Studying properties of water data using manifold-aware anomaly detectors

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Standard

Studying properties of water data using manifold-aware anomaly detectors. / Paulsen, Tino; Brefeld, Ulf.
Design of Cyber-Secure Water Plants. Hrsg. / Aditya Mathur; Jianying Zhou; Gauthama Raman. MDPI AG, 2024. (Water).

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Harvard

Paulsen, T & Brefeld, U 2024, Studying properties of water data using manifold-aware anomaly detectors. in A Mathur, J Zhou & G Raman (Hrsg.), Design of Cyber-Secure Water Plants. Water, MDPI AG, First International Conference on the design of cyber-secure water plants - DCS-Water'24, Buford, Georgia, USA / Vereinigte Staaten, 23.04.24.

APA

Paulsen, T., & Brefeld, U. (2024). Studying properties of water data using manifold-aware anomaly detectors. Manuskript zur Veröffentlichung eingereicht. In A. Mathur, J. Zhou, & G. Raman (Hrsg.), Design of Cyber-Secure Water Plants (Water). MDPI AG.

Vancouver

Paulsen T, Brefeld U. Studying properties of water data using manifold-aware anomaly detectors. in Mathur A, Zhou J, Raman G, Hrsg., Design of Cyber-Secure Water Plants. MDPI AG. 2024. (Water).

Bibtex

@inbook{4a8f2f9494564f1fbee82ba4f751face,
title = "Studying properties of water data using manifold-aware anomaly detectors",
abstract = "Deep learning methods, especially the family of autoencoder architectures, exhibit state-of-the-art detection rates in anomaly detection tasks. Additionally, recent results show that learning latent spaces with deep architectures on Riemannian manifolds may further improve performances as well as related interpolation tasks. In this paper, we study the use of Riemannian manifolds with variational autoencoders (VAEs) for anomaly detection on data from water providers. Besides traditional embeddings in Euclidean space, we study embeddings in Poincar{\'e} disc, spheres, and Stiefel manifolds, where in general, the Poincar{\'e} disc is often preferred for data with hierarchical structures, embeddings in spheres suggests itself for cyclical structures and the Stiefel manifold is well suited for time-dependent data. Data from water providers clearly meets all three criteria and we report on empirical results with the different manifolds as latent spaces and compare their detection performance to that of standard Euclidean embeddings. ",
keywords = "Informatics",
author = "Tino Paulsen and Ulf Brefeld",
year = "2024",
month = apr,
day = "23",
language = "English",
series = "Water",
publisher = "MDPI AG",
editor = "Aditya Mathur and Jianying Zhou and Gauthama Raman",
booktitle = "Design of Cyber-Secure Water Plants",
address = "Switzerland",
note = "First International Conference on the design of cyber-secure water plants - DCS-Water'24, DCS-Water'24 ; Conference date: 23-04-2024 Through 24-04-2024",
url = "https://itrust.sutd.edu.sg/first-international-conference-on-the-design-of-cyber-secure-water-plants-dcs-water24/paper-submission-dcs-water24/",

}

RIS

TY - CHAP

T1 - Studying properties of water data using manifold-aware anomaly detectors

AU - Paulsen, Tino

AU - Brefeld, Ulf

PY - 2024/4/23

Y1 - 2024/4/23

N2 - Deep learning methods, especially the family of autoencoder architectures, exhibit state-of-the-art detection rates in anomaly detection tasks. Additionally, recent results show that learning latent spaces with deep architectures on Riemannian manifolds may further improve performances as well as related interpolation tasks. In this paper, we study the use of Riemannian manifolds with variational autoencoders (VAEs) for anomaly detection on data from water providers. Besides traditional embeddings in Euclidean space, we study embeddings in Poincaré disc, spheres, and Stiefel manifolds, where in general, the Poincaré disc is often preferred for data with hierarchical structures, embeddings in spheres suggests itself for cyclical structures and the Stiefel manifold is well suited for time-dependent data. Data from water providers clearly meets all three criteria and we report on empirical results with the different manifolds as latent spaces and compare their detection performance to that of standard Euclidean embeddings.

AB - Deep learning methods, especially the family of autoencoder architectures, exhibit state-of-the-art detection rates in anomaly detection tasks. Additionally, recent results show that learning latent spaces with deep architectures on Riemannian manifolds may further improve performances as well as related interpolation tasks. In this paper, we study the use of Riemannian manifolds with variational autoencoders (VAEs) for anomaly detection on data from water providers. Besides traditional embeddings in Euclidean space, we study embeddings in Poincaré disc, spheres, and Stiefel manifolds, where in general, the Poincaré disc is often preferred for data with hierarchical structures, embeddings in spheres suggests itself for cyclical structures and the Stiefel manifold is well suited for time-dependent data. Data from water providers clearly meets all three criteria and we report on empirical results with the different manifolds as latent spaces and compare their detection performance to that of standard Euclidean embeddings.

KW - Informatics

UR - https://itrust.sutd.edu.sg/first-international-conference-on-the-design-of-cyber-secure-water-plants-dcs-water24/paper-submission-dcs-water24/

UR - https://www.mdpi.com/journal/water/special_issues/7UA9S2ASB0

M3 - Article in conference proceedings

T3 - Water

BT - Design of Cyber-Secure Water Plants

A2 - Mathur, Aditya

A2 - Zhou, Jianying

A2 - Raman, Gauthama

PB - MDPI AG

T2 - First International Conference on the design of cyber-secure water plants - DCS-Water'24

Y2 - 23 April 2024 through 24 April 2024

ER -

Zuletzt angesehen

Publikationen

  1. Using Long-Duration Static Stretch Training to Counteract Strength and Flexibility Deficits in Moderately Trained Participants
  2. Compression behavior of typical silicone rubbers for soft robotics applications at elevated temperatures
  3. Exploring intrinsic, instrumental and relational values for sustainable management of social-ecological systems
  4. Intra-firm Wage Compression and Cost Coverage of Training
  5. Using a Bivariate Polynomial in an EKF for State and Inductance Estimations in the Presence of Saturation Effects to Adaptively Control a PMSM
  6. Combination of a reduced order state observer and an Extended Kalman Filter for Peltier cells
  7. Improving Flood Forecasting in a Developing Country
  8. A transfer operator based numerical investigation of coherent structures in three-dimensional Southern ocean circulation
  9. Investigation of the Controllability of Inductive Power Transmission Systems based on Flexible Coils
  10. Confidence levels and likelihood terms in IPCC reports
  11. Optimal scheduling for Automated Guided Vehicles (AGV) in blocking job-shops
  12. Natural enemy diversity reduces temporal variability in wasp but not bee parasitism
  13. Unusual two‐bond 13C, 13C coupling constants in sulphones
  14. Elastomeric Prepregs for Soft Robotics Applications
  15. Predicting the future performance of soccer players
  16. Open Innovation in Schools
  17. Testing for a break in the persistence in yield spreads of EMU government bonds
  18. CubeQA—question answering on RDF data cubes
  19. Fluorometer controlled apparatus designed for long-duration algal-feeding experiments and environmental effect studies with mussels
  20. Careless responding detection revisited
  21. Selecting methods for ecosystem service assessment
  22. Integrated simulation method for investment decisions of micro production systems
  23. A duty-block network approach for an integrated driver rostering problem in public bus transport
  24. Diversity promotes temporal stability across levels of ecosystem organization in experimental grasslands
  25. Reduction of springback by use of deep drawing tools with locally and temporally varying stiffness