Service for Calculation of Performance Metrics of Indoor Localization Benchmarking Experiments
نویسندگان
چکیده
This report presents the service for calculation of performance metrics of indoor localization benchmarking experiments. By performance metrics we mean point and room level accuracy of location estimation, response time and power consumption of the system under test. The service is developed in order to standardize the way performance metrics of indoor localization benchmarking experiments are calculated, to automatize the storage of metrics into specific storage service and to remove the burden of manual calculation of metrics, removing the possibility of the errors in calculations. The service provides two ways of usage, namely offline and online calculation of performance metrics. Offline calculation can be used for calculating performance metrics of a previously performed experiment, so on the set of ground truths and estimates. Contrary to that, online calculation calculates and updates metrics in a real-time, so ground truths and corresponding estimates can be provided sequentially to the service and the service will take care of calculation and updating the performance metrics in the database. The services is publicly available and easy to use only by defining a specific message and sending it on a provided HTTP URL.
منابع مشابه
Demo Abstract: Virtual Experimental Evaluation of RF-based Indoor Localization Algorithms
This demonstration presents a set of services for streamlined experimental evaluation and benchmarking of RFbased indoor localization algorithms using previously collected raw measurements. The platform consists of an online service for storing and managing raw indoor localization data collected in a set of extensive experiments. The platform also integrates a cloudbased service for calculation...
متن کاملData Management Services for Evaluation of RF-based Indoor Localization
This report presents R2DM (Raw Ranging Data Management) and PDM (Processed Data Management) services. R2DM service is a web service developed for storing, managing and accessing the raw data from indoor localization benchmarking experiments. By raw ranging data we mean the measured physical values used as input for the localization algorithms, such as Angle of Arrival (AoA), Time of Arrival (To...
متن کاملDemo Abstract: Testbed Infrastructure for Benchmarking RF-based Indoor Localization Solutions under Controlled Interference
The proliferation of RF-based indoor localization solutions raises the need for testing systems that enable objective evaluation of their functional and non functional properties. We introduce a testbed infrastructure for automatized benchmarking of RF-based indoor localization solutions. The infrastructure leverages a robotic mobility platform which serves as a reference localization system an...
متن کاملIndoor Positioning and Pre-processing of RSS Measurements
Rapid expansions of new location-based services signify the need for finding accurate localization techniques for indoor environments. Among different techniques, RSS-based schemes and in particular oneof its variants which is based on Graph-based Semi-Supervised Learning (G-SSL) are widely-used approaches The superiority of this scheme is that it has low setup/training cost and at the same ti...
متن کاملDemo: Platform for Benchmarking RF-based Indoor Localization Solutions
This demonstration presents a user-friendly web-based platform that supports intuitive remote benchmarking of di↵erent indoor localization solutions. It reduces the barriers for experimental evaluation and fair comparison of their performance across a set of testing environments. The platform is aimed at addressing the limitations in the current praxis of publishing indoor localization research...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2014