Skip to search boxSkip to navigationSkip to main content

Curriculum Learning-Based Multivariate Time Series Anomaly Detection

  • Boğaziçi University
Output:
Chapter in Book/Report/Conference proceeding
Conference contribution
Academic
Peer-review

Information

Output type

Output:
Chapter in Book/Report/Conference proceeding
Conference contribution
Academic
Peer-review

Original language

English

Article number

10516396

Pages from-to (Number of pages)

Pages 186-193 (8 pages)

Publication milestones

  • Published - 09/05/2024

Publication status

Published - 09/05/2024

Publisher

Institute of Electrical and Electronics Engineers, United States

ISBN (Electronic)

978-952-65246-1-0

Host publication title

2024 35th Conference of Open Innovations Association (FRUCT)

Related Event

Title

2024 35th Conference of Open Innovations Association (FRUCT)

Event type

Conference

Date

24/04/2024 - 26/04/2024

Location

Tampere, FinlandTampereFinland

Abstract

Anomaly detection in multivariate time series (MVTS) is a significant research domain across several industries, including cybersecurity and industrial systems. There have been several deep learning-based methods proposed within this research domain. The development of high capacity frameworks has received the majority of attention in recent years due to the availability of large open-source datasets and improvement in computer processing power. However, there has not been much attention in investigating the importance of how the data is presented to these techniques during training. Curriculum learning (CL), a technique based on ordered learning, was proposed for machine learning. In CL, the model first learns from easy data and is progressively trained with increasingly difficult data. In this paper, we propose data-based CL for MVTS anomaly detection. We further introduce the CL concept to the learner (model), in which we first train a simple model and then utilize a complex model in the final training round. To the best of our knowledge, we are the first to investigate these approaches in MVTS anomaly detection. We evaluate the proposed designs on the SWaT dataset using the F1 score and the results show an improvement in performance.

Metrics

Metrics

SciVal
FWCI
0.80
SciVal
Author count
2
SciVal
Paper percentile
65
SciVal
citations
2
Scopus
citations
2