Seq2Seq 오토인코더 기반의 이상 이동경로 탐지Anomalous Trajectory Detection Based on Seq2Seq Auto-Encoder

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 112
  • Download : 0
DC FieldValueLanguage
dc.contributor.author김현수ko
dc.contributor.author강준혁ko
dc.contributor.author문호원ko
dc.contributor.author이재길ko
dc.date.accessioned2020-11-16T05:55:42Z-
dc.date.available2020-11-16T05:55:42Z-
dc.date.created2020-11-04-
dc.date.created2020-11-04-
dc.date.created2020-11-04-
dc.date.issued2020-03-
dc.identifier.citation대한공간정보학회지, v.28, no.1, pp.35 - 40-
dc.identifier.issn1598-2955-
dc.identifier.urihttp://hdl.handle.net/10203/277310-
dc.description.abstractRNN model has become a specialized model for time-series data by showing outstanding performance in various application fields that use the time-series data. However, unlike the common time-series data, the trajectory data is a spatio-temporal data that contains both spatial and temporal information so the trajectory data requires a specialized methodology for feature extraction that utilizes both spatial and temporal characteristics. Because simply constructing a RNN type model is insufficient for efficient feature extraction, we propose Seq2Seq Auto-Encoder based model that effectively captures distinctive high-quality features and movement characteristics from the trajectories. Our proposed Seq2Seq Auto-Encoder based model to extract complicated movement features and use extracted feature vectors to detect outlying trajectories.-
dc.languageEnglish-
dc.publisher대한공간정보학회-
dc.titleSeq2Seq 오토인코더 기반의 이상 이동경로 탐지-
dc.title.alternativeAnomalous Trajectory Detection Based on Seq2Seq Auto-Encoder-
dc.typeArticle-
dc.type.rimsART-
dc.citation.volume28-
dc.citation.issue1-
dc.citation.beginningpage35-
dc.citation.endingpage40-
dc.citation.publicationname대한공간정보학회지-
dc.identifier.doi10.7319/kogsis.2020.28.1.035-
dc.identifier.kciidART002571365-
dc.contributor.localauthor이재길-
dc.contributor.nonIdAuthor김현수-
dc.contributor.nonIdAuthor문호원-
dc.description.isOpenAccessN-
Appears in Collection
CS-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0