UWB Localization Employing Supervised Learning Method
Conference paper
Rana, S., Dey, M., Siddiqui, H., Tiberi, G., Ghavami, M. and Dudley, S (2017). UWB Localization Employing Supervised Learning Method. IEEE International Conference on Ubiquitous Wireless Broadband 2017. Salamanca, Spain 12 - 15 Sep 2017 Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICUWB.2017.8250971
Authors | Rana, S., Dey, M., Siddiqui, H., Tiberi, G., Ghavami, M. and Dudley, S |
---|---|
Type | Conference paper |
Abstract | An indoor positioning system (IPS) is a technology employed to locate objects and people within a building scenario using signal processing or other sensory information. Ultra Wide Band (UWB) is a versatile wireless technology that can be employed as an IPS and has shown very good performances. UWB can be used in many scenarios and its effectiveness in through wall detection along with its excellent resolution for person localization is one of the best applications of IR-UWB. The main objective of this work is to propose a concept for intelligent radar systems employing UWB augmented by machine learning approaches to not only localize but understand the location of a person or target within a building. Although suitably developed UWB is excellent for obtaining localizing data it does not automatically understand what that location effectively means or where it is thus further methods are required to create meaningful data for end user appreciation. Learning from the huge amount of UWB signal data through Multi Class Support Vector Machine (MC-SVM) architecture enables a truly evolving scheme to both localize targets and identify them in a useful way. Statistical analysis of the experimental results supports the proposed algorithm |
Keywords | Indoor Positioning System (IPS); Localization; Ultra Wide Band (UWB; Principal Component Analysis (PCA); Multi Class Support Vector Machine (MC-SVM) |
Year | 2017 |
Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
Digital Object Identifier (DOI) | https://doi.org/10.1109/ICUWB.2017.8250971 |
Accepted author manuscript | License File Access Level Open |
Publication dates | |
12 Sep 2017 | |
Publication process dates | |
Deposited | 12 Oct 2017 |
Accepted | 23 Jun 2017 |
https://openresearch.lsbu.ac.uk/item/86xv9
Download files
278
total views479
total downloads1
views this month2
downloads this month