Developing an Unsupervised Real-Time Anomaly Detection Scheme for Time Series With Multi-Seasonality

Wu, Wentai; He, Ligang; Lin, Weiwei; Su, Yi; Cui, Yuhua; Maple, Carsten; Jarvis, Stephen A.

doi:10.1109/tkde.2020.3035685

Cited by 39 publications

(9 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Basak et al [39] analyzed the cascade effects of traffic congestion using a citywide ensemble of intersection level connected LSTM models and demonstrated a Timed Failure Propagation Graph-based diagnostics mechanism in [40]. The major drawback of these attempts is that the forecasting accuracy is likely to be affected by anomalies when training models with polluted datasets [41], leading to unreliable anomaly detection results. In this case, the encoder-decoder structure was embedded in LSTM networks, known as sequence-to-sequence (Seq2Seq) prediction models.…”

Section: F Results and Discussion For Server Machine Datamentioning

confidence: 99%

Generative Anomaly Detection for Time Series Datasets

Kang¹,

Mukhopadhyay²,

Gokhale³

et al. 2022

Preprint

View full text Add to dashboard Cite

Section: F Results and Discussion For Server Machine Datamentioning

confidence: 99%

Generative Anomaly Detection for Time Series Datasets

Kang¹,

Mukhopadhyay²,

Gokhale³

et al. 2022

Preprint

View full text Add to dashboard Cite

“…Hundman et al adopted a long short-term memory (LSTM) (Hochreiter and Schmidhuber 1997) to forecast the current time-step-ahead input. Another variant of the recurrent model, the gated recurrent unit (Chung et al 2014), was applied to the forecasting-based TAD (Wu et al 2020).…”

Section: Unsupervised Tadmentioning

confidence: 99%

Towards a Rigorous Evaluation of Time-series Anomaly Detection

Kim¹,

Choi²,

Choi³

et al. 2021

Preprint

View full text Add to dashboard Cite

In recent years, proposed studies on time-series anomaly detection (TAD) report high F1 scores on benchmark TAD datasets, giving the impression of clear improvements. However, most studies apply a peculiar evaluation protocol called point adjustment (PA) before scoring. In this paper, we theoretically and experimentally reveal that the PA protocol has a great possibility of overestimating the detection performance; that is, even a random anomaly score can easily turn into a state-of-the-art TAD method. Therefore, the comparison of TAD methods with F1 scores after the PA protocol can lead to misguided rankings. Furthermore, we question the potential of existing TAD methods by showing that an untrained model obtains comparable detection performance to the existing methods even without PA. Based on our findings, we propose a new baseline and an evaluation protocol. We expect that our study will help a rigorous evaluation of TAD and lead to further improvement in future researches.

show abstract

“…Today, anomaly detection is broadly used in many research areas such as health monitoring [1], [2], [3], [4], [5], [6] for example heart disease diagnosis [1] and neuromuscular disorders diagnosis [5], environment monitoring such as sewer pipeline fault identification [7] and solar farms anomalies detection [8], and machine condition monitoring [9], [10] for example machinery fault diagnosis [11], [12], [13], [14], [9]. Depending on the anomaly detection problem, it is required to design algorithms which are able to identify anomalies in different types of data such as image [15], [2], [16], [17], video [7], sound signal [9] speech signal [18], sensor signal [19], [5], text [20], spatio-temporal data [4], streaming data [21] and time-series [22], [23]. Hence, it seems that no general solution works for all of the anomaly detection problems.…”

Section: Introductionmentioning

confidence: 99%

Developing a Data-Driven Unsupervised Pattern Recognition Approach for Sensor Signal Anomaly Detection

Iranmehr¹,

Ferreira²,

Böhnert³

et al. 2021

Preprint

View full text Add to dashboard Cite

Coming up with a system for early detection of machine damages and failures is one of the important challenges in the industrial maintenance procedure to avoid additional costs and downtimes. To approach this goal, this paper uses the signal gathered by a sensing system which employed a spintropic sensor to measure the magnetic field around the machine which somehow shows the machine's behaviour. Using this signal and focusing on analysing and processing the signal, this paper develops a data-driven method to recognize signal patterns and subsequently detects anomalies. A challenging task that we succeeded to overcome in this paper is recognizing relevant signal patterns without having any prior knowledge. An algorithm designed for this task is therefore completely unsupervised which makes it consistent and suitable to apply it for the signals gathered for other types of machines. Using both frequency and time domain information, the proposed algorithm, which utilizes signal processing and machine learning techniques, is able to efficiently identify relevant signal patterns. Clustering results on the real data gathered by the aforementioned sensor have shown the high accuracy of 99.38% in recognizing patterns. Furthermore, an anomaly score measure is used and according to its distribution, anomalies are detected appropriately. <br>

show abstract

Developing an Unsupervised Real-Time Anomaly Detection Scheme for Time Series With Multi-Seasonality

Abstract: Please refer to published version for the most recent bibliographic citation information. If a published version is known of, the repository item page linked to above, will contain details on accessing it.

Cited by 39 publications

References 43 publications

Generative Anomaly Detection for Time Series Datasets

Generative Anomaly Detection for Time Series Datasets

Towards a Rigorous Evaluation of Time-series Anomaly Detection

Developing a Data-Driven Unsupervised Pattern Recognition Approach for Sensor Signal Anomaly Detection

Contact Info

Product

Resources

About