Robust Indoor Localization using Wireless Signal Sensing and Data-driven Models
Keywords:
Deep learning, Fingerprinting, Indoor localization, Machine learning, Multi-floor localization, RMSE, RSSI, Wireless sensor networksAbstract
Accurate indoor localization remains a challenging problem due to multipath propagation, signal attenuation, and dynamic environmental changes that degrade the reliability of traditional positioning techniques. This research presents a robust indoor localization framework that leverages wireless signal sensing and data-driven models to achieve high positioning accuracy in complex indoor environments. The proposed approach utilizes widely available wireless signals, such as Wi-Fi and Bluetooth, and extracts discriminative features from received signal measurements to construct an adaptive localization model. Advanced data-driven techniques, including machine learning and deep learning algorithms, are employed to capture nonlinear relationships between signal characteristics and spatial locations, enabling improved resilience to noise and environmental variability. Experimental evaluations conducted in diverse indoor scenarios demonstrate that the proposed method significantly outperforms conventional fingerprinting and model-based approaches. Results indicate an average localization accuracy improvement of 20–35%, with sub-meter positioning precision achieved in dense deployment settings. Furthermore, the system exhibits strong robustness to signal fluctuations and layout changes, maintaining stable performance over time with minimal recalibration. These results highlight the effectiveness of combining wireless signal sensing with data-driven modelling for reliable and scalable indoor localization applications.
References
I. Ashraf, S. Hur, and Y. Park, “Recent advancements in indoor positioning and localization,” Electronics, vol. 11, no. 13, p. 2047, 2022.
S. Łukasik, S. Szott, and M. Leszczuk, “Multimodal image-based indoor localization with machine learning—A systematic review,” Sensors, vol. 24, no. 18, p. 6051, 2024.
B. S. Meena, “Indoor localization using signal-based techniques: A review of fingerprinting and radio-based hybrid systems,” International Journal of Applied Mathematics, vol. 38, no. 5, 2025.
D. Mao, H. Lin, and X. Lou, “Fingerprinting indoor positioning based on improved sequential deep learning,” Algorithms, vol. 18, no. 1, p. 17, 2025.
S. Martín-Frechina, E. Dura, I. Miralles, and J. Torres-Sospedra, “From fingerprinting to advanced machine learning: A systematic review of Wi-Fi and BLE-based indoor positioning systems,” Sensors, vol. 25, no. 22, p. 6946, 2025.
K. A. Kordi, M. Roslee, M. Y. Alias, A. Alhammadi, A. Waseem, and A. F. Osman, “Survey of indoor localization based on deep learning,” Computers, Materials and Continua, vol. 79, no. 2, pp. 3261–3298, 2024.
B. H. Lee, K. M. Park, Y. H. Kim, and S. C. Kim, “Hybrid approach for indoor localization using received signal strength of dual-band Wi-Fi,” Sensors, vol. 21, no. 16, p. 5583, Aug. 2021.
P. Y. Lajoie, B. H. Baghi, S. Herath, F. Hogan, X. Liu, and G. Dudek, “PEOPLEx: Pedestrian opportunistic positioning leveraging IMU, UWB, BLE and WiFi,” in Proc. IEEE Int. Conf. Communications (ICC), Jun. 2024, pp. 3518–3523.
M. Mohsen, H. Rizk, H. Yamaguchi, and M. Youssef, “TimeSense: Multiperson device-free indoor localization via RTT,” IEEE Internet of Things Journal, vol. 11, no. 24, pp. 39593–39605, Aug. 2024.
S. Limkar, W. V. Ashok, V. Wadne, S. K. Wagh, K. Wagh, and A. Kumar, “Energy-efficient localization techniques for wireless sensor networks in indoor IoT environments,” Journal of Electrical Systems, vol. 19, no. 2, Jun. 2023.
B. Gumaida and A. Ibrahim, “Metaheuristic optimization techniques for localization in outdoor wireless sensor networks: A comprehensive review,” International Journal of Innovative Computing, vol. 15, no. 1, 2025.
B. Zholamanov et al., “RSSI fingerprint-based indoor localization solutions using machine learning algorithms: A comprehensive review,” Smart Cities, vol. 8, no. 5, 2025.
Sonny A, Kumar A, Cenkeramaddi LR. A survey of application of machine learning in wireless indoor positioning systems. arXiv preprint arXiv:2403.04333. 2024 Mar 7.
M. W. P. Maduranga, “Improved indoor localization with machine learning techniques for IoT applications,” Ph.D. dissertation, IIC University of Technology, 2024.
A. Alitaleshi, H. Jazayeriy, and J. Kazemitabar, “EA-CNN: A smart indoor 3D positioning scheme based on Wi-Fi fingerprinting and deep learning,” Engineering Applications of Artificial Intelligence, vol. 117, p. 105509, 2023.
K. Chandawar and P. H., “Accurate indoor positioning using Wi-Fi signals and deep learning techniques,” in Proc. 2025 Third Int. Conf. Networks, Multimedia and Information Technology (NMITCON), 2025, pp. 1–6.
T. Mamede, N. Silva, E. R. B. Marques, and L. M. B. Lopes, “Machine learning models for indoor positioning using Bluetooth RSSI and video data: A case study,” Sensors, vol. 25, no. 21, p. 6640, 2025.
M. A. Elaoud and W. F. Hassen, “WiFi CSI/RSSI fingerprints positioning based on data augmentation technique,” in Proc. Seventeenth Int. Conf. Mobile Ubiquitous Computing, Systems, Services and Technologies, 2023.
Y. Yu, Y. Zhang, L. Chen, and R. Chen, “Intelligent fusion structure for Wi-Fi/BLE/QR/MEMS sensor-based indoor localization,” Remote Sensing, vol. 15, p. 1202, 2023.
S. Leitch, Q. Ahmed, W. Abbas, M. Hafeez, P. Lazaridis, P. Sureephong, and T. Alade, “On indoor localization using WiFi, BLE, UWB, and IMU technologies,” Sensors, vol. 23, 2023.
Z. Deng, H. Luo, X. Gao, and P. Liu, “Fusion-based localization system integrating UWB, IMU, and vision,” Applied Sciences, vol. 15, no. 12, 2025.
