Outlier Detection for Multidimensional Time Series using Deep Neural Networks

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

150 Citationer (Scopus)

Abstract

Due to the continued digitization of industrial and societal processes, including the deployment of networked sensors, we are witnessing a rapid proliferation of time-ordered observations, known as time series. For example, the behavior of drivers can be captured by GPS or accelerometer as a time series of speeds, directions, and accelerations. We propose a framework for outlier detection in time series that, for example, can be used for identifying dangerous driving behavior and hazardous road locations. Specifically, we first propose a method that generates statistical features to enrich the feature space of raw time series. Next, we utilize an autoencoder to reconstruct the enriched time series. The autoencoder performs dimensionality reduction to capture, using a small feature space, the most representative features of the enriched time series. As a result, the reconstructed time series only capture representative features, whereas outliers often have non-representative features. Therefore, deviations of the enriched time series from the reconstructed time series can be taken as indicators of outliers. We propose and study autoencoders based on convolutional neural networks and long-short term memory neural networks. In addition, we show that embedding of contextual information into the framework has the potential to further improve the accuracy of identifying outliers. We report on empirical studies with multiple time series data sets, which offers insight into the design properties of the proposed framework, indicating that it is effective at detecting outliers.

OriginalsprogEngelsk
TitelProceedings of the 19th IEEE International Conference on Mobile Data Management, MDM 2018
Antal sider10
Vol/bind2018-June
ForlagIEEE
Publikationsdato13 jul. 2018
Sider125-134
ISBN (Elektronisk)9781538641330
DOI
StatusUdgivet - 13 jul. 2018
Begivenhed19th IEEE International Conference on Mobile Data Management, MDM 2018 - Aalborg, Danmark
Varighed: 25 jun. 201828 jun. 2018

Konference

Konference19th IEEE International Conference on Mobile Data Management, MDM 2018
Land/OmrådeDanmark
ByAalborg
Periode25/06/201828/06/2018
SponsorAalborg University, Center for Data-Intensive Systems (DAISY), Aalborg University, IEEE, IEEE Technical Committee on Data Engineering (TCDE), Otto Monsted Foundation
NavnIEEE International Conference on Mobile Data Management (MDM)
ISSN2375-0324

Fingeraftryk

Dyk ned i forskningsemnerne om 'Outlier Detection for Multidimensional Time Series using Deep Neural Networks'. Sammen danner de et unikt fingeraftryk.

Citationsformater