Evaluating location fingerprinting methods for underground GSM networks deployed over Leaky Feeder

Abstract

Abstract-Accurate localization techniques have long been of major importance for safety systems and a lot of research has been conducted in the distributed computing field regarding its functionality and reliability. In the specific scenario of long yet narrow tunnels existing at CERN, localization methods will enable a number of applications and processes to substantially reduce human intervention.In this paper we evaluate the use of Fingerprinting techniques with GSM signal available throughout the LHC tunnel via a radiating cable and compare some methods to estimate the location. The existing GSM infrastructure and tunnel conditions seem to be favorable to the adoption of these Fingerprinting methods. Nevertheless significant variations in the signal have been observed which might be traced back to different operational states of accelerator equipment. These effects and their sources will be analyzed in more detail in order to improve the applied techniques and their accuracy under such challenging conditions.

A Survey of Enabling Technologies for Network Localization, Tracking, and Navigation

“…It has also been shown that using different functions and methods to compare the user's RSS fingerprint with those in the radiomap has a significant impact on the positioning accuracy [67]- [69]. In [68], several alternatives for matching fingerprints are evaluated in the context of a GSM-based underground positioning system. In this case, the Euclidean distance proved to be the function leading to a better accuracy.…”

2018 International Conference on Indoor Positioning and Indoor Navigation

“…This method was created as an alternative to the one suggested in ref. [4], but since it is rather synthetic it doesn't take into account combined or post-processed results. Therefore, performance is also evaluated in terms of the actual achieved accuracy with KNN, calculated for K=1, 3, 5 and 7.…”

“…Nevertheless, the accuracy obtained with these methods is highly dependent on the type of the underlying radio network and on the specific environment characteristics that determine the conditions for the signal propagation. In the case of tunnels whose network coverage is implemented using leaky-feeders, the relatively low attenuation of the signal along the cable can be obfuscated by fluctuations occurring in the short-range due to fast-fading and signal coupling phenomena [3] [4], thus yielding very often unsatisfactory results.…”

“…Because they enable for better Line-of-Sight (LoS) conditions, localization accuracy is usually less sensitive to environmental changes [2]. Nevertheless, previous studies also show that when the cable insufficiently attenuates the signal being transmitted, RSS fingerprinting methods might be unable to deliver high accuracies in the range of up to a few meters [4]. This is particularly problematic for the case of GSM, whose lower frequency also imposes lower attenuation.…”

Performance and limits of KNN-based positioning methods for GSM networks over leaky feeder in underground tunnels

“…In a first attempt to estimate location a modified weighted K-Nearest Neighbour (KNN) approach, in 16 variants, was explored (Pereira et al 2011). In this method, raw data are being pre-processed so that for each point of the radio-map, the average, the maximum and the standard deviation of the RSS values are calculated.…”