Published October 4, 2021 | Version v1
Conference paper Open

Anomaly Detection on Live Water Pressure Data Stream

  • 1. Jožef Stefan Institute, Jamova cesta 39, 1000 Ljubljana, Slovenia

Description

We present the application of several anomaly detection algorithms to water pressure data streams. We evaluate their quality on unlabelled data sets using agreement rates. The applied algorithms are the Generative Adversarial Network (GAN), DBSCAN, Welford’s algorithm and Facebook Prophet. We found that GAN performed best.

Files

PetkovšeketalSIKDD_2021.pdf

Files (559.2 kB)

Name Size Download all
md5:1503621caa67d57ddc91024213b319c8
559.2 kB Preview Download

Additional details

Funding

NAIADES – A holistic water ecosystem for digitisation of urban water sector 820985
European Commission