<rss version="2.0" xmlns:atom="https://www.w3.org/2005/Atom">
  <channel>
    <title>Research in Progress (RIP)</title>
    <link>https://rip.trb.org/</link>
    <atom:link href="https://rip.trb.org/Record/RSS?s=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" rel="self" type="application/rss+xml" />
    <description></description>
    <language>en-us</language>
    <copyright>Copyright © 2026. National Academy of Sciences. All rights reserved.</copyright>
    <docs>http://blogs.law.harvard.edu/tech/rss</docs>
    <managingEditor>tris-trb@nas.edu (Bill McLeod)</managingEditor>
    <webMaster>tris-trb@nas.edu (Bill McLeod)</webMaster>
    <image>
      <title>Research in Progress (RIP)</title>
      <url>https://rip.trb.org/Images/PageHeader-wTitle-RIP.jpg</url>
      <link>https://rip.trb.org/</link>
    </image>
    <item>
      <title>Disability, Mode Perceptions, and Travel Behavior</title>
      <link>https://rip.trb.org/View/2695812</link>
      <description><![CDATA[Despite the more than three decades since the passage of the Americans with Disabilities Act (ADA), people with disabilities, which comprise roughly one quarter of the US population, still face considerable challenges to their mobility and access. They make fewer trips and are more dependent on others because of deficiencies in pedestrian infrastructure, transit and for-hire vehicles, and specialized paratransit services. While there is a considerable amount of research that identifies the breadth of mobility challenges and access barriers, limited research has addressed how these mobility challenges influence mode choice for people with disabilities. This project will develop and administer a web-based survey by oversampling California residents with disabilities to understand how disability influences mode choice, accounting for perceptions of the built environment and mode-specific challenges. The research team anticipates using several analytical methods to answer the research questions, including descriptive statistics, basic statistical tests of comparison, and multinomial logistic regression. The research team aims to engage with disability-serving organizations to ensure that the survey reflects real concerns and will provide meaningful data, and to share results in support of universal access goals that the organizations and public agencies are pursuing.]]></description>
      <pubDate>Thu, 23 Apr 2026 17:58:32 GMT</pubDate>
      <guid>https://rip.trb.org/View/2695812</guid>
    </item>
    <item>
      <title>Unraveling the Causes of Fatal Crashes in the U.S.: A Machine Learning Approach to Safer Roads</title>
      <link>https://rip.trb.org/View/2694440</link>
      <description><![CDATA[This project investigates the underlying causes of fatal traffic crashes in the United States using advanced machine learning (ML) techniques to enhance road safety. Each year, traffic crashes claim over 42,000 lives nationwide, inflicting significant social, economic, and health burdens. Traditional analytical methods have struggled to capture the complex, nonlinear interactions among factors such as driver behavior, vehicle characteristics, roadway design, and environmental conditions. To address this limitation, this project employs data-driven ML models to identify key determinants of fatal crashes and generate actionable insights for evidence-based safety interventions.

The research activities will proceed in four phases. First, comprehensive crash data will be collected from the National Highway Traffic Safety Administration (NHTSA) and integrated across multiple datasets to ensure completeness and consistency. Next, statistical analysis and visualization will be used to identify spatial and temporal trends in crash patterns, revealing geographic disparities and risk concentrations. In the modeling phase, several machine learning algorithms—Balanced Bagging, Balanced Random Forest, and RUSBoost—will be developed and compared against traditional logistic regression models to enhance prediction accuracy in imbalanced datasets. Finally, the top-performing model will be used to assess variable importance and generate policy-relevant recommendations.

OBJECTIVE: The objective of this project is to develop predictive models that accurately identify risk factors associated with fatal crashes and support data-informed decision-making by transportation agencies. The findings will guide targeted interventions such as improved traffic regulations, safer roadway designs, and enhanced vehicle technologies. This research will provide a scalable analytical framework for improving transportation safety and sustainability nationwide.
]]></description>
      <pubDate>Tue, 21 Apr 2026 13:45:15 GMT</pubDate>
      <guid>https://rip.trb.org/View/2694440</guid>
    </item>
    <item>
      <title>Examining Attribution of Fault in Fatal &amp; Serious Injury Crashes between Drivers and Vulnerable Road Users</title>
      <link>https://rip.trb.org/View/2625585</link>
      <description><![CDATA[Traffic crashes killing or severely injuring pedestrians and bicyclists have increased dramatically in the past 10 years in the US. Research has found media and police narratives to play a strong role in shaping public opinion around strategies to prevent crashes involving vulnerable road users (VRUs), including whether those narratives attribute blame to the VRU victim. In California, following a crash, data are collected by law enforcement officers who make a determination of the “party most at fault.” Concerns exist as to whether fault in crash report data is over-attributed to VRUs, but no systematic research has assessed this.   We will utilize 2016-2023 electronically reported California Crash Reporting System data to identify the presence of a crash witness at each fatal or serious injury (FSI) single-vehicle/VRU crash, under the hypothesis that fault is more accurately attributed when a witness is present. Because VRU victims involved in FSI crashes with a motor vehicle are often unconscious, in transport to a hospital, or deceased at the time of the crash investigation, only the driver’s perspective is incorporated into police reports in the absence of a witness, while the presence of a witness provides additional and, we hypothesize, more objective information. The specific research question is: is the presence of a witness associated with a higher probability that the driver will be named at fault in FSI crashes between a driver and a VRU compared to crashes between a driver and a VRU when no witness is present?  We will use logistic regression to estimate the probability of the driver being attributed fault in crashes where a witness was present compared to crashes with no witness. If the probability is higher when a witness is present, we will discuss the likelihood that this implies that fault is systemically over-attributed to the VRU when there is no witness vs. other explanations. We will control for neighborhood and investigate if the effect of a witness on attribution varies according to reporting agency, victim attributes, or victim mode.  The overall goal will be to estimate minimum correction factors and 95% confidence intervals for VRU-involved crashes so statistics on attribution of fault can be adjusted for future research or in policy settings.]]></description>
      <pubDate>Tue, 18 Nov 2025 15:03:49 GMT</pubDate>
      <guid>https://rip.trb.org/View/2625585</guid>
    </item>
    <item>
      <title>Bridge Load Posting Prediction</title>
      <link>https://rip.trb.org/View/1750147</link>
      <description><![CDATA[1600 (~12%) of the 13,000 bridges in Louisiana that facilitate movement of people, goods, and services are load posted, i.e. they are deemed to lack the strength to safely carry all legal loads. With time, bridges will age and deteriorate; at the same time, legal loads might also become heavier. In this context, it is essential to estimate the expected number of load posted bridges in future to allocate necessary resources during long term planning and maintenance scheduling. Therefore, the research goal of this project is to quantify the number of load posted bridges in Louisiana for the next 50 years by combining machine learning techniques, physics based deterioration models, and probabilistic methods. To this end, the National Bridge Inventory (NBI) database along with element level inspection data from Louisiana Department of Transportation and Development (LADOTD) (if available) will be used to gather data on bridges. Next, clustering techniques will be used to identify the key bridge parameters that have the most influence on load posting decisions. The future values of the key parameters will be determined using Markov chain models whose transition probability matrices will be developed using the available datasets and physics-based deterioration models. To estimate the probability of load posting on a bridge given its key parameters, logistic regression models will be developed. This model will be used along with future values of key parameters to estimate the load posting probability of each bridge for the next 50 years. These load posting probability estimates will be used in a Monte Carlo simulation-based methodology to estimate the expected number of load posted bridges, along with confidence interval estimates. During the implementation phase, an interactive tool will be developed, training manuals will be prepared, and training workshops will be conducted to facilitate the adoption of the research products. Additionally, the research outcomes will be disseminated via various platforms and outreach activities will be organized to involve middle and high school students to increase their interests in engineering careers.]]></description>
      <pubDate>Mon, 09 Nov 2020 14:04:38 GMT</pubDate>
      <guid>https://rip.trb.org/View/1750147</guid>
    </item>
    <item>
      <title>Assessing the Impact of Air Pollution on Public Health Along Transit Routes  </title>
      <link>https://rip.trb.org/View/1483621</link>
      <description><![CDATA[This study seeks to investigate the role that individual (e.g., age, income, race/ethnicity, smoking status, diet, physical activity, health status) factors may play in confounding or modifying the health effects of traffic-related air pollution.  The study will also explore aggregating these individual level factors to create socio-economic profiles and indicators of health risk due to traffic-related air pollution along transit routes.   
 This study will utilize a panel of individuals that participated in the 2015 or 2016 (if available) National Health Interview Survey (NHIS).  The research team will complete a proposal to the Dallas-Fort Worth Federal Statistical Research Data Center to gain access to the restricted variables, which include geocodes.  The abundance of data within the NHIS will allow the research team to control for individual and household level factors that may also contribute to the incidence of morbidity and mortality.  The health outcomes of interest relate to the rate of occurrence of the chronic impacts of traffic-related air pollution, which include the following: (1) Asthma; (2) Lung cancer; (3) Type II diabetes; and (4) Low birth-weight.
Since the study’s primary goal is isolating the impact of traffic-related air pollution, the team will investigate two approaches.  Both modeling strategies use the occurrence of a health outcome (see those discussed above) as the dependent variable and the air quality measures and individual health-related variables (e.g. smoking status, diet, physical activity) as independent variables.  The first approach estimates a disaggregate logistic regression model for the aforementioned variables.  The second approach uses treed regression models, which are combinations of Classification and Regression Tree (CART) models and stepwise logistic regression models to assess adverse health effects of exposure.   In both cases, the researchers will characterize the risks related to traffic-related air pollution for different socio-economic profiles along transit routes.  
]]></description>
      <pubDate>Fri, 22 Sep 2017 14:20:07 GMT</pubDate>
      <guid>https://rip.trb.org/View/1483621</guid>
    </item>
  </channel>
</rss>