MERLIN: Parameter-Free Discovery of Arbitrary Length Anomalies in Massive Time Series Archives

Nakamura, Takaaki; Imamura, Makoto; Mercer, Ryan; Keogh, Eamonn

doi:10.1109/icdm50108.2020.00147

Cited by 51 publications

(63 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare TranAD with state-of-the-art models for mutlivariate time-series anomaly detection, including MERLIN [37], LSTM-NDT [20] (with autoencoder implementation from openGauss [30]), DAGMM [65], OmniAnomaly [45], MSCRED [60], MAD-GAN [29], USAD [4], MTAD-GAT [62], CAE-M [61] and GDN [14] (with graph embedding implementation from GraphAn [9]) . For more details refer Section 2.…”

Section: Methodsmentioning

confidence: 99%

“…Time-series discord discovery is another recently proposed method for fault prediction [16,37,58,59]. Time series discords refer to the most unusual time series subsequences, i.e., subsequences that are maximally different from all other subsequences in the same time series.…”

Section: Related Workmentioning

confidence: 99%

“…(1) Numenta Anomaly Benchmark (NAB): is a dataset of multiple real-world data traces, including readings from temperature sensors, CPU utilization of cloud machines, service request latencies and taxi demands in New York city [2]. However, this dataset is known to have sequences with incorrect anomaly labels such as the nyc-taxi trace [37], which we exclude in our experiments. ( 2) HexagonML (UCR) dataset: is a dataset of multiple univariate time series (included just for completeness) that was used in KDD 2021 cup [13,26].…”

Section: Datasetsmentioning

confidence: 99%

“…(5) Mars Science Laboratory (MSL) dataset: is a dataset similar to SMAP but corresponds to the sensor and actuator data for the Mars rover itself [20]. However, this dataset is known to have many trivial sequences; hence, we consider only the three nontrivial ones (A4, C2 and T1) pointed out by [37].…”

Section: Datasetsmentioning

confidence: 99%

See 3 more Smart Citations

TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data

Tuli¹,

Casale²,

Jennings³

2022

Preprint

View full text Add to dashboard Cite

Efficient anomaly detection and diagnosis in multivariate timeseries data is of great importance for modern industrial applications. However, building a system that is able to quickly and accurately pinpoint anomalous observations is a challenging problem. This is due to the lack of anomaly labels, high data volatility and the demands of ultra-low inference times in modern applications. Despite the recent developments of deep learning approaches for anomaly detection, only a few of them can address all of these challenges. In this paper, we propose TranAD, a deep transformer network based anomaly detection and diagnosis model which uses attentionbased sequence encoders to swiftly perform inference with the knowledge of the broader temporal trends in the data. TranAD uses focus score-based self-conditioning to enable robust multi-modal feature extraction and adversarial training to gain stability. Additionally, model-agnostic meta learning (MAML) allows us to train the model using limited data. Extensive empirical studies on six publicly available datasets demonstrate that TranAD can outperform state-of-the-art baseline methods in detection and diagnosis performance with data and time-efficient training. Specifically, TranAD increases F1 scores by up to 17%, reducing training times by up to 99% compared to the baselines.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

See 2 more Smart Citations

TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data

Tuli¹,

Casale²,

Jennings³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Having said that, perhaps 10% of the examples in the NASA archive are challenging, although even those examples do not need to avail of the power of deep learning, as the yield to decade-old simple ideas [18].…”

Section: Fig 2 (Top To Bottom)mentioning

confidence: 99%

Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progress

Wu¹,

Keogh²

2021

IEEE Trans. Knowl. Data Eng.

Self Cite

View full text Add to dashboard Cite

Time series anomaly detection has been a perennially important topic in data science, with papers dating back to the 1950s. However, in recent years there has been an explosion of interest in this topic, much of it driven by the success of deep learning in other domains and for other time series tasks. Most of these papers test on one or more of a handful of popular benchmark datasets, created by Yahoo, Numenta, NASA, etc. In this work we make a surprising claim. The majority of the individual exemplars in these datasets suffer from one or more of four flaws. Because of these four flaws, we believe that many published comparisons of anomaly detection algorithms may be unreliable, and more importantly, much of the apparent progress in recent years may be illusionary. In addition to demonstrating these claims, with this paper we introduce the UCR Time Series Anomaly Datasets. We believe that this resource will perform a similar role as the UCR Time Series Classification Archive, by providing the community with a benchmark that allows meaningful comparisons between approaches and a meaningful gauge of overall progress.

show abstract

TSI-GAN: Unsupervised Time Series Anomaly Detection Using Convolutional Cycle-Consistent Generative Adversarial Networks

Saravanan

Luo

Ngo

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

MERLIN: Parameter-Free Discovery of Arbitrary Length Anomalies in Massive Time Series Archives

Cited by 51 publications

References 10 publications

TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data

TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data

Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progress

TSI-GAN: Unsupervised Time Series Anomaly Detection Using Convolutional Cycle-Consistent Generative Adversarial Networks

Contact Info

Product

Resources

About