Tarrahan Parseh Transportation Research InstituteInternational Journal of Transportation Engineering2322-259X13120250701How Threshold-Moving Technique May Change the Performance of Different Machine Learning Models in Crash Severity Prediction Problems2039205421374710.22119/ijte.2024.417727.1652ENAlirezaMahpourFaculty of Civil, Water, and Environmental Engineering, Shahid Beheshti University, Tehran, IranMostafaShafaatiPhD, Faculty of Civil, and Environmental Engineering, Tarbiat Modares University, Tehran, IranMahmoudSaffarzadehProfessor, Faculty of Civil, and Environmental Engineering, Tarbiat Modares University, Tehran, Iran0000-0002-9713-2776Journal Article20230924To predict crash severity using Machine Learning (ML) models, dealing with imbalanced classification problems could be inevitable. Threshold-moving can address such problems. Based on a review of the literature, this technique seems to be underutilized. Also, the issue of comparing the performance of different machine learning models in the prediction of crash severity seems to be an open one. Thus, this research focuses on comparing the performance of Random Forest (RF), Logistic Regression (LR) and Naïve Bayes (NB) models by analyzing the trade-off between accuracy and recall for the minority class (both measures change as a result of thresholding). The minority class in our problem is fatal and serious injuries crashes. We use a state-wide crash database from California which contains 143310 records in order to address this issue. Various thresholds are used in the comparison, which are determined by Receiver Operating Characteristic Curves (ROC) and Precision-Recall Curves. There are three thresholds chosen for this study: 0.05, 0.10, and 0.15. Based on the results, the LR with a threshold of 0.1, the RF with 250 trees and the Bernoulli Naive Bayes (BNB) with a threshold of 0.05 are the best models. In addition, LR outperforms the rest of these three models. After threshold moving is employed, even simple models such as the LR can outperform more complicated ones like the RF in this paper, contradicting several previous studies in which the RF is found to be the best model.http://www.ijte.ir/article_213747_4c9abc7a93268aea9b45d4518e1a37fe.pdfTarrahan Parseh Transportation Research InstituteInternational Journal of Transportation Engineering2322-259X13120250701How to choose Hazard perception test scenarios in Rapid bus transit routes? A ranking study2055206621668810.22119/ijte.2025.466876.1667ENAmir HosseinZareiDepartment of Geotechnic and Transportation / Faculty of Civil Engineering, Water and Environment / Shahid Beheshti University of TehranMortezaAsadamrajiDepartment of Geotechnic and Transportation / Faculty of Civil Engineering, Water and Environment / Shahid Beheshti University of Tehran0000-0003-2799-4052Journal Article20240721Traffic safety and behavioral studies have long been critical areas of focus in urban transportation research. Among behavioral studies, hazard perception in driving has been identified as a key factor in reducing road accidents and improving overall traffic safety. In recent years, with the rise in accident statistics, hazard perception models have gained significant attention and are increasingly being implemented across various countries. This study explores the prioritization of hazards using the MABAC (Multi-Attributive Border Approximation Area Comparison) method for application in hazard perception test scenarios, alongside examining the factors influencing hazard perception among city bus drivers. To achieve this, drivers operating on one of Tehran's busiest and most accident-prone bus routes, specifically the Khavaran-Azadi route, were analyzed. The findings reveal that the crossing of motorcyclists and pedestrians into bus lanes is the highest-priority hazard to be incorporated into hazard perception tests for bus drivers. The results of this research can be applied to enhance hazard perception and prediction tests for city bus drivers, improve driver evaluation and training programs, and increase the safety of dedicated bus lanes.http://www.ijte.ir/article_216688_83688fd05118630013a3a747a5d4837a.pdfTarrahan Parseh Transportation Research InstituteInternational Journal of Transportation Engineering2322-259X13120250701A Model for Determining Railway Network Capacity (Case Study: Iran Network)2067207922408210.22119/ijte.2025.487492.1676ENHassanKhaksarAssistant Professor of Civil Engineering, North Tehran Branch, Islamic Azad University, Tehran, Iran0000-0003-0291-9128Journal Article20241106Capacity of lines and stations is one of the most influential and important factors in network planning and operation. Various methods and methodologies exist for calculating capacity. Accurately and appropriately determining this concept in railway network lines is a very complex task. This becomes even more important when considering the number of network blocks and their different characteristics and properties. In recent years, the Scott method has been used to calculate line capacity. This research aims to identify the various methods of calculating capacity in networks. Furthermore, while comparing these methods, an attempt has been made to introduce a suitable method for use in the country. To this end, by considering the characteristics of the country's railway network and calculating the capacity of 8 selected routes, an attempt has been made to identify a method suitable for the country's railway network. The International Union of Railways (UIC) has presented methods for calculating network capacity under codes 405 and 406. Based on the results of this research, the method presented in the UIC406 guideline, which is the latest and most up-to-date method of this union, has a good fit with the country's network conditions and can be used in the country's railway network. One of the outputs of this study is a software for calculating the capacity of the country's rail network based on UIC code 406. The outputs of this software include train capacity (train set of each block), tonnage capacity in two modes of dominant tonnage and maximum tonnage (nominal tonnage), network bottlenecks based on the performance-to-capacity ratio, and sensitivity analysis of various solutions to increase network capacity.http://www.ijte.ir/article_224082_6b7acc6eb2d8d7521f034efd1471893c.pdfTarrahan Parseh Transportation Research InstituteInternational Journal of Transportation Engineering2322-259X13120250701What Shapes Parental Concerns? Exploring the Impact of the COVID-19 Pandemic on School Travel Behavior of Elementary School Students (Case Study: Rural Roads of Gilan Province)2081210122229710.22119/ijte.2025.503453.1684ENBahramAmiri Nezhad AshoorabadiPhD Candidate, Transportation Department, Civil Engineering Faculty, Imam Khomeini International University, Qazvin, IranHamid RezaBehnoodAssociate Professor, Transportation Department, Civil Engineering Faculty, Imam Khomeini International University, Qazvin, IranBabakMirbahaAssociate Professor, Transportation Department, Civil Engineering Faculty, Imam Khomeini International University, Qazvin, Iran0000-0003-1004-7673Journal Article20250130This study examines the travel behavior of elementary school children in rural and suburban areas, focusing on the influence of parental concerns regarding traffic safety, the social environment, and the COVID-19 pandemic. Data were collected through surveys completed by 582 families with children attending elementary schools located near highways in Gilan Province, Iran. Using structural equation modeling (SEM), the study analyzes how these factors influenced travel mode choices both before and after the pandemic. The findings reveal that heightened concerns about traffic safety and social security significantly shaped travel decisions. Key results indicate that parental concerns about traffic safety, such as the availability of safe road crossings and adequate sidewalks, are primary determinants of travel mode selection, often resulting in increased reliance on private vehicles. Additionally, the COVID-19 outbreak exacerbated these concerns, introducing fears of virus transmission that drastically reduced public transportation usage while promoting private vehicle reliance and remote learning. The study also demonstrates that parents’ perceptions of children’s travel skills significantly impact travel choices, with safety concerns playing a crucial role. Policy recommendations include strengthening safety infrastructure, implementing traffic-calming measures, and enhancing community engagement to address social safety concerns. This research provides valuable insights into the factors influencing children’s travel behavior in rural and suburban contexts, offering a foundation for targeted interventions.http://www.ijte.ir/article_222297_7e4b64ea9e222dc17b132d4740802d95.pdfTarrahan Parseh Transportation Research InstituteInternational Journal of Transportation Engineering2322-259X13120250701An Economic Analysis of Cordon Pricing (Case study: New York City CBD)2103211722598610.22119/ijte.2025.508635.1688ENAmirhosseinBaghestaniFaculty of Civil, Water, and Environmental Engineering, Shahid Beheshti University, Tehran, IranRozhinBorhaniFaculty of Civil, Water, and Environmental Engineering, Shahid Beheshti University, Tehran, IranJournal Article20250313Cordon pricing has emerged as a critical Transportation Demand Management (TDM) strategy aimed at reducing traffic congestion, improving air quality, and generating revenue for sustainable transportation investments. This study evaluates the economic impacts of implementing a cordon pricing scheme in New York City’s Central Business District (CBD), where chronic congestion imposes significant economic and environmental costs. Using the New York Best Practice Model (NYBPM), we analyze two pricing scenarios—High-Toll ($20), and Low-Toll ($5)—to assess their effects on traffic flow, emissions, and economic outcomes. The findings demonstrate that cordon pricing generates substantial economic advantages by quantifying benefits through the Value of Time (VOT) and the traffic-weighted emission factor. One major benefit stems from the annual decrease in Vehicle Hours of Delay (VHD), while the other results from reduced emissions, both of which yield significant financial gains. By providing a data-driven evaluation of these economic outcomes, this research highlights the potential of cordon pricing as a strategic policy tool that balances financial efficiency, environmental responsibility, and equitable urban mobility planning.http://www.ijte.ir/article_225986_c9a66e75ab62be12be640258491d5fbc.pdfTarrahan Parseh Transportation Research InstituteInternational Journal of Transportation Engineering2322-259X13120250701Microstructure Study of Ordinary Concrete Containing High Grade Portland Cement2119212922681310.22119/ijte.2025.517813.1694ENMohammadhosseinMansourghanaeiPh.D. in Civil Engineering, Department of Civil Engineering, Chalous Branch, Islamic Azad University, Chalous, Iran0000-0003-4644-104XJournal Article20250419In this experimental study, a mixture design of ordinary concrete containing Portland cement (OPCC) with a grade of 500 kg/m<sup>3</sup> was made and compressive strength tests were performed at 7, 28 and 90 days of curing, and X-ray diffraction spectrometer (XRD) and scanning electron microscopy (SEM) imaging were performed on concrete samples at 90 days of curing at 21 ℃ to evaluate the microstructure of the concrete and to compare it with the test results of this study. Increasing the curing age due to the progress of the polymerization process (hydration) improved the results of the concrete compressive strength test. In this regard, at 90 days of curing, a compressive strength of 64.92 MPa was obtained, which was an increase of 79.48% compared to 7 days. SEM and XRD results indicate that a large part of the polymerization process has been completed and a high volume of hydrated calcium aluminosilicate gel called ettringite gel (C-A-S-H) and hydrated calcium silicate gel called tobermorite gel (C-S-H) has been produced in the concrete mix. The reduction in the amount of calcium hydroxide (Ca(OH)<sub>2</sub>) crystals in the XRD results indicates that this product has a good contribution to the hydration process and the production of hydrated gels. The high grade of cement used has played a significant role in increasing the volume of C-S-H gel production (as the main product of the chemical reaction process in OPCC) and filling the pores, cracks and capillary pores in the microstructure matrix of OPCC.http://www.ijte.ir/article_226813_ff2ace384f966a1baf7155bb179b199a.pdf