<rss version="2.0" xmlns:atom="https://www.w3.org/2005/Atom">
  <channel>
    <title>Transport Research International Documentation (TRID)</title>
    <link>https://trid.trb.org/</link>
    <atom:link href="https://trid.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>Transport Research International Documentation (TRID)</title>
      <url>https://trid.trb.org/Images/PageHeader-wTitle.jpg</url>
      <link>https://trid.trb.org/</link>
    </image>
    <item>
      <title>Immobility or soft refusal? An empirical analysis of the association between respondents’ diligence and reported immobility in household travel surveys</title>
      <link>https://trid.trb.org/View/2639402</link>
      <description><![CDATA[In household travel surveys (HTS), some respondents may report immobility despite having actually traveled on the survey day to reduce survey burden, which is an instance of soft refusal. Since this can deteriorate the data quality of HTS, detecting possible soft refusals is important for HTS organizers and users. The respondents’ diligence can be used to detect possible soft refusals, but its examination is not sufficient. The objective of this study is to explore the association between their diligence and possible soft refusals in HTS. Data from the 2023 Kumamoto Metropolitan Area Household Travel Survey in Japan were used to examine this association. Firstly, we defined five types of less diligent respondents: item nonrespondents, nonrespondents to the open-ended questions (OEQ), proxy respondents, incentive seekers, and late submitters. Then, their immobility rates were compared with those of their more diligent counterparts. Binomial logit models were estimated to investigate the association comprehensively, and the model incorporating diligence variables was used to correct possible soft refusal bias. The results suggest that most less diligent respondents are more likely to report immobility, especially for the nonrespondents to OEQ and item nonrespondents. In contrast, incentive seekers are less likely to report immobility than non-incentive seekers, and late submitters show similar immobility rates to punctual ones. These findings suggest that handling less diligent respondents helps correct the overstated immobility rates. The results of this study contribute to the assessment and improvement of HTS data quality, which is important for transportation research and policymaking.]]></description>
      <pubDate>Thu, 12 Mar 2026 14:02:12 GMT</pubDate>
      <guid>https://trid.trb.org/View/2639402</guid>
    </item>
    <item>
      <title>Preliminary Insights from Multi-Year State-Level Pavement Friction Management Data</title>
      <link>https://trid.trb.org/View/2672511</link>
      <description><![CDATA[As a proven, cross-cutting safety countermeasure for reducing the frequency and severity of vehicle crashes, Pavement Friction Management (PFM) provides road agencies with a powerful tool for balancing the existing roadway friction with that required by vehicles to navigate the road network.  Between 2020 and 2024, several US states embarked on ambitious efforts to collect network-level continuous pavement friction and texture data with the ultimate goal of reducing injuries and fatalities. While singular data collection efforts offer a baseline of existing pavement friction at high resolution, collecting replicate data on all pavement sections allows for increasingly sophisticated characterizations of network performance.  With a focus upon pavement management and material performance in service, this paper will present the preliminary insights uncovered through analysis of thousands of miles (kilometres) of continuous pavement friction data, including the influence of material selection and composition, roadway geometry, and traffic loading on pavement friction performance. Many insights reinforce conventional wisdom although some challenge conventional thinking with respect to mixture composition and ultimately agency specifications. Challenges associated with data management at the network-scale, project-level data input quality, and data aggregation and clustering will also be discussed.]]></description>
      <pubDate>Thu, 12 Mar 2026 08:52:52 GMT</pubDate>
      <guid>https://trid.trb.org/View/2672511</guid>
    </item>
    <item>
      <title>Seismic Instrumentation at the I-40 Hernando Desoto Bridge in Memphis, Tennessee</title>
      <link>https://trid.trb.org/View/2235301</link>
      <description><![CDATA[Over the past several years, the Hernando Desoto Bridge carrying I-40 across the Mississippi river at Memphis has been the scene of an intensive strong motion monitoring project, involving the installation of numerous traditional and several non-traditional forms of instrumentation designed to characterize the response of the structure to shaking from seismic and induced sources. This bridge is being retrofitted to withstand a magnitude (mb) 7 event at 65 km distance from the site at a depth of 20 km. The goal of the retrofit is to have this bridge fully operational following the maximum probable earthquake (2500 year return period). As part of the I-40 bridge retrofit, Friction Pendulum TM Isolation Bearings have been used to insure the integrity of the main spans of the bridge. The Tennessee Department of Transportations (TDOT) in conjunction with the Federal Highway Administration (FHWA) have provided funding to install strong-motion instrumentation with 108 data channels at 36 different locations on the bridge. The United State Geological Survey (USGS) in 2002 funded the installation of sensors at the foundation levels. In addition, two free field monitoring stations were installed by Center for Earthquake Research and Information (CERI), at the University of Memphis, through funding from the Advanced National Seismic System (ANSS). Currently, in the United States and elsewhere in the world, there are very little data available on the response of long-span bridges during seismic events. Since such data are scarce, our ability to understand the behavior of such structures and to verify dynamic analyses performed on such structures during design/analyses/retrofit phases is limited. In the NMSZ, there are no long-span suspension bridge structures instrumented. Therefore, data collected from instrumentation of the I-40 bridge in Memphis will be an invaluable asset in evaluating the structure. The data will be used to assess the performance of the bridge following the retrofit and in particular for the assessment of the performance of the base-isolation system. In addition, data collected on the behavior of the base-isolation system will be applicable to any structure incorporating the system. Furthermore, lessons that will be learned from instrumentation of a bridge such as the I-40 bridge will provide important and needed information that will be applicable to structures built on similar seismological and geological settings as the 1-40 bridge. One of the goals of the instrumentation system is to develop a rapid warning system. The rapid warning system will be developed in partnership with TDOT, FHWA, the United States Geological Survey (USGS) and the Mid-America Earthquake Center (MAEC) researchers. The system will be triggered when certain acceleration thresholds, at free fields, are exceeded. Key officials at TDOT will be automatically notified of the exceedance of threshold acceleration within minutes over standard communication devices. This information will help determine the forces that the bridge underwent in a large earthquake, or other threatening events such a barge collision, and should allow quick determination whether it should be closed or/and what precautions rescuers and engineers should take. This type of monitoring and the associated rapid response may save lives.]]></description>
      <pubDate>Wed, 11 Mar 2026 14:44:32 GMT</pubDate>
      <guid>https://trid.trb.org/View/2235301</guid>
    </item>
    <item>
      <title>Review of Advantages and Disadvantages of Magnetometer Types and Measuring Techniques to be Used for GNSS-free PNT in the Maritime Environment</title>
      <link>https://trid.trb.org/View/2624154</link>
      <description><![CDATA[Reliable determination of position, navigation and timing (PNT) is essential for safe shipping traffic. PNT using the Earth's magnetic anomaly field, which is always globally available, is a promising alternative to satellite-based positioning which can be disturbed in case of conflicts. The aim of the review is to give an overview of the advantages and disadvantages of magnetometer technologies and data gathering methods with respect to positioning and their restrictions of the maritime environment such as specific setups, necessary accuracy and sensitivity as well as measurement frequency to obtain the high frequency components of the earth magnetic field.]]></description>
      <pubDate>Tue, 10 Mar 2026 09:57:53 GMT</pubDate>
      <guid>https://trid.trb.org/View/2624154</guid>
    </item>
    <item>
      <title>A reusable public transport electronic ticket system with fast validation</title>
      <link>https://trid.trb.org/View/2625373</link>
      <description><![CDATA[This paper presents an electronic ticket system for public transport which provides reusability in the sense that, after the validation of a ticket, a traveler is enabled to perform a journey which can include a limited number of transfers before an expiration time. The proposal has been designed following a privacy-by-design approach. Travelers are only required to identify themselves if requested to prove possession of a valid ticket by an officer. Otherwise, they can travel without being required to disclose their identity (anonymity). Also, the diverse interactions of a traveler with the system cannot be related to them (unlinkability). The security and privacy requirements are achieved by making use of advanced cryptographic techniques. The system has been simulated and proven to provide running times which make it appropriate for a real deployment. When compared to an existing proposal designed for an equivalent scenario, the reduction in the time required for ticket validation is especially remarkable. In effect, all the use cases with real-time constraints (“Ticket validation”, “Get-in”, and “Get-out”) can be run in less than one second.]]></description>
      <pubDate>Tue, 10 Mar 2026 09:57:53 GMT</pubDate>
      <guid>https://trid.trb.org/View/2625373</guid>
    </item>
    <item>
      <title>Mobile Weather Data Collection Guidelines (on DOT Fleet Vehicles)</title>
      <link>https://trid.trb.org/View/2636167</link>
      <description><![CDATA[In the 2009 Aurora Program Peer Exchange, guidelines for mobile weather data collection were identified as a high priority by the states that participated. The problem statement assigned to the Aurora Pooled Fund, given their expertise, includes the collection and dissemination of road and weather data. The problem statement addressed in this brief report is: With the addition of integrated telecommunications and information technology or telematics to maintenance fleet vehicles, we gain the ability to collect data that may aid in identifying current road and weather conditions. However, care must be taken to assure these data reflect actual conditions and not a microclimate created by the vehicle. It was concluded that sensor technology and environmental issues caused during snow and ice operations make a snowplow a very unlikely candidate to collect accurate data on salinity and friction values.]]></description>
      <pubDate>Mon, 02 Mar 2026 16:12:38 GMT</pubDate>
      <guid>https://trid.trb.org/View/2636167</guid>
    </item>
    <item>
      <title>Integrating Deep Learning and Real-Time GNSS Localization for GIS-Based Traffic Sign Management</title>
      <link>https://trid.trb.org/View/2640544</link>
      <description><![CDATA[Traffic signs are fundamental in ensuring road safety and maintaining traffic stability. Due to the scattered distribution, managing information on traffic signs is challenging and requires extensive manual efforts in conventional practice. This study proposes an efficient and highly automated method for traffic sign management by leveraging deep learning, global navigation satellite systems (GNSS), and geographic information systems (GIS). A mobile application is developed to collect sign images and geolocations simultaneously. A YOLOv8 model, through pretraining and transfer learning, is utilized to detect the types of traffic signs, and the results are combined with the geolocations to create a digital map for visualizing the traffic sign distribution. The feasibility of the method is validated using real-world road scenarios, where the results indicate the average precision of sign detection is 85% and the positioning error is 9.46 m. The proposed method drives an instrumental solution for efficient traffic sign asset management.]]></description>
      <pubDate>Fri, 27 Feb 2026 11:00:15 GMT</pubDate>
      <guid>https://trid.trb.org/View/2640544</guid>
    </item>
    <item>
      <title>Exploring the reliability of Floating Car Data (FCD) through penetration rate prediction in urban contexts</title>
      <link>https://trid.trb.org/View/2636183</link>
      <description><![CDATA[Monitoring and predicting traffic conditions is a crucial task for transportation agencies. Recent technological advances and the rise of big data have enabled real-time, high-frequency traffic data collection through Floating Car Data (FCD), which offers broader coverage and lower costs compared to traditional methods like fixed sensors. However, FCD is limited as it represents only a sample of users with heterogeneous market shares and, in some cases, lacks vehicle classification information.This study aims to assess the reliability of FCD through a comparative analysis using fixed radar sensors as a ground truth. The analysed variables include vehicle counts to measure FCD Penetration Rates (PRs) as a performance metric and vehicle speeds to assess possible bias phenomena. Additionally, we developed a PR prediction model, identifying the most influential variables through feature engineering and assessing the model's accuracy with Symmetric Mean Absolute Percentage Error (SMAPE). The case study focuses on the city of Catania, Italy, with sensor data obtained from a traffic monitoring system consisting of several counting sections installed along a cordon surrounding the urban area, while FCD were extracted from TomTom portal. Results show spatial and temporal variability in FCD coverage, particularly low PRs at night, and an underestimation of speeds by FCD. The developed predictive model uses widely available FCD data to estimate PRs, helping identify FCD's opportunities and limitations for a more comprehensive understanding of road network performance. Future research will extend the analysis period and integrate more data sources to enhance traffic prediction accuracy and reliability.]]></description>
      <pubDate>Thu, 26 Feb 2026 16:18:09 GMT</pubDate>
      <guid>https://trid.trb.org/View/2636183</guid>
    </item>
    <item>
      <title>Co-training framework for enhancing survey accuracy while reducing respondent burden in travel data collection</title>
      <link>https://trid.trb.org/View/2627576</link>
      <description><![CDATA[A major bottleneck in travel behavior analysis is the need for a substantial amount of labeled data, which typically places a burden on survey respondents for collecting travel behavior data. Our study addresses this issue by leveraging semi-supervised learning, specifically utilizing the co-training algorithm, which effectively incorporates both labeled (active) and unlabeled (passive) data. We extend the semi-supervised learning concept to be a part of the survey scheme that involves both data collection process and enrichment process of travel attributes. Our experiments, focusing on travel mode identification using GPS data from Hiroshima, Japan, demonstrate that our proposed method outperforms existing conventional supervised learning methods such as neural networks, KNN, and SVM, particularly when incorporating an increased proportion of unlabeled data. This strategic use of unlabeled data achieves two apparently conflicting goals: (1) reduces the reliance on extensive manual labeling, thereby alleviating respondent burdens, and (2) increases the accuracy of the prediction. The results of our experiments also reveal that the delicate balance between labeled and unlabeled data proportions plays a pivotal role in co-training performance. Beyond serving as a mode identification tool, our findings underscore the transformative potential of co-training as a valuable data filtering method: By optimizing the interplay between labeled and unlabeled data, co-training efficiently filters noise and refines the dataset. This contributes to enhanced survey accuracy while minimizing labeling burdens. Our results provide useful information to design an adaptive scheme that dynamically tailors the information solicited from respondents to optimize the balance between data quality and respondent burden.]]></description>
      <pubDate>Thu, 26 Feb 2026 14:51:30 GMT</pubDate>
      <guid>https://trid.trb.org/View/2627576</guid>
    </item>
    <item>
      <title>Identifying walkability factors for urban metro station areas toward transit-oriented development</title>
      <link>https://trid.trb.org/View/2627371</link>
      <description><![CDATA[Despite significant efforts to enhance accessibility to transportation facilities and transit-oriented development (TOD), the rapid expansion of cities has hindered improvements in citizens’ access to transportation facilities. This study addresses these challenges by aiming to delineate key factors pertaining to access distance that facilitate successful station area development and to identify areas requiring enhancements in public transport access. To measure accessibility and the factors affecting it, various types of mobility and demographic data, including transit fare card data, residential and workplace population density, and the count of bus stops and metro lines, were used to assess access distance characteristics. Findings indicate that bus stops within 500m of metro stations tend to have more bus stops within a 500m radius and lower residential population within a 100m radius, compared to stations with access distances exceeding 500m. Bus stops in the 500m range outnumber those beyond 500m, and their associated residential and workplace population densities are lower. Considering the number of bus stops as well, stations indicating access distances exceeding 500m are relatively scarce in public transportation, indicating lower public transportation accessibility. Therefore, this study suggests that when developing station areas within urban centres, priority should be given to areas where subway station population density is high but distributed over a wide area and the number of bus stops within the station area is low. These findings on the walkability quality factors and considerations to assess the walkability will be a great reference to the policy decision makers to prioritize TOD areas.]]></description>
      <pubDate>Wed, 25 Feb 2026 09:11:18 GMT</pubDate>
      <guid>https://trid.trb.org/View/2627371</guid>
    </item>
    <item>
      <title>Variations in value of travel time savings on express lanes: Evidence from passively collected data</title>
      <link>https://trid.trb.org/View/2626092</link>
      <description><![CDATA[This paper investigates preference heterogeneity in the Value of Travel Time Savings (VTTS) among Express Lane (EL) users, highlighting how VTTS varies across individuals. The study contributes to the literature by demonstrating how travel demand modeling can be effectively conducted using a large, high-resolution dataset that integrates transponder-based Express Lane usage with travel time savings derived from probe vehicle data. VTTS is estimated through a trip generation model, where the dependent variable is trip frequency.To address the absence of user-specific socio-demographic characteristics and to capture the full spectrum of preference heterogeneity, the study employs three advanced ordered logit models: the generalized ordered logit (GOL), the heteroskedastic ordered logit (HOL), and the latent class ordered logit (LCOL). Results reveal substantial heterogeneity in user preferences. Notably, infrequent Express Lane users demonstrate a higher willingness to pay for time savings compared to regular commuters, suggesting that EL usage patterns reflect deeper differences in value perception.By identifying nuanced user segments and their evolving preferences, this study offers actionable insights for transportation agencies, planners, toll operators, and policymakers. The findings support the development of dynamic tolling and incentive-based strategies that are responsive to user diversity.]]></description>
      <pubDate>Wed, 25 Feb 2026 09:11:18 GMT</pubDate>
      <guid>https://trid.trb.org/View/2626092</guid>
    </item>
    <item>
      <title>A spatially structured empirical Bayes framework for the evaluation of network-wide safety countermeasures</title>
      <link>https://trid.trb.org/View/2667184</link>
      <description><![CDATA[This study proposes a two-step, spatially structured Empirical Bayes (EB) framework for evaluating the safety effectiveness of network-wide countermeasures, leveraging the Network Process Convolution (NPC) model. A central challenge in road safety evaluation is not only estimating treatment effects but also accurately quantifying uncertainty, particularly when interventions generate local and spillover effects. The NPC uses a network-based Gaussian Process with reweighted kernel convolution to capture spatial correlations of collisions along road networks, enabling robust estimation of both site-specific and network-wide effects. The two-step procedure ensures an unbiased prior structure for generating counterfactual outcomes. The authors conducted a simulation study under varying spatial correlation scenarios and applied the method to the City of Edmonton’s Driver Feedback Sign (DFS) program using 10 years of collision data across 1,366 road segments. Performance was benchmarked against the traditional EB Poisson-Gamma (EB-PG) method. Simulations show that while both methods accurately recover counterfactual collisions and reduction ratios, EB-NPC provides more reliable and well-calibrated uncertainty quantification, particularly under moderate to strong spatial correlation. In the Edmonton case study, EB-NPC mostly produced slightly higher estimated reductions and more informative predictive uncertainty, whereas EB-PG remained more robust in areas with weak spatial structure. Beyond numerical estimation, EB-NPC generates continuous spatial risk surfaces, allowing practitioners to visualize network-wide safety patterns and prioritize high-risk segments. Overall, the proposed approach improves recovery of counterfactual outcomes and delivers accurate, interpretable uncertainty characterization, offering a powerful tool for data-driven transportation safety management.]]></description>
      <pubDate>Wed, 25 Feb 2026 08:53:19 GMT</pubDate>
      <guid>https://trid.trb.org/View/2667184</guid>
    </item>
    <item>
      <title>Identification of high-risk expressway segments using connected vehicle data: An empirical analysis</title>
      <link>https://trid.trb.org/View/2664102</link>
      <description><![CDATA[Traditional road safety analysis primarily relies on historical crash data, which require long accumulation periods and are constrained by limitations such as insufficient data volume, imprecise location information, and underreporting, potentially leading to biased or delayed assessments of road safety risks. The emergence of connected vehicle (CV) technology provides new opportunities for more timely safety analysis. CVs are equipped with onboard sensors that monitor driving behavior and issue critical warnings, including headway monitoring warnings (HMWs) and forward collision warnings (FCWs). This study aims to proactively identify high-risk expressway segments using CV warning data. Accordingly, an integrated framework is developed, combining spatial hotspot identification and statistical regression modeling. Based on CV data from nine expressways in Shanghai, warning hotspots are identified using Moran’s I and Getis-Ord Gi*, indicating locations with spatial clustering of HMWs and FCWs. The relationship between warning frequency and the number of collisions is examined through Poisson and Negative Binomial models estimated with and without incorporating CV warning frequencies as explanatory variables. To address the potential endogeneity between traffic conflicts and collisions, an instrumental variable Poisson model is further employed. The results confirm that HMW and FCW frequencies are positively associated with collisions, and that accounting for endogeneity improves estimation robustness. In addition, hotspot co-occurrence analysis and statistical testing reveal that segments identified exclusively as CV warning hotspots still experience significantly more collisions compared to segments identified as neither warning nor collision hotspots. This suggests that CV warning data can support early detection of emerging safety risks. This study contributes a structured and empirically supported framework that advances the application of connected vehicle data in proactive traffic risk assessment.]]></description>
      <pubDate>Wed, 25 Feb 2026 08:53:19 GMT</pubDate>
      <guid>https://trid.trb.org/View/2664102</guid>
    </item>
    <item>
      <title>A Flexible Approach Based on Hybrid Global Low-Rankness and Smoothness Regularization With Nonlocal Structure for Traffic Data Imputation</title>
      <link>https://trid.trb.org/View/2561793</link>
      <description><![CDATA[Spatial-temporal traffic data are collected by a wide array of data collection devices deployed in intelligent transportation systems, which play crucial roles in data-driven intelligent transportation systems. However, hardware malfunctions or software system errors can lead to the inability to collect accurate data. Incomplete data in intelligent transportation systems can cause difficulties for subsequent applications, such as traffic flow anomaly detection and forecasting. Recently, low-rank tensor-based methods that characterize the global correlation of high-dimensional data have achieved superior performance. However, the majority of tensor-based approaches primarily account for the global correlation within the target traffic data, which is not sufficient to recover some challenging missing scenarios, such as fiber missing and slice missing that often occur in real situations. In this manuscript, we suggest a flexible method to explore the global correlation, local smoothness, and nonlocal self-similar redundancy in traffic data to improve recovery accuracy. Specifically, we utilize the multidimensional tensor nuclear norm to characterize the correlation structure, the multidimensional total variation to maintain smoothness detail, and the plug-and-play term to promote nonlocal self-similarity. The primary merits of this model lie in the fact that these priors characterize data features from different perspectives and complement each other. We develop an alternating direction method of multipliers to achieve efficient optimization for each variable. The proposed method is comprehensively evaluated through experiments across seven missing scenarios. Extensive experiments demonstrate that the suggested method with the aid of different priors outperforms many state-of-the-art approaches, especially structured missing scenarios.]]></description>
      <pubDate>Tue, 24 Feb 2026 09:00:43 GMT</pubDate>
      <guid>https://trid.trb.org/View/2561793</guid>
    </item>
    <item>
      <title>Data Imputation for Traffic State Estimation and Pre-diction Using Wi-Fi Sensors</title>
      <link>https://trid.trb.org/View/2113517</link>
      <description><![CDATA[Real-time monitoring of traffic conditions is essential to support control strategies and provide useful information to travelers. With the accelerated development in transportation management systems (TMSs), traffic data collection methods have progressed rapidly. Despite the development in the data collection systems, there is missing data due to occasional sensor damage, trans-mission error, or a low penetration rate of the probe vehicle, thereby affecting the reliability and effectiveness of the Intelligent Transportation Systems (ITS). There is a need for effective data imputation methods to ensure the integrity and quality of traffic data. Two clustering-based methods for such traffic imputations are proposed in this paper—one using k-means clustering and the other using speed bins. Mean Absolute Percentage Error (MAPE) is used as a performance efficiency index for both methods. The Speed bin method was found to be more effective with a maximum MAPE of 13.8%. The maximum MAPE observed for the k-means clustering method is 22.6%.]]></description>
      <pubDate>Tue, 24 Feb 2026 08:30:16 GMT</pubDate>
      <guid>https://trid.trb.org/View/2113517</guid>
    </item>
  </channel>
</rss>