Analytical Model for Traffic Congestion and Accident Analysis

Traffic congestion and road accidents have been important public challenges that impose a large burden to the society. According to an annual study from INRIX in 2019, traffic congestion in the urban areas of US is getting worse and the average time lost to traffic increased by two hours from 2017 to 2019. The firm found that the average American lost $1,377 and 99 hours sitting in traffic last year. Road accidents may have even more significant impact to persons’ life depending on the severity of the event. In the US, over 38,000 people die in road crashes each year, and 2.35 million are injured or disabled according to the statistics report from the Association for Safe International Road Travel (ASIRT) in 2020. Road crashes cost U.S. $230.6 billion per year. Road accidents (RTAs) and traffic congestion seem to be very dependent on one another. On one side, road accidents can cause massive traffic congestions in nearby areas that affect the daily life of many. On the other side, some studies suggested that an increase in the road traffic congestion level is likely to cause a higher number of less severe accidents. It is important to understand the association between traffic congestion and road accidents so that effective policies or transportation decision tools can be implemented to improve roadway safety and relieve traffic congestion. The analysis on traffic congestion and road accidents is complex as many factors come into play such as road characteristics, time of the day/week, weather conditions and events that may change in real time. The development of advanced technologies such as GPS and IoT offers great visibilities and transparency of roadway conditions nowadays. The information, if utilized appropriately, can help people understand the impact of factors on traffic congestion and to enable timely transportation decisions to improve mobility of people and goods. In 2015, the U.S. Department of Transportation launched the Smart City Challenge, asking for ideas to create an integrated, first-of-its-kind smart transportation system that would use data, applications, and technology to revolutionize the transportation systems to help improve people’s lives. In response to the aforementioned needs, we propose to use statistical techniques and machine learning algorithms to process and train the large amount of data offered by advanced information technologies to obtain predictive models/application tools for traffic congestion and road accidents. The proposed models/tools incorporate multiple environmental parameter and together with real time data are expected to be more accurate in assisting people making smart real time transportation decisions. The proposed research work consists of the following research tasks. Task 1: Perform exploratory data analysis (EDA) and data processing on US accident and traffic congestion data. Task 2: Develop statistical models using machine learning algorithms to understand the relationship between traffic congestion levels and the frequency, rate, severity and distance of road accidents. Task 3: Assess the impacts of multiple factors such as precipitation, wind chill, temperature, pressure, wind speed, road demographics on traffic congestion and road accidents and improve the model. Task 4: Test model accuracy and compare results

    Language

    • English

    Project

    • Status: Active
    • Funding: $5008
    • Contract Numbers:

      69A3551747127

    • Sponsor Organizations:

      Office of the Assistant Secretary for Research and Technology

      University Transportation Centers Program
      Department of Transportation
      Washington, DC  United States  20590
    • Managing Organizations:

      Office of the Assistant Secretary for Research and Technology

      University Transportation Centers Program
      Department of Transportation
      Washington, DC  United States  20590
    • Performing Organizations:

      Mineta Consortium for Transportation Mobility

      San Jose State University
      San Jose, CA  United States  95112
    • Principal Investigators:

      Liu, Hongrui

    • Start Date: 20200930
    • Expected Completion Date: 20210831
    • Actual Completion Date: 0
    • USDOT Program: University Transportation Centers

    Subject/Index Terms

    Filing Info

    • Accession Number: 01759576
    • Record Type: Research project
    • Source Agency: Mineta Consortium for Transportation Mobility
    • Contract Numbers: 69A3551747127
    • Files: UTC, RiP
    • Created Date: Dec 2 2020 5:25PM