IRUS Total

Variational Gaussian process for optimal sensor placement

File Description SizeFormat 
VGP_IndoorSensors_v2.pdfAccepted version9.91 MBAdobe PDFView/Open
Title: Variational Gaussian process for optimal sensor placement
Authors: Tajnafoi, G
Arcucci, R
Mottet, L
Vouriot, C
Molina-Solana, M
Pain, C
Guo, Y-K
Item Type: Journal Article
Abstract: Sensor placement is an optimisation problem that has recently gained great relevance. In order to achieve accurate online updates of a predictive model, sensors are used to provide observations. When sensor location is optimally selected, the predictive model can greatly reduce its internal errors. A greedy-selection algorithm is used for locating these optimal spatial locations from a numerical embedded space. A novel architecture for solving this big data problem is proposed, relying on a variational Gaussian process. The generalisation of the model is further improved via the preconditioning of its inputs: Masked Autoregressive Flows are implemented to learn nonlinear, invertible transformations of the conditionally modelled spatial features. Finally, a global optimisation strategy extending the Mutual Information-based optimisation and fine-tuning of the selected optimal location is proposed. The methodology is parallelised to speed up the computational time, making these tools very fast despite the high complexity associated with both spatial modelling and placement tasks. The model is applied to a real three-dimensional test case considering a room within the Clarence Centre building located in Elephant and Castle, London, UK.
Issue Date: 1-Apr-2021
Date of Acceptance: 12-Feb-2021
URI: http://hdl.handle.net/10044/1/87964
DOI: 10.21136/am.2021.0307-19
ISSN: 0373-6725
Publisher: Institute of Mathematics, Czech Academy of Sciences.
Start Page: 287
End Page: 317
Journal / Book Title: Applications of Mathematics
Volume: 66
Issue: 2
Copyright Statement: © 2021, Institute of Mathematics, Czech Academy of Sciences.
Sponsor/Funder: European Commission Directorate-General for Research and Innovation
Engineering & Physical Science Research Council (E
Funder's Grant Number: RG80519
Keywords: Science & Technology
Physical Sciences
Mathematics, Applied
sensor placement
variational Gaussian process
mutual information
0102 Applied Mathematics
Numerical & Computational Mathematics
Publication Status: Published
Online Publication Date: 2021-02-12
Appears in Collections:Civil and Environmental Engineering
Earth Science and Engineering