Chapter
Jul 2, 2019
Traffic Crash Forensic Analysis Based on Univariate Feature Selection
Authors: Shaohua Wang [email protected], Yanyan Chen [email protected], Jianling Huang [email protected], Jianming Ma [email protected], and Yao Lu [email protected]Author Affiliations
Publication: CICTP 2019
Abstract
In China, determining which party is liable for damages or injuries resulting from a traffic crash involving both a motor vehicle and a cyclist can be challenging. Based on an analysis of traffic crash data, this paper has proposed a univariate feature selection method which can emulate human thinking and help determine the moving status of the cyclist prior to the collision. This research employed support vector machines (SVM), LDA, and artificial neural network (ANN) to classify the moving status of the cyclists. According to the analysis results, the SVM (kernel=linear) had the highest classification accuracy (81.84%). It could be used to determine if the cyclist was walking the bicycle prior to the collision.
Get full access to this chapter
View all available purchase options and get full access to this chapter.
Information & Authors
Information
Published In
CICTP 2019
Pages: 5458 - 5470
Copyright
© 2019 American Society of Civil Engineers.
History
Published online: Jul 2, 2019
Permissions
Request permissions for this article.
Authors
Affiliations
Beijing Key Lab of Traffic Engineering, Beijing Univ. of Technology, Beijing ST 100124, China. E-mail: [email protected]
Beijing Key Lab of Traffic Engineering, Beijing Univ. of Technology, Beijing ST 100124, China. E-mail: [email protected]
Beijing Transportation Information Center, Beijing ST 100161, China. E-mail: [email protected]
The Texas Dept. of Transportation, Austin, TX 78717. E-mail: [email protected]
Beijing Key Lab of Traffic Engineering, Beijing Univ. of Technology, Beijing ST 100124, China. E-mail: [email protected]
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
View Options
Get Access
Access content
Please select your options to get access
Log in/Register
Log in via your institution (Shibboleth)
ASCE Members:
Please log in to see member pricing
Purchase
Save for later Item saved, go to cart Information on ASCE Library Cards
ASCE Library Cards let you download journal articles, proceedings papers, and available book chapters across the entire ASCE Library platform. ASCE Library Cards remain active for 24 months or until all downloads are used. Note: This content will be debited as one download at time of checkout.
Terms of Use: ASCE Library Cards are for individual, personal use only. Reselling, republishing, or forwarding the materials to libraries or reading rooms is prohibited.
Terms of Use: ASCE Library Cards are for individual, personal use only. Reselling, republishing, or forwarding the materials to libraries or reading rooms is prohibited.
Get Access
Access content
Please select your options to get access
Log in/Register
Log in via your institution (Shibboleth)
ASCE Members:
Please log in to see member pricing
Purchase
Save for later Item saved, go to cart Information on ASCE Library Cards
ASCE Library Cards let you download journal articles, proceedings papers, and available book chapters across the entire ASCE Library platform. ASCE Library Cards remain active for 24 months or until all downloads are used. Note: This content will be debited as one download at time of checkout.
Terms of Use: ASCE Library Cards are for individual, personal use only. Reselling, republishing, or forwarding the materials to libraries or reading rooms is prohibited.
Terms of Use: ASCE Library Cards are for individual, personal use only. Reselling, republishing, or forwarding the materials to libraries or reading rooms is prohibited.