Accepted author manuscript, 479 KB, PDF document
Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License
Final published version
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - Optimum NN Algorithms Parameters on the UJIIndoorLoc for Wi-Fi Fingerprinting Indoor Positioning Systems
AU - Ebaid, Emad
AU - Navaie, Keivan
PY - 2023/1/5
Y1 - 2023/1/5
N2 - Wi-Fi fingerprinting techniques are commonly used in Indoor Positioning Systems (IPS) as Wi-Fi signal is available in most indoor settings. In such systems, the position is estimated based on a matching algorithm between the enquiry points and the recorded fingerprint data. In this paper, our objective is to investigate and provide quantitative insight into the performance of various Nearest Neighbour (NN) algorithms. The NN algorithms such as KNN are also often employed in IPS. We extensively study the performance of several NN algorithms on a publicly available dataset, UJIIndoorLoc. Furthermore, we propose an improved version of the Weighted KNN algorithm. The proposed model outperforms the existing works on the UJIIndoorLoc dataset and achieves better results for the success rate and the mean positioning error.
AB - Wi-Fi fingerprinting techniques are commonly used in Indoor Positioning Systems (IPS) as Wi-Fi signal is available in most indoor settings. In such systems, the position is estimated based on a matching algorithm between the enquiry points and the recorded fingerprint data. In this paper, our objective is to investigate and provide quantitative insight into the performance of various Nearest Neighbour (NN) algorithms. The NN algorithms such as KNN are also often employed in IPS. We extensively study the performance of several NN algorithms on a publicly available dataset, UJIIndoorLoc. Furthermore, we propose an improved version of the Weighted KNN algorithm. The proposed model outperforms the existing works on the UJIIndoorLoc dataset and achieves better results for the success rate and the mean positioning error.
U2 - 10.1109/ITNAC55475.2022.9998385
DO - 10.1109/ITNAC55475.2022.9998385
M3 - Conference contribution/Paper
SN - 9781665471046
SP - 280
EP - 286
BT - 2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)
PB - IEEE
T2 - 32nd International Telecommunication Networks and Applications Conference
Y2 - 30 November 2022 through 2 December 2022
ER -