Web-based platform for evaluation of RF-based indoor localization algorithms

Abstract

The experimental efforts for optimizing the performance of RF-based indoor localization algorithms for specific environments and scenarios is time consuming and costly. In this work, we address this problem by providing a publicly accessible platform for streamlined experimental evaluation of RF-based indoor localization algorithms, without the need of a physical testbed infrastructure. We also offer an extensive set of raw measurements that can be used as input data for indoor localization algorithms. The datasets are collected in multiple testbed environments, with various densities of measurement points, using different measuring devices and in various scenarios with controlled RF interference. The platform encompasses two core services: one focused on storage and management of raw data, and one focused on automated calculation of metrics for performance characterization of localization algorithms. Tools for visualization of the raw data, as well as software libraries for convenient access to the platform from MATLAB and Python, are also offered. By contrasting its fidelity and usability with respect to remote experiments on dedicated physical testbed infrastructure, we show that the virtual platform produces comparative performance results while offering significant reduction in the complexity, time and labor overheads.

Platform for benchmarking of RF-based indoor localization solutions

“…In [14] we illustrate the benefits of leveraging the presented platform for the evaluation of RFbased indoor localization, in terms of time and complexity of usage, in comparison to using an infrastructure or performing a manual evaluation.…”

“…3. The details about the structure of the raw RF data, exact descriptions of the currently available datasets, and an overview of the services available for using the raw RF data for the evaluation of RF-based indoor localization algorithms can be found in [14].…”

Toward Extrapolation of WiFi Fingerprinting Performance Across Environments

“…The performance results of fingerprinting algorithms in these additional environments are publicly available [8], and they serve as standardized benchmarks of the performance of fingerprinting algorithms. Our similarity characterization yields that one environment is highly similar to the hospital baseline, in both physical and propagation characteristics, while the other two environments have increasing dissimilarities with the baseline.…”

PerfLoc (Part 1): An extensive data repository for development of smartphone indoor localization apps

“…VirTIL testbed [5] is focused on the evaluation of RF range-based indoor localization algorithms by providing range measurements made throughout the evaluation area. The EU EVARILOS project's efforts [6] yielded unprocessed low-level RF data, such as Received Signal Strength Indicator (RSSI) and Time of Flight (ToF) measurements, that are used in a wide range of indoor localization solutions, including fingerprinting, hybrid and proximity-based solutions. This paper builds upon that work and focuses on the extensive set of sensors available in today's smartphones, including not only RF-based ones, but also environmental, position, and motion sensors.…”