Imperial College London
Portrait Picture

ProfessorNiallAdams

Faculty of Natural Sciences, Department of Mathematics

Professor of Statistics
 
 
 
//

Contact

 

+44 (0)20 7594 8837n.adams Website

 
 
//

Location

 

6M55Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Mikhailova:2021:10.1680/jsmic.19.00022,
author = {Mikhailova, A and Adams, N and Hallsworth, C and Lau, D and Jones, D},
doi = {10.1680/jsmic.19.00022},
journal = {Proceedings of the Institution of Civil Engineers - Smart Infrastructure and Construction},
pages = {135--147},
title = {Unsupervised deep learning-powered anomaly detection for instrumented infrastructure},
url = {http://dx.doi.org/10.1680/jsmic.19.00022},
volume = {172},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Deep learning methods have recently shown great success in numerous fields, including finance, healthcare, linguistics, robotics and even cybersports. Unsupervised learning methods identify the dominant patterns of variability that shape a data set. Such patterns may correspond to well-understood processes, previously unknown clusters or anomalies. This paper presents a case study where a state-of-the-art family of unsupervised deep learning models called variational autoencoder (VAE) is applied to data accrued from a network of fibre-optic sensors installed within a composite steel–concrete half-through railway bridge. The goals were (a) to characterise automatically the behaviour of the bridge based on sensor measurements and, (b) based on this characterisation, to determine when a train passes across a bridge. Based on the VAE model, an algorithm is presented to identify automatically the ‘train event’ points in an unsupervised setting. Two architectures for the VAE model are compared with commonly used baselines. The architecture tailored for modelling sequential data is shown to outperform other methods considered, on both seen and unseen data. No special hyperparameter optimisation is required. This study illustrates how state-of-the-art deep learning methods can be applied to a civil infrastructure engineering problem without directly modelling the physics of the objects or performing tedious hyperparameter optimisation.
AU  - Mikhailova,A
AU  - Adams,N
AU  - Hallsworth,C
AU  - Lau,D
AU  - Jones,D
DO  - 10.1680/jsmic.19.00022
EP  - 147
PY  - 2021///
SN  - 2397-8759
SP  - 135
TI  - Unsupervised deep learning-powered anomaly detection for instrumented infrastructure
T2  - Proceedings of the Institution of Civil Engineers - Smart Infrastructure and Construction
UR  - http://dx.doi.org/10.1680/jsmic.19.00022
UR  - https://www.icevirtuallibrary.com/doi/10.1680/jsmic.19.00022
UR  - http://hdl.handle.net/10044/1/83515
VL  - 172
ER  -
Download