Neural network approximation of graph Fourier transform for sparse sampling of networked dynamics

Simple item page
dc.contributor.authorPagani, Alessio
dc.contributor.authorWei, Zhuangkun
dc.contributor.authorSilva, Ricardo
dc.contributor.authorGuo, Weisi
dc.date.accessioned2021-09-27T11:49:00Z
dc.date.available2021-09-27T11:49:00Z
dc.date.issued2021-09-14
dc.description.abstractInfrastructure monitoring is critical for safe operations and sustainability. Like many networked systems, water distribution networks (WDNs) exhibit both graph topological structure and complex embedded flow dynamics. The resulting networked cascade dynamics are difficult to predict without extensive sensor data. However, ubiquitous sensor monitoring in underground situations is expensive, and a key challenge is to infer the contaminant dynamics from partial sparse monitoring data. Existing approaches use multi-objective optimization to find the minimum set of essential monitoring points but lack performance guarantees and a theoretical framework. Here, we first develop a novel Graph Fourier Transform (GFT) operator to compress networked contamination dynamics to identify the essential principal data collection points with inference performance guarantees. As such, the GFT approach provides the theoretical sampling bound. We then achieve under-sampling performance by building auto-encoder (AE) neural networks (NN) to generalize the GFT sampling process and under-sample further from the initial sampling set, allowing a very small set of data points to largely reconstruct the contamination dynamics over real and artificial WDNs. Various sources of the contamination are tested, and we obtain high accuracy reconstruction using around 5%–10% of the network nodes for known contaminant sources, and 50%–75% for unknown source cases, which although larger than that of the schemes for contaminant detection and source identifications, is smaller than the current sampling schemes for contaminant data recovery. This general approach of compression and under-sampled recovery via NN can be applied to a wide range of networked infrastructures to enable efficient data sampling for digital twins.en_UK
dc.identifier.citationPagnani A, Wei Z, Silva R, Guo W. (2021) Neural network approximation of graph Fourier transform for sparse sampling of networked dynamics. ACM Transactions on Internet Technology, Volume 22, Issue 1, 2021, Article number 21en_UK
dc.identifier.issn1533-5399
dc.identifier.urihttps://doi.org/10.1145/3461838
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/17105
dc.language.isoenen_UK
dc.publisherAssociation for Computing Machinery (ACM)en_UK
dc.rightsAttribution-NonCommercial 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/*
dc.subjectneural networksen_UK
dc.subjectgraph fourier transformen_UK
dc.subjectSampling theoryen_UK
dc.subjectNetwork dynamicsen_UK
dc.subjectNetworks Cyber-physical networksen_UK
dc.subjectEmbedded and cyber-physical systemsen_UK
dc.subjectComputer systems organizationen_UK
dc.titleNeural network approximation of graph Fourier transform for sparse sampling of networked dynamicsen_UK
dc.typeArticleen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Neural_network_approximation_graph_Fourier_transform-2021.pdf
Size:
4.94 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)