Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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
Detecting anomalies in robot time series data using stochastic recurrent networks
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Optimization and Systems Theory.
2015 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
: Anomalidetektion i robot-tidsserier med hjälp av stokastiska återkommande nätverk (Swedish)
Abstract [en]

This thesis proposes a novel anomaly detection algorithm for detect-ing anomalies in high-dimensional, multimodal, real-valued time se-ries data. The approach, requiring no domain knowledge, is based on Stochastic Recurrent Networks (STORNs), a universal distribution approximator for sequential data leveraging the power of Recurrent Neural Networks (RNNs) and Variational Auto-Encoders (VAEs).

The detection algorithm is evaluated on real robot time series data in order to prove that the method robustly detects anomalies off- and on-line.

Abstract [sv]

Detta arbete förslår en ny detektionsalgoritm för anomalier i högdi-mensionell multimodal reellvärd tidsseriedata. Metoden kräver in-gen domänkunskap och baseras på Stochastic Recurrent Networks (STORNs), en teknik för oövervakad och universell fördelningssapprox-imation för sekventiell data som bygger på Recurrent Neural Net-works (RNNs) och Variational Auto-Encoders (VAEs).

Algoritmen utvärderades på robotgenererade tidsserier och slutsat-sen är att metoden på ett robust sätt upptäcker anomalier både offline och online.

Abstract [de]

Anomaliedetektion in Roboterzeitreihen  mittels stochastischer Rekurrenter Netzwerke  

In dieser Arbeit wird ein neuartiger Algorithmus entwickelt, um in hochdimensionalen, multimodalen, reellwertigen Zeitreihen Anomalien zu detektieren. Der Ansatz benötigt keine domänenspezifisches Fachwissen und basiert auf Stochastischen Rekurrenten Netzwerken (STORN), einem universellen Wahrscheinlichkeitsverteilungsapproximator für sequenzielle Daten, der die Stärken von Rekurrenten Neuronalen Netzwerken (RNN) und dem Variational Auto-Encoder (VAE) vereinigt.

Der Detektionsalgorithmus wird auf realen Robotertrajektorien evaluiert. Es wird gezeigt, dass Anomalien robust online und offline gefunden werden können.

Place, publisher, year, edition, pages
2015.
Series
TRITA-MAT-E, 2015:90
National Category
Computational Mathematics
Identifiers
URN: urn:nbn:se:kth:diva-180473OAI: oai:DiVA.org:kth-180473DiVA: diva2:896301
External cooperation
Technische Universität München, Tyskland
Subject / course
Optimization and Systems Theory
Educational program
Master of Science in Engineering -Engineering Physics
Supervisors
Examiners
Available from: 2016-01-20 Created: 2016-01-14 Last updated: 2016-01-20Bibliographically approved

Open Access in DiVA

fulltext(6318 kB)2404 downloads
File information
File name FULLTEXT01.pdfFile size 6318 kBChecksum SHA-512
08e3aedfe1eb630dad5e97077fae1c100cc6ddcca77744d969bf3c6729287a71385d61547af52c8877965892d2060472816e67726acc02c415825ae013ed6e34
Type fulltextMimetype application/pdf

By organisation
Optimization and Systems Theory
Computational Mathematics

Search outside of DiVA

GoogleGoogle Scholar
Total: 2404 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: 552 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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