A New Indoor Positioning Approach based on Weighted K-Nearest Algorithm

Akanni, Jimoh (Department of Electrical and Electronics Engineering, University of Ilorin, Ilorin, Nigeria)
Isa, Abdurrhaman Ademola (Federal Institute of Industrial Research, Oshodi, South West Zonal Office, Akure, Ondo State, Nigeria)
Abdulrahman, Amuda Yusuf (Department of Electrical and Electronics Engineering, University of Ilorin, Ilorin, Nigeria)
Alao, Atanda Rasaq (Department of Electrical and Electronics Engineering, University of Ilorin, Ilorin, Nigeria)
Ogunbiyi, Olalekan (Department of Electrical and Computer Engineering, Kwara State University, Malete, Kwara State Nigeria.)

IPTEK The Journal for Technology and Science
Vol 35, No 2 (2024)

Many contemporary technological services rely heavily on precise location data within smartphone applications, making accuracy a crucial aspect of indoor positioning systems. However, the variability in received signal strength (RSS) poses a challenge for achieving exact locations in Wi-Fi indoor positioning algorithms. Traditional weighted k-nearest neighbor (WkNN) techniques typically utilize RSS spatial distance for selecting reference points (RPs) to estimate locations. To enhance position accuracy, this study introduces a novel indoor positioning method based on WkNN. By incorporating three geometrical distances of RSS (physical, spatial, and Canberra), this approach selects RPs and conducts position estimation using a fusion weighted strategy based on these distances. Experimental findings indicate that the newly proposed method outperforms the nearest neighbor (NN) technique. Moreover, comparative investigations demonstrate its superiority over k-nearest neighbor (kNN) and weighted k-nearest neighbor (WkNN) algorithms. Compared to NN, kNN, and WkNN algorithms, this novel technique improves positioning accuracy by approximately 49.9%, 32%, and 25%, respectively.