Machine Learning Approaches for Indoor Positioning: A Case Study on KNN vs WKNN-inv and WKNN-cos
DOI:
https://doi.org/10.65568/gujes.2026.020101الكلمات المفتاحية:
Indoor localization ، KNN، WKNN-inv، WKNN-cosالملخص
Indoor localization is of paramount importance in intelligent environments, particularly in scenarios where Global Positioning System (GPS) signals are hindered by physical barriers within indoor settings. This study investigates machine learning methodologies designed to enhance the precision of indoor positioning systems. In particular, we conduct a comparative analysis of three algorithms: the conventional KNearest Neighbors (KNN), a Weighted KNN utilizing inverse distance metrics (WKNN-inv), and an additional variant that employs cosine similarity measures (WKNN-cos). Each algorithm was systematically implemented and assessed concerning its positioning accuracy. The results from simulations indicate that WKNN-inv yields an accuracy enhancement of approximately 11.2% relative to KNN, whereas WKNN-cos provides a 13.0% improvement.
المراجع
References
[1] A. Nessa, B. AdhIkari, F. Hussain and X. N. Fernando, "A Survey of Machine Learning for Indoor Positioning," IEEE Access,vol 8, pp 214945–214965, 2020, doi: 10.1109/ACCESS.2020.3039271.
[2] A. Gadhgadhi, Y. Hacha¨ıchi and H. Zairi, "A Machine Learning based Indoor Localization," 2020 4th International Conference on Advanced Systems and Emergent Technologies (IC_ASET), pp. 33-38,2020, doi: 10.1109/ICASET49463.2020.9318284.
[3] Dissanayake, R. M. M. R. Rathnayake, M. W. P. Maduranga, V. Tilwari and M. B, "RSSI and Machine Learning-Based Indoor Localization Systems for Smart Cities,". MDPI/Eng, pp 1468–1494, 2023, https://doi.org/10.3390/eng4020085.
[4] N. Singh, S. Choe and R. Punmiya, "Machine Learning Based Indoor Localization Using Wi-Fi RSSI Fingerprints:AnOverview,"IEEEAccess,pp.127150–127174, 2021, doi:10.1109/ACCESS.2021.311108.
[5] B. Adhikari, "Neural Network Based Recursive Least SquareTechnique for Indoor Wireless Positioning," Ryerson University, Canda Torinu , 2021.
[6] F. Qin, T. Zuo and a. X. Wang, "CCpos: WiFi Fingerprint Indoor Positioning System Based on CDAE-CNN," Sensors ,pp 1-17, 2021,http://doi.org/10.3390/s21041114.
[7] S. Liu, R. d. Lacerda and J. Fiorina, "Performance Analysis of Adaptive K for Weighted K-Nearest Neighbor based Indoor Positioning," Vehicular Technology Conference (VTC2022-Spring), Helsinki, Finland, 2022, doi:10.1109/vtc2022-spring54318.2022.9860699.
[8] E. I. A. Costa and J. A. Carro, "Development of AI/ML Methods for Advanced Device Localization in Beyond 5G Systems," Lund University, Sweden, 2023.
[9] R. Uttarwar and J. Valentín, "Indoor Positioning and Machine Learning Algorithms," Lund University, Sweden , 2021.
[10] H. Lu, L. Zhang, H. Chen, S. Zhang, S. Wang, H. Peng and J. Zou, "An Indoor Fingerprint Positioning Algorithm Based on WKNN and Improved XGBoost," Sensors, 2023, https://doi.org/10.3390/s23083952.
التنزيلات
منشور
إصدار
القسم
الرخصة
الحقوق الفكرية (c) 2026 مجلة جامعة غريان للعلوم الهندسية
هذا العمل مرخص بموجب Creative Commons Attribution-NonCommercial 4.0 International License.
