Unsupervised anomaly detection with LSTM neural networks

Simple item page
buir.contributor.authorKozat, Süleyman Serdar
dc.citation.epage3141en_US
dc.citation.issueNumber8en_US
dc.citation.spage3127en_US
dc.citation.volumeNumber31en_US
dc.contributor.authorErgen, T.
dc.contributor.authorKozat, Süleyman Serdar
dc.date.accessioned2021-02-18T11:19:05Z
dc.date.available2021-02-18T11:19:05Z
dc.date.issued2020
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.description.abstractWe investigate anomaly detection in an unsupervised framework and introduce long short-term memory (LSTM) neural network-based algorithms. In particular, given variable length data sequences, we first pass these sequences through our LSTM-based structure and obtain fixed-length sequences. We then find a decision function for our anomaly detectors based on the one-class support vector machines (OC-SVMs) and support vector data description (SVDD) algorithms. As the first time in the literature, we jointly train and optimize the parameters of the LSTM architecture and the OC-SVM (or SVDD) algorithm using highly effective gradient and quadratic programming-based training methods. To apply the gradient-based training method, we modify the original objective criteria of the OC-SVM and SVDD algorithms, where we prove the convergence of the modified objective criteria to the original criteria. We also provide extensions of our unsupervised formulation to the semisupervised and fully supervised frameworks. Thus, we obtain anomaly detection algorithms that can process variable length data sequences while providing high performance, especially for time series data. Our approach is generic so that we also apply this approach to the gated recurrent unit (GRU) architecture by directly replacing our LSTM-based structure with the GRU-based structure. In our experiments, we illustrate significant performance gains achieved by our algorithms with respect to the conventional methods.en_US
dc.description.sponsorshipThis work was supported by Tubitak Project under Grant 117E153.en_US
dc.identifier.doi10.1109/TNNLS.2019.2935975en_US
dc.identifier.issn2162-237X
dc.identifier.urihttp://hdl.handle.net/11693/75452
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttps://dx.doi.org/10.1109/TNNLS.2019.2935975en_US
dc.source.titleIEEE Transactions on Neural Networks and Learning Systemsen_US
dc.subjectAnomaly detectionen_US
dc.subjectGated recurrent unit (GRU)en_US
dc.subjectLong short-term memory (LSTM)en_US
dc.subjectSupport vector data description (SVDD)en_US
dc.subjectSupport vector machines (SVMs)en_US
dc.titleUnsupervised anomaly detection with LSTM neural networksen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Unsupervised_Anomaly_Detection_With_LSTM_Neural_Networks.pdf
Size:
1.14 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Department of Electrical and Electronics Engineering