complex environments

Abstract

In developing Wi-Fi indoor positioning systems for large-scale complex environments, the fundamental challenge lies in the significant impact of signal noise on high-frequency data volatility, which substantially degrades positioning accuracy. To address this limitation, we propose an improved hierarchical positioning model combining a Gaussian mixture model (GMM) regional classifier with random forest secondary classifiers. During the offline phase, recognizing that Wi-Fi signal strength typically follows Gaussian distributions, we employed GMM to partition the target area into non-overlapping sub-regions with similar signal strength characteristics. For each sub-region, we then trained dedicated random forest classifiers. In the online phase, the system first identifies the probable sub-region using the GMM classifier before applying the corresponding random forest classifier for precise location estimation. We evaluated our approach in an indoor parking lot featuring an irregular layout, numerous solid walls, scattered access point distribution, and intermittent electromagnetic interference. Experimental results demonstrated that our hierarchical model delivers satisfactory performance for indoor location-based services in such challenging large-scale environments.

Keywords

Wi-Fi indoor positioning / hierarchical positioning model / enhance real application

References

[1] Wang Y,Gong W.Survey of deep learning applications in WiFi localization. In 2024 IEEE 7th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Chongqing, China. Mar 15-17, 2024. IEEE; 2024. pp. 517-22.

[2] Aziz T.A comprehensive review of indoor localization techniques and applications in various sectors.Appl Sci2025;15:1544

[3] Bock Y.Physical applications of GPS geodesy: a review.Rep Prog Phys2016;79:106801

[4] Qi H,Zhang Y,Liu X.Multi-scale sensing network for WIFI indoor localization. In 2023 IEEE 23rd International Conference on Communication Technology (ICCT), Wuxi, China. Oct 20-22, 2023. IEEE; 2023. pp. 1087-92.

[5] Rizk H,Ghazal A.Indoor localization system for seamless tracking across buildings and network configurations. In GLOBECOM 2023 - 2023 IEEE Global Communications Conference, Kuala Lumpur, Malaysia. Dec 04-08, 2023. IEEE; 2023. pp. 776-82.

[6] Li Y,Zheng C.Development and field deployment of a mid-infrared CO and CO₂ dual-gas sensor system for early fire detection and location.Spectrochim Acta A Mol Biomol Spectrosc2022;270:120834

[7] García Marquez, F. P.; Gómez Muñoz, C. Q. A new approach for fault detection, location and diagnosis by ultrasonic testing.Energies2020;13:1192

[8] Hao L,Jia B,Mao G.Toward accurate crowd counting in large surveillance areas based on passive WiFi sensing.IEEE Trans Intell Transport Syst2023;24:14086-96

[9] Shi F,Tang C,Brennan PV.Decimeter-level indoor localization using WiFi round-trip phase and factor graph optimization.IEEE J Select Areas Commun2024;42:177-91

[10] Bandini G,Tellini B.ORBITER: phase-based localization of RFID tags via circular antenna trajectory.IEEE Trans Instrum Meas2024;73:1-10

[11] Kandula H,Cao Y.Localization of a BLE device based on single-device RSSI and DOA measurements.Network2024;4:196-216

[12] Yao Z,Zhang Y,Luo M.Minimizing long-term energy consumption in RIS-assisted AAV-enabled MEC network.IEEE Internet Things J2025;12:20942-58

[13] Wang Z,Yan Y,Zhang B.Privacy-preserving WiFi localization based on inner product encryption in a cloud environment.IEEE Internet Things J2024;11:17264-82

[14] Zekavat S,Durgin GD.An overview on position location: past, present, future.Int J Wireless Inf Networks2021;28:45-76

[15] Zhang S,Wang W.Floor recognition based on SVM for WiFi indoor positioning. In China Satellite Navigation Conference (CSNC) 2018 Proceedings; Sun, J.; Yang, C.; Guo, S.; Eds.; Springer; 2018; Vol. 499, pp. 725-35.

[16] Lukito Y.Recurrent neural networks model for WiFi-based indoor positioning system. In 2017 International Conference on Smart Cities, Automation & Intelligent Computing Systems (ICON-SONICS), Yogyakarta, Indonesia. Nov 08-10, 2017. IEEE; 2017. pp. 121-5.

[17] Zhang W,Yu K,Zhang S.A novel WiFi indoor positioning strategy based on weighted squared Euclidean distance and local principal gradient direction.Sens Rev2019;39:99-106

[18] Li J,Cai YZ,Automation DO.Method of WiFi indoor location based on K-means and random forest.Control Eng China2017;

[19] Biswas J, Veloso M. WiFi localization and navigation for autonomous indoor mobile robots. In 2010 IEEE International Conference on Robotics and Automation, Anchorage, USA. May 03-07, 2010. IEEE; 2010. pp. 4379-84.

[20] Ahmad U,Lee Y.Context-aware, self-scaling Fuzzy ArtMap for received signal strength based location systems.Soft Comput2008;12:699-713

[21] Wu H,Miao Y.The propagation characteristics of radio frequency signals for wireless sensor networks in large-scale farmland.Wireless Pers Commun2017;95:3653-70

[22] Katircioğlu O,Ceylan O,Yagci HB.Comparing ray tracing, free space path loss and logarithmic distance path loss models in success of indoor localization with RSSI. In 2011 19thTelecommunications Forum (TELFOR) Proceedings of Papers, Belgrade, Serbia. Nov 22-24, 2011. IEEE; 2011. pp. 313-6.

[23] Kim SM,Oechtering TJ.On the entropy computation of large complex gaussian mixture distributions.IEEE Trans Signal Process2015;63:4710-23

[24] Vu TK,Le HL.An EM algorithm for GMM parameter estimation in the presence of censored and dropped data with potential application for indoor positioning.ICT Express2019;5:120-3

[25] Lau HY,Wong PL.A new design of smart journal bearing based on GMM actuators.Ind Lubr Tribol2012;64:147-51

[26] Kulkarni VY,Petare MC.Weighted hybrid decision tree model for random forest classifier.J Inst Eng India Ser B2016;97:209-17

[27] Tabatabaee Malazi, H.; Davari, M. Combining emerging patterns with random forest for complex activity recognition in smart homes.Appl Intell2018;48:315-30

[28] Dong Y,Zhang L.Target detection based on random forest metric learning.IEEE J Sel Top Appl Earth Obs Remote Sens2015;8:1830-8

[29] Lu C,Wang W.Making up the shortages of the Bayes classifier by the maximum mutual information classifier.J Eng2020;2020:659-63

[30] Gong W.SiFi: pushing the limit of time-based WiFi localization using a single commodity access point.Proc ACM Interact Mob Wearable Ubiquitous Technol2018;2:1-21

[31] Li T,Rezvani R,Abari O.Bringing wifi localization to any wifi devices. In Proceedings of the 21st ACM Workshop on Hot Topics in Networks. Association for Computing Machinery; 2022. pp. 46-52.