Denoising Recurrent Neural Networks for Classifying Crash-Related Events

Cited 3 time in webofscience Cited 3 time in scopus
  • Hit : 330
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorPark, Sungjoonko
dc.contributor.authorSeonwoo, Yeonko
dc.contributor.authorKim, Jiseonko
dc.contributor.authorKim, Jooyeonko
dc.contributor.authorOh, Aliceko
dc.date.accessioned2021-03-26T02:52:47Z-
dc.date.available2021-03-26T02:52:47Z-
dc.date.created2020-07-20-
dc.date.created2020-07-20-
dc.date.issued2020-07-
dc.identifier.citationIEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, v.21, no.7, pp.2906 - 2917-
dc.identifier.issn1524-9050-
dc.identifier.urihttp://hdl.handle.net/10203/281982-
dc.description.abstractWith detailed sensor and visual data from automobiles, a data-driven model can learn to classify crash-related events during a drive. We propose a neural network model accepting time-series vehicle sensor data and forward-facing videos as input for learning classification of crash-related events and varying types of such events. To elaborate, a novel recurrent neural network structure is introduced, namely, denoising gated recurrent unit with decay, in order to deal with time-series automobile sensor data with missing value and noises. Our model detects crash and near-crash events based on a large set of time-series data collected from naturalistic driving behavior. Furthermore, the model classifies those events involving pedestrians, a vehicle in front, or a vehicle on either side. The effectiveness of our model is evaluated with more than two thousand 30-s clips from naturalistic driving behavior data. The results show that the model, including sensory encoder with denoising gated recurrent unit with decay, visual encoder, and attention mechanism, outperforms gated recurrent unit with decay, gated CNN, and other baselines not only in event classification and but also in event-type classification.-
dc.languageEnglish-
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC-
dc.titleDenoising Recurrent Neural Networks for Classifying Crash-Related Events-
dc.typeArticle-
dc.identifier.wosid000545516200018-
dc.identifier.scopusid2-s2.0-85087658286-
dc.type.rimsART-
dc.citation.volume21-
dc.citation.issue7-
dc.citation.beginningpage2906-
dc.citation.endingpage2917-
dc.citation.publicationnameIEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS-
dc.identifier.doi10.1109/TITS.2019.2921722-
dc.contributor.localauthorOh, Alice-
dc.description.isOpenAccessY-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorData models-
dc.subject.keywordAuthorNoise reduction-
dc.subject.keywordAuthorAccidents-
dc.subject.keywordAuthorVideos-
dc.subject.keywordAuthorRecurrent neural networks-
dc.subject.keywordAuthorTask analysis-
dc.subject.keywordAuthorRecurrent neural networks-
dc.subject.keywordAuthormissing data imputation-
dc.subject.keywordAuthordenoising sensor inputs-
dc.subject.keywordAuthordriving events-
dc.subject.keywordPlusDRIVER-
dc.subject.keywordPlusMODEL-
Appears in Collection
CS-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 3 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0