Abstract

Indoor localization has become a critical component of modern smart environments, where traditional GPS technologies fail to provide reliable positioning. Among various techniques, Wi-Fi-based localization using Received Signal Strength Indicator (RSSI) has gained significant popularity due to its low cost and widespread infrastructure support. In recent years, machine learning (ML) algorithms have been increasingly applied to enhance the accuracy and adaptability of RSSI-based indoor positioning systems. This study presents a concise survey of research conducted between 2020 and 2025, focusing on supervised and deep learning models such as k-Nearest Neighbors, Support Vector Machines, Random Forests, and Convolutional Neural Networks. A comparative analysis of recent works is provided, highlighting their methodologies, datasets, and performance outcomes. Additionally, current challenges such as signal instability, device heterogeneity, and fingerprinting limitations are discussed. The paper concludes by outlining future research directions, including transfer learning and automated fingerprinting techniques.

References

[1] Rathnayake RMMR, Maduranga MWP, Tilwari V, Dissanayake MB. RSSI and Machine Learning-Based Indoor Localization Systems for Smart Cities. Eng 2023;4(2):1468–94.

[2] Carlos Agualimpia-Arriaga, J. Rodríguez, F. Barrero. Machine Learning Based Indoor Localization Using Wireless Sensor Networks. IEEE Access 2023;11:18185–200.

[3] Hwang S, Lee J, Kang H. WiFi-based Indoor Positioning Using RSSI Heatmaps and CNN. Sensors 2021;21(22):8086.

[4] Chen Z, Zhang Y, He Y, Zhang S. Hybrid Deep Learning for Indoor Localization Using RSSI. Applied Sciences 2023;13(2):1104.

[5] Kostas K, et al. WiFi Based Distance Estimation Using Supervised Machine Learning. Proc IEEE Int Conf Indoor Positioning and Indoor Navigation (IPIN) 2022.

[6] Park K, et al. Improved RSSI-Based Indoor Localization Using Ensemble Learning. IEEE Access 2023.

[7] Neyaz H, Inamullah M, Beg MMS. Machine Learning Based Indoor Positioning System using Wi-Fi Fingerprinting Dataset. Proc IEEE ICECET 2024.

[8] Maduranga MWP, et al. Machine Learning-Based Indoor Localization System to Support 5G Location-Based Services. Proc 7th SLAICAI 2023.

[9] Hassoon SF, Kavian YS, Soorki MN. Indoor Localization using RSSI Based Supervised Machine Learning Approaches. Proc IEEE ICACCCN 2025.

[10] Machine Learning-Based Indoor Localization Using Wi-Fi RSSI Fingerprints: An Overview. IEEE Access 2021;9:127163–84. DOI: 10.1109/ACCESS.2021.3110430.

[11] Qian J, Komuro N, Kim W-S. Improving Position Estimation Accuracy by Reducing RSSI Offsets in BLE Fingerprinting-Based Indoor Positioning. Proc IEEE ICMLC 2022.

[12] Madhav, A., , Akhil, K. M. Rssi based localization and evaluation using support vector machine. In 2022 4th International Conference on Inventive Research in Computing Applications (ICIRCA) (pp. 509-515), 2022, September, IEEE.

[13] Hassen WF, Mezghani J. CNN-Based Approach for Indoor Positioning Services Using RSSI Fingerprinting. Proc IEEE Conf on ITS 2022;pp. 778–783.

[14] Jia B, Liu J, Feng T, Huang B, Baker T, Tawfik H. TTSL: An Indoor Localization Method Based on Temporal Convolutional Network Using Time-Series RSSI. Comput Commun 2022;193:293–301.

[15] Wu S, Huang W, Li M, Xu K. A Novel RSSI Fingerprint Positioning Method Based on Virtual AP and Convolutional Neural Network. IEEE Sens J 2022;22(7):6898–6909.

[16] Jerry Landívar et al., “Trilateration-Based Indoor Localization using Regression Methods,”

Journal of Sensors, 2022.

[17] Singh N, et al. Machine Learning Based Indoor Localization Using Wi-Fi RSSI Fingerprints: An Overview. IEEE Access 2021;9:127163–84.