An Empirical Experiment on Deep Learning Models for Predicting Traffic Data

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 35
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorLee, Hyunwookko
dc.contributor.authorPark, Cheonbokko
dc.contributor.authorJin, Seungminko
dc.contributor.authorChu, Hyeshinko
dc.contributor.authorChoo, Jaegulko
dc.contributor.authorKo, Sungahnko
dc.date.accessioned2021-11-03T06:48:22Z-
dc.date.available2021-11-03T06:48:22Z-
dc.date.created2021-10-26-
dc.date.issued2021-04-
dc.identifier.citation37th IEEE International Conference on Data Engineering (IEEE ICDE), pp.1817 - 1822-
dc.identifier.issn1084-4627-
dc.identifier.urihttp://hdl.handle.net/10203/288665-
dc.description.abstractTo tackle ever-increasing city traffic congestion problems, researchers have proposed deep learning models to aid decision-makers in the traffic control domain. Although the proposed models have been remarkably improved in recent years, there are still questions that need to be answered before deploying models. For example, it is difficult to figure out which models provide state-of-the-art performance, as recently proposed models have often been evaluated with different datasets and experiment environments. It is also difficult to determine which models would work when traffic conditions change abruptly (e.g., rush hour). In this work, we conduct two experiments to answer the two questions. In the first experiment, we conduct an experiment with the state-of-the-art models and the identical public datasets to compare model performance under a consistent experiment environment. We then extract a set of temporal regions in the datasets, whose speeds change abruptly and use these regions to explore model performance with difficult intervals. The experiment results indicate that Graph-WaveNet and GMAN show better performance in general. We also find that prediction models tend to have varying performances with data and intervals, which calls for in-depth analysis of models on difficult intervals for real-world deployment.-
dc.languageEnglish-
dc.publisherIEEE COMPUTER SOC-
dc.titleAn Empirical Experiment on Deep Learning Models for Predicting Traffic Data-
dc.typeConference-
dc.identifier.wosid000687830800152-
dc.identifier.scopusid2-s2.0-85112868573-
dc.type.rimsCONF-
dc.citation.beginningpage1817-
dc.citation.endingpage1822-
dc.citation.publicationname37th IEEE International Conference on Data Engineering (IEEE ICDE)-
dc.identifier.conferencecountryGR-
dc.identifier.conferencelocationChania-
dc.identifier.doi10.1109/ICDE51399.2021.00160-
dc.contributor.localauthorChoo, Jaegul-
dc.contributor.nonIdAuthorLee, Hyunwook-
dc.contributor.nonIdAuthorPark, Cheonbok-
dc.contributor.nonIdAuthorJin, Seungmin-
dc.contributor.nonIdAuthorChu, Hyeshin-
dc.contributor.nonIdAuthorKo, Sungahn-
Appears in Collection
RIMS Conference Papers
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