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

Abstract

1 This paper proposes a soft range limited K nearest neighbours (SRL-KNN) localization fingerprinting algorithm. The conventional KNN determines the neighbours 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.

Recurrent Neural Networks for Accurate RSSI Indoor Localization

“…Therefore, we propose several RNN solutions, such as vanilla RNN, LSTM, GRU, BiRNN, BiLSTM and BiGRU, to solve the three RSSI fingerprinting challenges. Our localization results are compared not only with the other neural network methods, i.e., MLP [18] and MLNN [20], but also some conventional methods, i.e., RADAR [12], SRL-KNN [22], Kernel method [9] and Kalman filter [23].…”

“…Note that resolving the ambiguous locations has been a common challenge in indoor localization. Some works in literature also exploit the measurements in previous time steps to locate the current location, including the use of Kalman filter [23]- [26] and soft range limited K-nearest neighbors (SRL-KNN) [22]. Among them, Kalman filter estimates the most likely current location based on prior measurements, assuming a Gaussian noise of the RSSI and linear motion of the detecting object.…”

“…2 The proposed models are tested in two different datasets including an in-house measurement dataset and the published dataset UJIIndoorLoc [32]. The accuracy is compared not only with the other neural network methods, i.e., MLP [18] and MLNN [20], but also some popular conventional methods, i.e., RADAR [12], SRL-KNN [22], Kernel method [9] and Kalman filter [23]. 3 Three challenges of WiFi indoor localization, i.e., spatial ambiguity, RSSI instability and RSSI short collecting time per location are discussed and addressed.…”

Semi-Sequential Probabilistic Model for Indoor Localization Enhancement

“…Our semi-sequential probabilistic model (SSP) applies window functions such as Gaussian, Hann and Tukey, and is based on the physical distance between the RP and the user's predicted previous position to calculate the probability of RP being near the user's current position. As a result, the spatial ambiguity of fingerprints [29] is significantly reduced and the localization accuracy is improved.…”

“…In real scenarios, those assumptions are not necessarily valid [35]. SRL-KNN [29] does not require the above assumptions and reaches the lowest complexity. However, the modified penalty functions in SRL-KNN can only be applied for Euclidean distance, not for probabilistic model.…”