Skip to content

shengbo-ma/Prediction-of-Traffic-Crash-Risk

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

43 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Prediction of Traffic Crash Risk

Abstract

Traffic crash is not only an major topic in Geographic AI, but also directly related to people's daily life. Nearly 1.3 million people die internationally every year from car accidents and in addition up to 50 million people are injured. Machine learning can be a helpful tool to analyze and reduce the risk of crashes. In this work, an data analysis is demonstrated on Chicago traffic crashes (20016-2018), followed by a prediction of risk and severity of crashes based on random forrest model. This work is a promising application for safe route planning, emergency vehicle allocation, roadway design and where to place additional traffic control devices.

Data Source

Traffic crash data can be obtained at Chicago Data Portal, using SODA API or exporting directly from the website. The links and descriptions of datasets are listed below:

  1. Traffic Crashes - Crashes: Major dataset for this project.
  2. Traffic Crashes - Vehicles: Information of related vehicles.
  3. Traffic Crashes - People:Information of related people.
  4. Chicago Traffic Tracker - Congestion Estimates by Segments: Geo information of traffic segments of Chicago arterial streets (nonfreeway streets).
  5. Chicago Traffic Tracker - Congestion Estimates by Regions: Geo information of Chicago Regions.

Results

Please see this notebook: Chicago_Traffic_Crashes.ipynb. IF it failed to render or displayed incorrectly, here is a backup with better performance.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published