A Soft Range Limited K-Nearest Neighbors Algorithm for Indoor Localization Enhancement

TLDR

Conventional KNN localizes users by ranking fingerprint distances between an unknown position and reference points in the database. This paper proposes a soft range limited K‑Nearest Neighbors (SRL‑KNN) fingerprinting algorithm to improve indoor localization. SRL‑KNN scales fingerprint distances by a range factor derived from the user’s previous position, incorporates RSSI histograms to account for temporal fluctuations, and does not require knowledge of the user’s speed or direction. Experiments show the algorithm achieves an average error of 0.66 m, with 80 % of errors below 0.89 m, outperforming conventional KNN by 45 %.

Abstract

This paper proposes a soft range limited K-nearest neighbors (SRL-KNNs) localization fingerprinting algorithm. The conventional KNN determines the neighbors of a user by calculating and ranking the fingerprint distance measured at the unknown user location and the reference locations in the database. Different from that method, SRL-KNN scales the fingerprint distance by a range factor related to the physical distance between the user's previous position and the reference location in the database to reduce the spatial ambiguity in localization. Although utilizing the prior locations, SRL-KNN does not require knowledge of the exact moving speed and direction of the user. Moreover, to take into account of the temporal fluctuations of the received signal strength indicator (RSSI), RSSI histogram is incorporated into the distance calculation. Actual on-site experiments demonstrate that the new algorithm achieves an average localization error of 0.66 m with 80% of the errors under 0.89 m, which outperforms conventional KNN algorithms by 45% under the same test environment.