File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Short-term traffic speed forecasting based on data recorded at irregular intervals

TitleShort-term traffic speed forecasting based on data recorded at irregular intervals
Authors
KeywordsAutoregressive integrated moving average (ARIMA)
combined forecasting
exponential smoothing method
Holt's method
irregularly spaced time series data
neural network
short-term traffic speed forecasting
Issue Date2012
Citation
IEEE Transactions on Intelligent Transportation Systems, 2012, v. 13 n. 4, p. 1727-1737 How to Cite?
AbstractRecent growth in demand for proactive real-time transportation management systems has led to major advances in short-time traffic forecasting methods. Recent studies have introduced time series theory, neural networks, and genetic algorithms to short-term traffic forecasting to make forecasts more reliable, efficient, and accurate. However, most of these methods can only deal with data recorded at regular time intervals, which restricts the range of data collection tools to presence-type detectors or other equipment that generates regular data. The study reported here is an attempt to extend several existing time series forecasting methods to accommodate data recorded at irregular time intervals, which would allow transportation management systems to obtain predicted traffic speeds from intermittent data sources such as Global Positioning System (GPS). To improve forecasting performance, acceleration information was introduced, and information from segments adjacent to the current forecasting segment was adopted. The study tested several methods using GPS data from 480 Hong Kong taxis. The results show that the best performance in terms of mean absolute relative error is obtained by using a neural network model that aggregates speed information and acceleration information from the current forecasting segment and adjacent segments.
Persistent Identifierhttp://hdl.handle.net/10722/152648
ISSN
2023 Impact Factor: 7.9
2023 SCImago Journal Rankings: 2.580
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorYe, Qen_US
dc.contributor.authorSzeto, WYen_US
dc.contributor.authorWong, SCen_US
dc.date.accessioned2012-07-16T09:45:03Z-
dc.date.available2012-07-16T09:45:03Z-
dc.date.issued2012en_US
dc.identifier.citationIEEE Transactions on Intelligent Transportation Systems, 2012, v. 13 n. 4, p. 1727-1737en_US
dc.identifier.issn1524-9050-
dc.identifier.urihttp://hdl.handle.net/10722/152648-
dc.description.abstractRecent growth in demand for proactive real-time transportation management systems has led to major advances in short-time traffic forecasting methods. Recent studies have introduced time series theory, neural networks, and genetic algorithms to short-term traffic forecasting to make forecasts more reliable, efficient, and accurate. However, most of these methods can only deal with data recorded at regular time intervals, which restricts the range of data collection tools to presence-type detectors or other equipment that generates regular data. The study reported here is an attempt to extend several existing time series forecasting methods to accommodate data recorded at irregular time intervals, which would allow transportation management systems to obtain predicted traffic speeds from intermittent data sources such as Global Positioning System (GPS). To improve forecasting performance, acceleration information was introduced, and information from segments adjacent to the current forecasting segment was adopted. The study tested several methods using GPS data from 480 Hong Kong taxis. The results show that the best performance in terms of mean absolute relative error is obtained by using a neural network model that aggregates speed information and acceleration information from the current forecasting segment and adjacent segments.-
dc.languageengen_US
dc.relation.ispartofIEEE Transactions on Intelligent Transportation Systemsen_US
dc.subjectAutoregressive integrated moving average (ARIMA)-
dc.subjectcombined forecasting-
dc.subjectexponential smoothing method-
dc.subjectHolt's method-
dc.subjectirregularly spaced time series data-
dc.subjectneural network-
dc.subjectshort-term traffic speed forecasting-
dc.titleShort-term traffic speed forecasting based on data recorded at irregular intervalsen_US
dc.typeArticleen_US
dc.identifier.emailSzeto, WY: ceszeto@hku.hken_US
dc.identifier.emailWong, SC: hhecwsc@hku.hken_US
dc.identifier.authoritySzeto, WY=rp01377en_US
dc.identifier.authorityWong, SC=rp00191en_US
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TITS.2012.2203122-
dc.identifier.scopuseid_2-s2.0-84870549790-
dc.identifier.hkuros201975en_US
dc.identifier.volume13-
dc.identifier.issue4-
dc.identifier.spage1727-
dc.identifier.epage1737-
dc.identifier.eissn1558-0016-
dc.identifier.isiWOS:000314291400023-
dc.identifier.issnl1524-9050-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats