Article (Scientific journals)
DDANF: Deep denoising autoencoder normalizing flow for unsupervised multivariate time series anomaly detection
Zhao, Xigang; Liu, Peng; Mahmoudi, Saïd et al.
2024In Alexandria Engineering Journal, 108, p. 436 - 444
Peer Reviewed verified by ORBi
 

Files


Full Text
DDANF Deep denoising autoencoder normalizing flow for unsupervised times series detection.pdf
Author postprint (1.13 MB)
Request a copy

All documents in ORBi UMONS are protected by a user license.

Send to



Details



Keywords :
Anomaly detection; Autoencoder; Normalizing flow; Time series; Adoption of wireless; Auto encoders; De-noising; Multivariate time series; Time-series data; Times series; Unsupervised anomaly detection; Unsupervised method; Engineering (all)
Abstract :
[en] In recent years, the proliferation of IoT technologies and the widespread adoption of wireless sensors across various critical infrastructures such as power plants, service monitoring systems, space and earth exploration missions, and water treatment facilities have resulted in the generation of vast quantities of multivariate time series data. Within this context, unsupervised anomaly detection has emerged as a pivotal yet challenging problem in time series research, necessitating machine learning models capable of identifying rare anomalies amidst massive datasets. Traditionally, unsupervised methods have approached this issue by learning representations of primary patterns within sequences and detecting deviations through reconstruction errors. However, the effectiveness of this approach is often limited due to the intricate dynamics and diverse patterns inherent in these dynamic systems. Moreover, many existing unsupervised anomaly detection techniques fail to fully exploit inter-feature relationships within multivariate time series data, thereby overlooking a crucial criterion for accurate detection. To address these shortcomings, this paper introduces a novel unsupervised method for multivariate time series anomaly detection based on normalized flows and autoencoders. Central to our approach is the incorporation of a channel shuffling mechanism during training, enhancing the model's capacity to discern inter-channel patterns and anomalies. Concurrently, the application of normalized flows within the autoencoder framework serves to constrain the latent space, effectively isolating anomalies and improving detection accuracy. Experimental validation conducted on two large-scale public datasets demonstrates the efficacy of the proposed method compared to established benchmarks, highlighting its superior performance.
Disciplines :
Computer science
Author, co-author :
Zhao, Xigang;  School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China
Liu, Peng ;  School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China
Mahmoudi, Saïd  ;  Université de Mons - UMONS > Faculté Polytechnique > Service Informatique, Logiciel et Intelligence artificielle
Garg, Sahil;  École de technologie supérieure, Montreal, Canada ; Centre for Research Impact & Outcome, Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, India
Kaddoum, Georges ;  École de technologie supérieure, Montreal, Canada
Hassan, Mohammad Mehedi;  Department of Information Systems, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia
Language :
English
Title :
DDANF: Deep denoising autoencoder normalizing flow for unsupervised multivariate time series anomaly detection
Publication date :
December 2024
Journal title :
Alexandria Engineering Journal
ISSN :
1110-0168
Publisher :
Elsevier B.V.
Volume :
108
Pages :
436 - 444
Peer reviewed :
Peer Reviewed verified by ORBi
Research unit :
F114 - Informatique, Logiciel et Intelligence artificielle
Research institute :
R300 - Institut de Recherche en Technologies de l'Information et Sciences de l'Informatique
Funders :
King Saud University
National Natural Science Foundation of China
Funding text :
This work was supported by National Natural Science Foundation of China (No. 62172134 ). The authors are grateful to King Saud University, Riyadh, Saudi Arabia for funding this work through Researchers Supporting Project Number (RSP2024R18).
Available on ORBi UMONS :
since 14 January 2025

Statistics


Number of views
0 (0 by UMONS)
Number of downloads
0 (0 by UMONS)

Scopus citations®
 
2
Scopus citations®
without self-citations
2
OpenCitations
 
0
OpenAlex citations
 
2

Bibliography


Similar publications



Contact ORBi UMONS