Loading...
Pattern discovery in time series using autoencoder in comparison to nonlearning approaches
Noering, Fabian Kai Dietrich Schroeder, Yannik Jonas, Konstantin
Noering, Fabian Kai Dietrich
Schroeder, Yannik
Jonas, Konstantin
Citations
Altmetric:
Advisors
Editors
Other Contributors
Issue Date
2021-01-01
Submitted date
Files
Loading...
accepted manuscript
Adobe PDF, 15.17 MB
Other Titles
Abstract
In technical systems the analysis of similar situations is a promising technique to gain information about the system's state, its health or wearing. Very often, situations cannot be defined but need to be discovered as recurrent patterns within time series data of the system under consideration. This paper addresses the assessment of different approaches to discover frequent variable-length patterns in time series. Because of the success of artificial neural networks (NN) in various research fields, a special issue of this work is the applicability of NNs to the problem of pattern discovery in time series. Therefore we applied and adapted a Convolutional Autoencoder and compared it to classical nonlearning approaches based on Dynamic Time Warping, based on time series discretization as well as based on the Matrix Profile. These nonlearning approaches have also been adapted, to fulfill our requirements like the discovery of potentially time scaled patterns from noisy time series. We showed the performance (quality, computing time, effort of parametrization) of those approaches in an extensive test with synthetic data sets. Additionally the transferability to other data sets is tested by using real life vehicle data. We demonstrated the ability of Convolutional Autoencoders to discover patterns in an unsupervised way. Furthermore the tests showed, that the Autoencoder is able to discover patterns with a similar quality like classical nonlearning approaches. © 2021 - IOS Press. All rights reserved.
Citation
(2021)Integrated Computer-Aided Engineering; 28(3): 237-256. DOI: 10.3233/ICA-210650.
Publisher
PubMed ID
PubMed Central ID
Additional Links
Embedded video
Type
Article
Language
en
Description
Series/Report no.
ISSN
10692509
EISSN
18758835
ISBN
ISMN
Gov't Doc #
Sponsors
License
Attribution 4.0 International