Research Article
BibTex RIS Cite

WiFi RSSI ile Makine Öğrenme Tabanlı Gerçek Zamanlı Kapalı Alan Konum İzleme Sistemi

Year 2025, Volume: 20 Issue: 2, 389 - 400, 30.09.2025
https://doi.org/10.55525/tjst.1625642

Abstract

Kapalı alanda yerelleştirmeye yönelik artan talep, binalar içindeki kullanıcı konumlarını doğru bir şekilde belirlemek için gelişmiş yöntemlerin geliştirilmesine yol açmıştır. Bu çalışma, yakındaki erişim noktalarından (AP’ler) alınan WiFi sinyal güçlerini (RSSI) kullanarak bir kullanıcının konumunu gerçek zamanlı olarak tahmin eden bir kapalı alan yerelleştirme sistemini tanıtmaktadır. Rastgele Orman sınıflandırıcısına dayalı bir makine öğrenimi yaklaşımı, önceden toplanmış WiFi RSSI verileri üzerinde eğitilir ve yüksek tahmin doğruluğu elde etmek için dinamik girdiler üzerinde test edilir. Sistem, kullanıcıların canlı sinyal verilerini yüklemelerine ve konumlarını binanın bir kat planı üzerinde görselleştirmelerine olanak tanıyan bir grafiksel kullanıcı arayüzü (GUI) ile sorunsuz bir şekilde entegre olur. Eğitim ve tahmin veri kümeleri arasındaki uyumsuz özellik boyutlarının zorluklarını gidermek için, model uyumluluğunu sağlamak amacıyla özellik seçimi ve ön işleme yöntemleri uygulanır. Deneysel sonuçlar, sistemin 5 saniyelik gecikmeyle oda düzeyinde yer belirlemede %100 genel doğruluk sağladığını göstermektedir. Önerilen çözüm, akıllı evler, sağlık izleme ve güvenlik sistemlerinde potansiyel uygulamalarla kapalı alan yerelleştirmesi için uygun maliyetli, ölçeklenebilir ve kullanıcı dostu bir çerçeve sunmaktadır.

References

  • Shang S, Wang L. Overview of WiFi fingerprinting-based indoor positioning. IET Commun 2022;16(6):725–734.
  • He S, Chan SHG. Wi-Fi fingerprint-based indoor positioning: recent advances and comparisons. IEEE Commun Surv Tutorials 2016;18(1):466–490.
  • Hegde R, Hegde SK, Prasad K, Srinivas V, De T, Dankan Gowda V. Wi-Fi router signal coverage position prediction system using machine learning algorithms. Int Conf Sustain Comput Smart Syst (ICSCSS) Proc 2023:253–258.
  • Navarro E, Peuker B, Quan M, Clark AC, Jipson J. Wi-Fi localization using RSSI fingerprinting. Cal Poly Digit Commons 2010;Test 1. Available from: http://digitalcommons.calpoly.edu/cpesp/17
  • Al Mohammad A, Marku D, Reedy J, Reedy S, Maleki M, Banitaan S. Enhancing indoor positioning of wireless access points using RSSI fingerprints. IEEE Int Conf Electro Inf Technol 2024:364–371.
  • Çabuk UC, Dalkılıç F, Dağdeviren O. A study on room-level accuracy of Wi-Fi fingerprinting-based indoor localization systems. Celal Bayar Univ J Sci 2019;15(1):17–22.
  • Nabati M, Ghorashi SA. A real-time fingerprint-based indoor positioning using deep learning and preceding states. Expert Syst Appl 2023;213:118889.
  • Yildirim ME. RSSI based indoor localization with reduced feature dimension. Balk J Electr Comput Eng 2022;10(1):106–109.
  • Singh N, Choe S, Punmiya R. Machine learning based indoor localization using Wi-Fi RSSI fingerprints: an overview. IEEE Access. 2021;9:127150–127174.
  • Koçoğlu FÖ. Research on the success of unsupervised learning algorithms in indoor location prediction. Int Adv Res Eng J 2022;6(2):148–153.
  • Tilwari V, Pack S, Maduranga M, Lakmal HKIS. An improved Wi-Fi RSSI-based indoor localization approach using deep randomized neural network. IEEE Trans Veh Technol 2024;73(5):18593–18604.
  • Matsunaga T, Arai I, Atarashi Y, Endo A, Fujikawa K. Performance evaluation of fingerprint-based indoor positioning using RSSI in 802.11ah. 14th Int Conf Indoor Position Indoor Navig (IPIN). 2024:1–7.
  • Paudel K, Kadel R, Guruge DB. Machine-learning-based indoor mobile positioning using wireless access points with dual SSIDs—an experimental study. J Sens Actuator Netw 2022;11(4):72.
  • Reyes JMR, Ho IWH, Mak MW. Wi-Fi CSI fingerprinting-based indoor positioning using deep learning and vector embedding for temporal stability. Expert Syst Appl 2025;264:125802.
  • Horn BKP. Indoor localization using uncooperative Wi-Fi access points. Sensors. 2022;22(8):3091.
  • Speiser JL, Miller ME, Tooze J, Ip E. A comparison of random forest variable selection methods for classification prediction modeling. Expert Syst Appl 2019;134:93–101.
  • Miao J, Zhu W. Precision–recall curve (PRC) classification trees. Evol Intell 2022;15(3):1545–1569.
  • Paul A, Mukherjee DP, Das P. Improved random forest for classification. IEEE Trans. Image Process. 2018;27(8):4012–4024.

Machine Learning Based Real Time Indoor Location Tracking System with WiFi RSSI

Year 2025, Volume: 20 Issue: 2, 389 - 400, 30.09.2025
https://doi.org/10.55525/tjst.1625642

Abstract

The increasing demand for indoor localization has led to the development of advanced methods to accurately determine user locations within buildings. This study introduces an indoor localization system that uses WiFi signal strengths (RSSI) sniffed from nearby access points (APs) to estimate a user’s location in real-time. A machine learning approach based on the Random Forest classifier is trained on pre-collected WiFi RSSI data and tested on dynamic inputs to achieve high prediction accuracy. The system seamlessly integrates with a graphical user interface (GUI) that allows users to load live signal data and visualize their locations on a floor plan of the building. To address the challenges of mismatched feature sizes between the training and prediction datasets, feature selection and preprocessing methods are applied to ensure model compatibility. Experimental results demonstrate that the system achieves an overall accuracy of 100% in room-level localization with a latency of 5 seconds. The proposed solution provides a cost-effective, scalable, and user-friendly framework for indoor localization with potential applications in smart homes, health monitoring, and security systems.

References

  • Shang S, Wang L. Overview of WiFi fingerprinting-based indoor positioning. IET Commun 2022;16(6):725–734.
  • He S, Chan SHG. Wi-Fi fingerprint-based indoor positioning: recent advances and comparisons. IEEE Commun Surv Tutorials 2016;18(1):466–490.
  • Hegde R, Hegde SK, Prasad K, Srinivas V, De T, Dankan Gowda V. Wi-Fi router signal coverage position prediction system using machine learning algorithms. Int Conf Sustain Comput Smart Syst (ICSCSS) Proc 2023:253–258.
  • Navarro E, Peuker B, Quan M, Clark AC, Jipson J. Wi-Fi localization using RSSI fingerprinting. Cal Poly Digit Commons 2010;Test 1. Available from: http://digitalcommons.calpoly.edu/cpesp/17
  • Al Mohammad A, Marku D, Reedy J, Reedy S, Maleki M, Banitaan S. Enhancing indoor positioning of wireless access points using RSSI fingerprints. IEEE Int Conf Electro Inf Technol 2024:364–371.
  • Çabuk UC, Dalkılıç F, Dağdeviren O. A study on room-level accuracy of Wi-Fi fingerprinting-based indoor localization systems. Celal Bayar Univ J Sci 2019;15(1):17–22.
  • Nabati M, Ghorashi SA. A real-time fingerprint-based indoor positioning using deep learning and preceding states. Expert Syst Appl 2023;213:118889.
  • Yildirim ME. RSSI based indoor localization with reduced feature dimension. Balk J Electr Comput Eng 2022;10(1):106–109.
  • Singh N, Choe S, Punmiya R. Machine learning based indoor localization using Wi-Fi RSSI fingerprints: an overview. IEEE Access. 2021;9:127150–127174.
  • Koçoğlu FÖ. Research on the success of unsupervised learning algorithms in indoor location prediction. Int Adv Res Eng J 2022;6(2):148–153.
  • Tilwari V, Pack S, Maduranga M, Lakmal HKIS. An improved Wi-Fi RSSI-based indoor localization approach using deep randomized neural network. IEEE Trans Veh Technol 2024;73(5):18593–18604.
  • Matsunaga T, Arai I, Atarashi Y, Endo A, Fujikawa K. Performance evaluation of fingerprint-based indoor positioning using RSSI in 802.11ah. 14th Int Conf Indoor Position Indoor Navig (IPIN). 2024:1–7.
  • Paudel K, Kadel R, Guruge DB. Machine-learning-based indoor mobile positioning using wireless access points with dual SSIDs—an experimental study. J Sens Actuator Netw 2022;11(4):72.
  • Reyes JMR, Ho IWH, Mak MW. Wi-Fi CSI fingerprinting-based indoor positioning using deep learning and vector embedding for temporal stability. Expert Syst Appl 2025;264:125802.
  • Horn BKP. Indoor localization using uncooperative Wi-Fi access points. Sensors. 2022;22(8):3091.
  • Speiser JL, Miller ME, Tooze J, Ip E. A comparison of random forest variable selection methods for classification prediction modeling. Expert Syst Appl 2019;134:93–101.
  • Miao J, Zhu W. Precision–recall curve (PRC) classification trees. Evol Intell 2022;15(3):1545–1569.
  • Paul A, Mukherjee DP, Das P. Improved random forest for classification. IEEE Trans. Image Process. 2018;27(8):4012–4024.
There are 18 citations in total.

Details

Primary Language English
Subjects Wireless Communication Systems and Technologies (Incl. Microwave and Millimetrewave)
Journal Section TJST
Authors

Mert Yağcıoğlu 0000-0001-6493-6447

Publication Date September 30, 2025
Submission Date January 23, 2025
Acceptance Date June 22, 2025
Published in Issue Year 2025 Volume: 20 Issue: 2

Cite

APA Yağcıoğlu, M. (2025). Machine Learning Based Real Time Indoor Location Tracking System with WiFi RSSI. Turkish Journal of Science and Technology, 20(2), 389-400. https://doi.org/10.55525/tjst.1625642
AMA Yağcıoğlu M. Machine Learning Based Real Time Indoor Location Tracking System with WiFi RSSI. TJST. September 2025;20(2):389-400. doi:10.55525/tjst.1625642
Chicago Yağcıoğlu, Mert. “Machine Learning Based Real Time Indoor Location Tracking System With WiFi RSSI”. Turkish Journal of Science and Technology 20, no. 2 (September 2025): 389-400. https://doi.org/10.55525/tjst.1625642.
EndNote Yağcıoğlu M (September 1, 2025) Machine Learning Based Real Time Indoor Location Tracking System with WiFi RSSI. Turkish Journal of Science and Technology 20 2 389–400.
IEEE M. Yağcıoğlu, “Machine Learning Based Real Time Indoor Location Tracking System with WiFi RSSI”, TJST, vol. 20, no. 2, pp. 389–400, 2025, doi: 10.55525/tjst.1625642.
ISNAD Yağcıoğlu, Mert. “Machine Learning Based Real Time Indoor Location Tracking System With WiFi RSSI”. Turkish Journal of Science and Technology 20/2 (September2025), 389-400. https://doi.org/10.55525/tjst.1625642.
JAMA Yağcıoğlu M. Machine Learning Based Real Time Indoor Location Tracking System with WiFi RSSI. TJST. 2025;20:389–400.
MLA Yağcıoğlu, Mert. “Machine Learning Based Real Time Indoor Location Tracking System With WiFi RSSI”. Turkish Journal of Science and Technology, vol. 20, no. 2, 2025, pp. 389-00, doi:10.55525/tjst.1625642.
Vancouver Yağcıoğlu M. Machine Learning Based Real Time Indoor Location Tracking System with WiFi RSSI. TJST. 2025;20(2):389-400.