Show simple item record

dc.contributor.authorTambuwal, Ahmad I.
dc.contributor.authorNeagu, Daniel
dc.date.accessioned2021-11-18T20:08:19Z
dc.date.accessioned2021-11-30T09:50:24Z
dc.date.available2021-11-18T20:08:19Z
dc.date.available2021-11-30T09:50:24Z
dc.date.issued2021-09-30
dc.identifier.citationTambuwal AI and Neagu D (2021) Deep Quantile Regression for Unsupervised Anomaly Detection in Time-Series. SN Computer Science. 2: 475.en_US
dc.identifier.urihttp://hdl.handle.net/10454/18658
dc.descriptionYesen_US
dc.description.abstractTime-series anomaly detection receives increasing research interest given the growing number of data-rich application domains. Recent additions to anomaly detection methods in research literature include deep neural networks (DNNs: e.g., RNN, CNN, and Autoencoder). The nature and performance of these algorithms in sequence analysis enable them to learn hierarchical discriminative features and time-series temporal nature. However, their performance is affected by usually assuming a Gaussian distribution on the prediction error, which is either ranked, or threshold to label data instances as anomalous or not. An exact parametric distribution is often not directly relevant in many applications though. This will potentially produce faulty decisions from false anomaly predictions due to high variations in data interpretation. The expectations are to produce outputs characterized by a level of confidence. Thus, implementations need the Prediction Interval (PI) that quantify the level of uncertainty associated with the DNN point forecasts, which helps in making better-informed decision and mitigates against false anomaly alerts. An effort has been made in reducing false anomaly alerts through the use of quantile regression for identification of anomalies, but it is limited to the use of quantile interval to identify uncertainties in the data. In this paper, an improve time-series anomaly detection method called deep quantile regression anomaly detection (DQR-AD) is proposed. The proposed method go further to used quantile interval (QI) as anomaly score and compare it with threshold to identify anomalous points in time-series data. The tests run of the proposed method on publicly available anomaly benchmark datasets demonstrate its effective performance over other methods that assumed Gaussian distribution on the prediction or reconstruction cost for detection of anomalies. This shows that our method is potentially less sensitive to data distribution than existing approaches.en_US
dc.description.sponsorshipPetroleum Technology Development Fund (PTDF) PhD Scholarship, Nigeria (Award Number: PTDF/ ED/PHD/IAT/884/16)en_US
dc.language.isoenen_US
dc.publisherSpringer
dc.rights(c) 2021 The Authors. This is an Open Access article distributed under the Creative Commons CC-BY license (http://creativecommons.org/licenses/by/4.0/)en_US
dc.subjectTime-seriesen_US
dc.subjectAnomaly detectionen_US
dc.subjectPrediction intervalen_US
dc.subjectDeep neural networksen_US
dc.subjectLong short-term memoryen_US
dc.subjectQuantile regressionen_US
dc.titleDeep Quantile Regression for Unsupervised Anomaly Detection in Time-Seriesen_US
dc.status.refereedYesen_US
dc.date.Accepted2021-09-08
dc.typeArticleen_US
dc.type.versionPublished versionen_US
dc.identifier.doihttps://doi.org/10.1007/s42979-021-00866-4
dc.date.updated2021-11-18T20:08:29Z
refterms.dateFOA2021-11-30T09:50:49Z
dc.openaccess.statusGolden_US


Item file(s)

Thumbnail
Name:
Tambuwal-Neagu2021_Article_Dee ...
Size:
2.234Mb
Format:
PDF
Description:
tambuwal_and_neagu_2021

This item appears in the following Collection(s)

Show simple item record