Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Anomaly Detection for Temporal Data using Long Short-Term Memory (LSTM)
KTH, School of Information and Communication Technology (ICT).
2017 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

We explore the use of Long short-term memory (LSTM) for anomaly detection in temporal data. Due to the challenges in obtaining labeled anomaly datasets, an unsupervised approach is employed. We train recurrent neural networks (RNNs) with LSTM units to learn the normal time series patterns and predict future values. The resulting prediction errors are modeled to give anomaly scores. We investigate different ways of maintaining LSTM state, and the effect of using a fixed number of time steps on LSTM prediction and detection performance. LSTMs are also compared to feed-forward neural networks with fixed size time windows over inputs. Our experiments, with three real-world datasets, show that while LSTM RNNs are suitable for general purpose time series modeling and anomaly detection, maintaining LSTM state is crucial for getting desired results. Moreover, LSTMs may not be required at all for simple time series.

Abstract [sv]

Vi undersöker Long short-term memory (LSTM) för avvikelsedetektion i tidsseriedata. På grund av svårigheterna i att hitta data med etiketter så har ett oövervakat an-greppssätt använts. Vi tränar rekursiva neuronnät (RNN) med LSTM-noder för att lära modellen det normala tidsseriemönstret och prediktera framtida värden. Vi undersö-ker olika sätt av att behålla LSTM-tillståndet och effekter av att använda ett konstant antal tidssteg på LSTM-prediktionen och avvikelsedetektionsprestandan. LSTM är också jämförda med vanliga neuronnät med fasta tidsfönster över indata. Våra experiment med tre verkliga datasetvisar att även om LSTM RNN är tillämpbara för generell tidsseriemodellering och avvikelsedetektion så är det avgörande att behålla LSTM-tillståndet för att få de önskaderesultaten. Dessutom är det inte nödvändigt att använda LSTM för enkla tidsserier.

Place, publisher, year, edition, pages
2017. , p. 52
Series
TRITA-ICT-EX ; 2017:124
Keywords [en]
LSTM; RNN; anomaly detection; time series; deep learning
Keywords [sv]
LSTM; RNN; avvikelsedetektion; tidsserier; djupt lärande
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-215723OAI: oai:DiVA.org:kth-215723DiVA, id: diva2:1149130
Subject / course
Computer Science
Educational program
Master of Science - Computer Science
Examiners
Available from: 2017-10-13 Created: 2017-10-13 Last updated: 2018-01-13Bibliographically approved

Open Access in DiVA

fulltext(2626 kB)5349 downloads
File information
File name FULLTEXT01.pdfFile size 2626 kBChecksum SHA-512
9b05a1050c1c5ee255b4f825023bbbf1c1bd0ce1c8feffbb54526874b0250ab71d63a020fc44ff19130ccf894fe3a1adb450156abff9870aafdfc9ab6342cdf7
Type fulltextMimetype application/pdf

By organisation
School of Information and Communication Technology (ICT)
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 5349 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 21958 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf