http://yetl.yabesh.ir/yetl1/handle/yetl/19014 2026-04-14T17:30:16Z 2026-04-14T17:30:16Z Jake Robbennolt Lu Xu Kyle Bathgate Shidong Pan Stephen D. Boyles http://yetl.yabesh.ir/yetl1/handle/yetl/4309591 2026-02-16T21:41:47Z 2025-01-01T00:00:00Z

Identifying Critical Locations for Traffic Monitoring Devices during Hurricane Evacuations Jake Robbennolt; Lu Xu; Kyle Bathgate; Shidong Pan; Stephen D. Boyles Large-scale evacuations from natural disasters such as hurricanes pose major logistical and operational challenges. There is often insufficient roadway capacity for entire populations to evacuate immediately, causing costly and potentially deadly delays. Traffic monitoring devices (TMDs) can help ensure an evacuation proceeds smoothly. Information collected by such devices can help authorities direct traffic onto underutilized routes and dispatch emergency services to clear traffic incidents faster. Closely monitoring every roadway in the system is prohibitively expensive, so we propose an efficient quantitative method to identify links that would most benefit the system by being monitored; we define these critical locations as roadway segments where any delay or underutilization of capacity will increase the overall evacuation time. We test this method in two case study hurricane scenarios along the Texas coast, and demonstrate how monitoring these critical locations could reduce delays if the information collected leads to faster incident clearance times and information provided to drivers improves their routing decisions. The simulation indicates that routing decisions have a larger impact on performance than incident detection and that effective traffic monitoring and route guidance can reduce clearance time for a large-scale evacuation in the Houston region by 19.1%.

2025-01-01T00:00:00Z Shih-Hsien Yang Nam Hoai Tran Firmansyah Rachman Hoang Dao http://yetl.yabesh.ir/yetl1/handle/yetl/4309590 2026-02-16T21:41:44Z 2025-01-01T00:00:00Z

Application of a Hybrid Approach in Developing Urban Road Livability-Related Indicators for the Sustainable Urban Road Rating System Shih-Hsien Yang; Nam Hoai Tran; Firmansyah Rachman; Hoang Dao In light of recent sustainable development goals, there is a growing demand for developing a systematic and quantifiable sustainable roadway assessment, also known as a sustainability rating system, on a global scale. Accordingly, efforts have been undertaken to improve the adaptability of rating systems by formulating country-specific indicators. This research focuses on the existing limitations in selecting indicators and assigning scores to indicators. This study adopted a hybrid approach to establish urban road livability-related indicators (URLIs) and the corresponding indicator weights within a sustainability rating system and identify significant obstacles to URLI application in urban road projects. This novel hybrid approach combines the top-down and bottom-up approach. The top-down approach involves an extensive literature review to identify potential URLIs and preselected obstacles. The bottom-up approach incorporates insights from experts in Taiwan and Vietnam to finalize 16 requirements under four URLIs and nine obstacles. The URLIs are pedestrian infrastructure, equitable road design, intermodal transportation, and utility infrastructure. Then, the analytical hierarchy process (AHP) method was employed to assign weights to proposed indicators/requirements, while the weighted sum model (WSM) investigated three critical obstacles: unfavorable conditions on-site, absence of coordination interface among stakeholders, and lack of support from government policy and regulations. The suggested hybrid approach could be a foundation for establishing the indicator system across various categories and investigating obstacles to indicator adoption in other regions/countries. The research findings also provide roadway engineers and policy makers with improved insights into the livability standards for urban road projects.

2025-01-01T00:00:00Z Jisu Hong Se-Jin Jeon http://yetl.yabesh.ir/yetl1/handle/yetl/4309589 2026-02-16T21:41:43Z 2025-01-01T00:00:00Z

Efficient Decision Tree-Based Classification Models to Predict Safety Rating for Bridge Maintenance Jisu Hong; Se-Jin Jeon To address insufficient costs and manpower available for maintenance of aging bridges, recent research has been examining advanced maintenance technologies that can theoretically predict the condition and performance of infrastructure facilities. The current study proposes a method that is intended to predict the safety rating of bridges; among the various machine learning techniques available for this purpose, a decision tree-based classification model has been selected. Using decision tree, random forest, XGBoost (extreme gradient boosting), and LightGBM (light gradient boosting machine), 8,850 bridges on general national roads in Korea were analyzed, and the results were compared. It was possible to identify the variables that have critical impacts on the model during the model formation process. The models were analyzed through various evaluation metrics or indices such as balanced accuracy, recall, ROC (receiver operating characteristic) curve, and AUC (area under the curve). The results showed that the models using random forest, XGBoost, and LightGBM, and not those using a decision tree, exhibited excellent performance in predicting bridge safety ratings. These models achieved a recall of more than 80% for bridges with C and D ratings, which are the main targets of maintenance due to their high degree of aging. Moreover, the AUC exceeded 0.8, indicating that the prediction of bridges with ratings other than C and D was also satisfactory. These results indicate that the multiclass classification model applied in this study, with proper data sampling technique and the optimum parameters, showed improved predictive performance compared with the existing models. As infrastructure throughout the world—such as bridges—continues to age, proper maintenance is becoming increasingly important. However, with the increasing number of aging bridges that require such consideration, it is increasingly common for there to be insufficient costs and manpower available for maintenance. As a result, there have been several bridge collapses due to lack of maintenance, such as the I-35W Mississippi River Bridge, Ynys-y-Gwas Bridge, and Malle Bridge. The proposed multiclass classification model using a decision tree is expected to contribute to the establishment of proactive and economical bridge maintenance plans by allowing for quick identification of the safety rating of bridges without available data on safety inspections and the estimation of a bridge’s safety rating at a specific time. Therefore, this study can contribute to bridge asset management (BAM) by determining an optimal time for maintenance to prolong the asset’s life.

2025-01-01T00:00:00Z Qiming Chen Zhongjie Zhang http://yetl.yabesh.ir/yetl1/handle/yetl/4309587 2026-02-16T21:41:39Z 2025-01-01T00:00:00Z

Feasibility Study on Use of Drone-Based Infrared Thermography for Soil Moisture Detection in Highway Embankment and Dam Inspections Qiming Chen; Zhongjie Zhang This research explored the capabilities of drone-based infrared thermography technology for soil moisture detection on embankment/dam soils. FLIR Vue Pro R, a radiometric thermal camera, was evaluated in both laboratory and field settings on embankment/dam soils for their accuracy, repeatability, and dependability. Field testing was first carried out at the Pavement Research Facility (PRF) of the Louisiana Transportation Research Center (LTRC) to assess the camera’s capabilities and limitations. Subsequently, field data were collected at one embankment and two dam sites. The laboratory tests showed that the decreasing trend in measured apparent temperature is obvious when the moisture content is low. After that, the relationship curve got flatter. Meanwhile, the field results showed that drier soil is associated with higher the measured apparent temperature. The correlation between the soil moisture content and apparent temperature reading from the thermal camera is very complicated and only has a relative value for spatial comparison when the ambient environment is not considered. The index combining the land surface temperature and vegetation within the normalized difference vegetation index (NDVI)-land surface temperature (LST) space showed promising results for detecting false wet soil results in thermal sensing due to vegetation. The failure areas or seepage issues with abnormal moisture conditions at the field-testing sites were successfully identified within regions exhibiting low measured apparent temperatures. The findings of this study demonstrate that the drone-mounted thermal camera is capable of distinguishing various moisture zones. Hence, drone-based infrared thermography technology proves to be a promising tool for rapidly mapping earth embankment and dam slope surface moisture conditions, indicating potential stability risks. Its application can enhance the information available to inspectors and dam owners, facilitating targeted ground inspections focused on areas identified as potential concerns by drone-based thermal inspection.

2025-01-01T00:00:00Z