File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Early car collision prediction in VANET

TitleEarly car collision prediction in VANET
Authors
Wu, QHui, LCKYeung, CYChim, TW
Issue Date2016
PublisherIEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1802714
Citation
The 4th International Conference on Connected Vehicles and Expo (ICCVE 2015), Shenzhen, China, 19-23 October 2015. In Conference Proceedings, 2016, p. 94-99 How to Cite?
DOI: http://dx.doi.org/10.1109/ICCVE.2015.55
AbstractTraffic safety is critical to our lives. In recent years, the increasing traffic accidents have brought considerable deaths. Reducing the rate of car accident has become one of the most important tasks in transportation field. VANET is a widely used platform contributing to possible solutions. In the past, there are protocols to generate or broadcast warning messages after vehicle collision. However, since most of them are made after car accidents have already occurred, they may help accident investigation but do not prevent the accident from taking place. In this paper, we proposed a method using support vector machine(SVM) [1] for early car accident detection in VANET. Once any dangerous situation is predicted, immediately the endangered driver gets a alert along with a suggestion to avoid danger.
Persistent Identifierhttp://hdl.handle.net/10722/234890
ISSN
2378-1297

 

DC FieldValueLanguage
dc.contributor.authorWu, Q-
dc.contributor.authorHui, LCK-
dc.contributor.authorYeung, CY-
dc.contributor.authorChim, TW-
dc.date.accessioned2016-10-14T13:49:55Z-
dc.date.available2016-10-14T13:49:55Z-
dc.date.issued2016-
dc.identifier.citationThe 4th International Conference on Connected Vehicles and Expo (ICCVE 2015), Shenzhen, China, 19-23 October 2015. In Conference Proceedings, 2016, p. 94-99-
dc.identifier.issn2378-1297-
dc.identifier.urihttp://hdl.handle.net/10722/234890-
dc.description.abstractTraffic safety is critical to our lives. In recent years, the increasing traffic accidents have brought considerable deaths. Reducing the rate of car accident has become one of the most important tasks in transportation field. VANET is a widely used platform contributing to possible solutions. In the past, there are protocols to generate or broadcast warning messages after vehicle collision. However, since most of them are made after car accidents have already occurred, they may help accident investigation but do not prevent the accident from taking place. In this paper, we proposed a method using support vector machine(SVM) [1] for early car accident detection in VANET. Once any dangerous situation is predicted, immediately the endangered driver gets a alert along with a suggestion to avoid danger.-
dc.languageeng-
dc.publisherIEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1802714-
dc.relation.ispartofInternational Conference on Connected Vehicles and Expo (ICCVE) Proceedings-
dc.rightsInternational Conference on Connected Vehicles and Expo (ICCVE) Proceedings. Copyright © IEEE.-
dc.rights©2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.-
dc.titleEarly car collision prediction in VANET-
dc.typeConference_Paper-
dc.identifier.emailHui, LCK: hui@cs.hku.hk-
dc.identifier.emailChim, TW: twchim99@hku.hk-
dc.identifier.authorityHui, LCK=rp00120-
dc.identifier.authorityChim, TW=rp01844-
dc.identifier.doi10.1109/ICCVE.2015.55-
dc.identifier.scopuseid_2-s2.0-84966539541-
dc.identifier.hkuros268885-
dc.identifier.spage94-
dc.identifier.epage99-
dc.publisher.placeUnited States-
dc.customcontrol.immutablesml 161107-
dc.identifier.issnl2378-1289-

Export via OAI-PMH Interface in XML Formats

OR

Export to Other Non-XML Formats