File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: An adaptive vehicle rear-end collision warning algorithm based on neural network

TitleAn adaptive vehicle rear-end collision warning algorithm based on neural network
Authors
KeywordsAdaptive
Nerual Network
Rear-End Collision
Warning Algorithm
Issue Date2011
Citation
Communications In Computer And Information Science, 2011, v. 236 CCIS PART 6, p. 305-314 How to Cite?
AbstractMost of the existing algorithms of vehicle rear-end collision have poor adaptive, high false alarm and missed alarm rates. A two-level early warning model based on logic algorithm of safe distance is discussed. The influence of road conditions, driver status and vehicle performance on the warning distance of rear-end collision in the driving process is analyzed. And for different driving conditions, a warning algorithm of vehicle rear-end collision based on neural network with adaptive threshold which can adapt to different status of the three main elements, human-vehicle-road is proposed. Also the comparison of the warning distance whether using adaptive strategies for the rear-end collision algorithm through changing the real-time status of human-vehicle-road is presented. The result of the simulation shows that the algorithm proposed is self-adaptive to the warning distance and region, and the feasibility of the algorithm is verified. © 2011 Springer-Verlag.
Persistent Identifierhttp://hdl.handle.net/10722/168876
ISSN
2015 SCImago Journal Rankings: 0.149
References

 

DC FieldValueLanguage
dc.contributor.authorWei, Zen_US
dc.contributor.authorXiang, Sen_US
dc.contributor.authorXuan, Den_US
dc.contributor.authorXu, Len_US
dc.date.accessioned2012-10-08T03:35:21Z-
dc.date.available2012-10-08T03:35:21Z-
dc.date.issued2011en_US
dc.identifier.citationCommunications In Computer And Information Science, 2011, v. 236 CCIS PART 6, p. 305-314en_US
dc.identifier.issn1865-0929en_US
dc.identifier.urihttp://hdl.handle.net/10722/168876-
dc.description.abstractMost of the existing algorithms of vehicle rear-end collision have poor adaptive, high false alarm and missed alarm rates. A two-level early warning model based on logic algorithm of safe distance is discussed. The influence of road conditions, driver status and vehicle performance on the warning distance of rear-end collision in the driving process is analyzed. And for different driving conditions, a warning algorithm of vehicle rear-end collision based on neural network with adaptive threshold which can adapt to different status of the three main elements, human-vehicle-road is proposed. Also the comparison of the warning distance whether using adaptive strategies for the rear-end collision algorithm through changing the real-time status of human-vehicle-road is presented. The result of the simulation shows that the algorithm proposed is self-adaptive to the warning distance and region, and the feasibility of the algorithm is verified. © 2011 Springer-Verlag.en_US
dc.languageengen_US
dc.relation.ispartofCommunications in Computer and Information Scienceen_US
dc.subjectAdaptiveen_US
dc.subjectNerual Networken_US
dc.subjectRear-End Collisionen_US
dc.subjectWarning Algorithmen_US
dc.titleAn adaptive vehicle rear-end collision warning algorithm based on neural networken_US
dc.typeConference_Paperen_US
dc.identifier.emailXiang, S:sxiang@hkucc.hku.hken_US
dc.identifier.authorityXiang, S=rp00816en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.doi10.1007/978-3-642-24097-3_46en_US
dc.identifier.scopuseid_2-s2.0-80052818115en_US
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-80052818115&selection=ref&src=s&origin=recordpageen_US
dc.identifier.volume236 CCISen_US
dc.identifier.issuePART 6en_US
dc.identifier.spage305en_US
dc.identifier.epage314en_US
dc.identifier.scopusauthoridWei, Z=37123082100en_US
dc.identifier.scopusauthoridXiang, S=36194404300en_US
dc.identifier.scopusauthoridXuan, D=52063903900en_US
dc.identifier.scopusauthoridXu, L=52063900000en_US

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats