Faulty measurements impact on wireless local area network positioning performance

Abstract

Indoor positioning methods based on wireless local area network (WLAN) signal measurements have gained popularity because of high localisation accuracy. These methods use radio-maps obtained from wireless signal measurement surveys on location grids. Measurement sets from various WLAN access points are called fingerprints and they can be used to identify locations where the measurements are collected. WLAN positioning methods face unexpected changes in signal patterns because of attenuation changes or transient faults in WLAN cards or access points that often make signal strength readings unavailable. This study studies the effect of faulty measurements on the performance of popular state-of-the-art WLAN indoor positioning methods. Additionally, an integrity monitoring preprocessing algorithm is provided that demonstrates a possibility of faulty measurements mitigation for conventional methods such as K-nearest-neighbour. This is achieved by detecting and excluding faulty measurements prior to classification. Performance figures are provided for both simulated and empirical environments.

Modern WLAN Fingerprinting Indoor Positioning Methods and Deployment Challenges

“…The first summation component is on a subset of APs that are available in both fingerprinting and online phase while the second term sums over the APs that are available only in the online period and not in the fingerprinting period. A more comprehensive model of outliers has been proposed [150], which considers different causes of outliers as…”

An algorithm for three-dimensional indoor positioning based on Bayesian inference, Fingerprinting method and Wi-Fi technology

“…2.1.2 FINGERPRINT Fingerprint is a technique based on pattern recognition and involves the division of the location system into two phases, offline and online phases. In the offline phase, the vectors of received signal strength are collected the of all the detected Wi-Fi signals from different access points at many known locations (reference points) [8]. The online phase consists of reading an RSS value, and by using a classification algorithm, this RSS value is compared with the values stored in the database during the offline phase, thus obtaining the location.…”

“…This procedure is repeated until there is no RP change between the clusters. This procedure is performed by minimizing an objective function, called the squared error function, which is defined as (8) Where ‖ − ‖is a 3D measure of the distance between each reference points and the centroid.In general, Euclidean distance is applied in (8). This, together with other measures of similarity, including Mahalanobis, Minkowski, and cosine distances, are discussed in [23].…”

“…These schemes are discussed in [1] and [2], whereas in [3] and [4] the application of artificial neural networks (ANNs) to the problem was proposed. The k-nearest neighbours (k-NN) algorithm and the Bayes method were addressed in [5], [6], [7], [8] and [9]. In this paper, we propose a three-dimensional (3D) solution to this problem through a hybrid algorithm.…”

A Fast-rate WLAN Measurement Tool for Improved Miss-rate in Indoor Navigation

“…Another approach to improve the reliability of the measurements is by detecting and filtering "outliers" from the available measurement set [17]- [19]. Distortion impact of various outlier types on WLAN-based fingerprint positioning as well as missed measurement effects is reported in [20], [21]. Therefore, the availability and reliability of measurements during offline surveying as well as online navigation is important.…”