1. Environmental Cross-Validation of NLOS Machine Learning Classification/Mitigation with Low-Cost UWB Positioning Systems
- Author
-
Carlos Escudero, Jose A. Garcia-Naya, Pedro Suarez-Casal, and Valentín Barral
- Subjects
Indoor location algorithms ,Computer science ,Real-time computing ,NLOS detection ,02 engineering and technology ,01 natural sciences ,Biochemistry ,Article ,Cross-validation ,Analytical Chemistry ,Non-line-of-sight propagation ,UWB ,Position (vector) ,Machine learning ,0202 electrical engineering, electronic engineering, information engineering ,Electrical and Electronic Engineering ,Instrumentation ,indoor location algorithms ,010401 analytical chemistry ,020206 networking & telecommunications ,Ranging ,neural networks ,Atomic and Molecular Physics, and Optics ,0104 chemical sciences ,Statistical classification ,machine learning ,Face (geometry) ,Radio frequency ,Neural networks - Abstract
[Abstract] Indoor positioning systems based on radio frequency inherently present multipath-related phenomena. This causes ranging systems such as ultra-wideband (UWB) to lose accuracy when detecting secondary propagation paths between two devices. If a positioning algorithm uses ranging measurements without considering these phenomena, it will face critical errors in estimating the position. This work analyzes the performance obtained in a localization system when combining location algorithms with machine learning techniques applied to a previous classification and mitigation of the propagation effects. For this purpose, real-world cross-scenarios are considered, where the data extracted from low-cost UWB devices for training the algorithms come from a scenario different from that considered for the test. The experimental results reveal that machine learning (ML) techniques are suitable for detecting non-line-of-sight (NLOS) ranging values in this situation. Xunta de Galicia; ED431C 2016-045 Xunta de Galicia; ED431G/01 Agencia Estatal de Investigación de España; TEC2016-75067-C4-1-R
- Published
- 2019
- Full Text
- View/download PDF