TCF-Trans: temporal context fusion transformer for anomaly detection in time series
Anomaly detection tasks involving time-series signal processing have been important research topics for decades. In many real-world anomaly detection applications, no specific distributions fit the data, and the characteristics of anomalies are different. Under these circumstances, the detection alg...
Saved in:
Main Authors: | , , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/173799 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-173799 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1737992024-03-01T15:40:35Z TCF-Trans: temporal context fusion transformer for anomaly detection in time series Peng, Xinggan Li, Hanhui Lin, Yuxuan Chen, Yongming Fan, Peng Lin, Zhiping School of Electrical and Electronic Engineering Engineering Anomaly detection Deep learning networks Anomaly detection tasks involving time-series signal processing have been important research topics for decades. In many real-world anomaly detection applications, no specific distributions fit the data, and the characteristics of anomalies are different. Under these circumstances, the detection algorithm requires excellent learning ability of the data features. Transformers, which apply the self-attention mechanism, have shown outstanding performances in modelling long-range dependencies. Although Transformer based models have good prediction performance, they may be influenced by noise and ignore some unusual details, which are significant for anomaly detection. In this paper, a novel temporal context fusion framework: Temporal Context Fusion Transformer (TCF-Trans), is proposed for anomaly detection tasks with applications to time series. The original feature transmitting structure in the decoder of Informer is replaced with the proposed feature fusion decoder to fully utilise the features extracted from shallow and deep decoder layers. This strategy prevents the decoder from missing unusual anomaly details while maintaining robustness from noises inside the data. Besides, we propose the temporal context fusion module to adaptively fuse the generated auxiliary predictions. Extensive experiments on public and collected transportation datasets validate that the proposed framework is effective for anomaly detection in time series. Additionally, the ablation study and a series of parameter sensitivity experiments show that the proposed method maintains high performance under various experimental settings. Published version 2024-02-27T08:52:57Z 2024-02-27T08:52:57Z 2023 Journal Article Peng, X., Li, H., Lin, Y., Chen, Y., Fan, P. & Lin, Z. (2023). TCF-Trans: temporal context fusion transformer for anomaly detection in time series. Sensors, 23(20), 8508-. https://dx.doi.org/10.3390/s23208508 1424-8220 https://hdl.handle.net/10356/173799 10.3390/s23208508 37896601 2-s2.0-85175278076 20 23 8508 en Sensors © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering Anomaly detection Deep learning networks |
spellingShingle |
Engineering Anomaly detection Deep learning networks Peng, Xinggan Li, Hanhui Lin, Yuxuan Chen, Yongming Fan, Peng Lin, Zhiping TCF-Trans: temporal context fusion transformer for anomaly detection in time series |
description |
Anomaly detection tasks involving time-series signal processing have been important research topics for decades. In many real-world anomaly detection applications, no specific distributions fit the data, and the characteristics of anomalies are different. Under these circumstances, the detection algorithm requires excellent learning ability of the data features. Transformers, which apply the self-attention mechanism, have shown outstanding performances in modelling long-range dependencies. Although Transformer based models have good prediction performance, they may be influenced by noise and ignore some unusual details, which are significant for anomaly detection. In this paper, a novel temporal context fusion framework: Temporal Context Fusion Transformer (TCF-Trans), is proposed for anomaly detection tasks with applications to time series. The original feature transmitting structure in the decoder of Informer is replaced with the proposed feature fusion decoder to fully utilise the features extracted from shallow and deep decoder layers. This strategy prevents the decoder from missing unusual anomaly details while maintaining robustness from noises inside the data. Besides, we propose the temporal context fusion module to adaptively fuse the generated auxiliary predictions. Extensive experiments on public and collected transportation datasets validate that the proposed framework is effective for anomaly detection in time series. Additionally, the ablation study and a series of parameter sensitivity experiments show that the proposed method maintains high performance under various experimental settings. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Peng, Xinggan Li, Hanhui Lin, Yuxuan Chen, Yongming Fan, Peng Lin, Zhiping |
format |
Article |
author |
Peng, Xinggan Li, Hanhui Lin, Yuxuan Chen, Yongming Fan, Peng Lin, Zhiping |
author_sort |
Peng, Xinggan |
title |
TCF-Trans: temporal context fusion transformer for anomaly detection in time series |
title_short |
TCF-Trans: temporal context fusion transformer for anomaly detection in time series |
title_full |
TCF-Trans: temporal context fusion transformer for anomaly detection in time series |
title_fullStr |
TCF-Trans: temporal context fusion transformer for anomaly detection in time series |
title_full_unstemmed |
TCF-Trans: temporal context fusion transformer for anomaly detection in time series |
title_sort |
tcf-trans: temporal context fusion transformer for anomaly detection in time series |
publishDate |
2024 |
url |
https://hdl.handle.net/10356/173799 |
_version_ |
1794549311465324544 |