Tarrahan Parseh Transportation Research InstituteInternational Journal of Transportation Engineering2322-259X13420260401Machine Learning based Distributed Traffic Signal Control2277228723259410.22119/ijte.2025.523812.1697ENAlirezaRezaeeAssociate Professor, Department of Mechatronics Engineering, School of Intelligent Systems Engineering, College of Interdisciplinary Science and Technology, University of Tehran, Tehran, Iran0000-0001-6628-5545AmirhosseinSafdariM.Sc., Department of Mechatronics Engineering, School of Intelligent Systems Engineering, College of Interdisciplinary Science and Technology, University of Tehran, Tehran, Iran0009-0007-4689-6518Journal Article20250515<span>Optimizing traffic flow remains a central objective in transportation research. With the continuous growth in vehicle numbers, the limited scalability of existing infrastructure, and the inherently nonlinear, dynamic, and stochastic nature of traffic systems, signal control at road junctions has become an increasingly complex control challenge. Traditional signal control methods are predominantly rule-based, designed for deterministic environments, and often fail to adapt to real-time traffic variations and unexpected disruptions. This study proposes a distributed traffic signal control framework built upon a Machine Learning (ML) paradigm utilizing Reinforcement Learning (RL). Owing to their non-model-based architecture and computational efficiency, RL-based methods exhibit strong adaptability to changing traffic conditions and robustness against environmental uncertainties. In the proposed system, each junction is independently managed by an autonomous learning agent capable of interacting with its environment, refining its control policy over time, and making localized, real-time decisions. Simulation results demonstrate the effectiveness of the proposed approach, with vehicle queue lengths and average waiting times reduced by 35% to 66.4% on roads leading to the junctions, compared to conventional rule-based systems. These findings highlight the potential of distributed, learning-enabled control strategies in achieving scalable, adaptive, and efficient urban traffic management.</span>http://www.ijte.ir/article_232594_4df1ce8898911f534f6884ecf87f898f.pdfTarrahan Parseh Transportation Research InstituteInternational Journal of Transportation Engineering2322-259X13420260401Analyzing and Predicting Fatal Road Traffic Crash Severity Using Tree-Based Classification Algorithms2289230723602210.22119/ijte.2025.528624.1698ENAlirezaDaviranAssociate professor Department of Geography Education, Farhangian University, P.O. Box 14665-889, Tehran, Iran0000-0003-4983-5853Journal Article20250622<span>School transportation services operate in connection with the urban transportation network. The compatibility of the network’s carrying and congestion capacity depends on the functional system of its activities across temporal and spatial dimensions to enable adaptive performance. This study aims to examine the rhythmic structure of private school transportation services in Zanjan city and their role in generating and reproducing traffic within urban networks. The research employs a qualitative-exploratory methodology with an applied focus. Data were collected from a sample of over 200 school transportation services using interviews and observations. The collected data were analyzed and categorized using a rhythmic interpretation approach, considering variables such as movement patterns, routing, traffic nodes, origins and destinations, temporal characteristics, routes, spatial occupation, and functional amalgamation, and implemented in a Geographic Information System (GIS). The findings indicate that the functional structure of private school transportation services in Zanjan operates at the urban scale and is dependent on the origin-destination system of residences and schools. The results show that the functional rhythm of these services in central city schools peaks in the afternoon, whereas in peripheral areas it peaks in the morning. The main arterial and primary road networks serve as the framework for the movement and traffic system of these services, operating proportionally to residential weights and traffic nodes. Consequently, the study concludes that the functioning of private school transportation services in Zanjan is based on regional and urban traffic patterns. Given the size and spatial scale of the city, the flows of these services exhibit relatively long temporal and spatial intervals.</span>http://www.ijte.ir/article_236022_7106b4b990fc5d55b3df908f5b6e2335.pdfTarrahan Parseh Transportation Research InstituteInternational Journal of Transportation Engineering2322-259X13420260401Preventing Motorcycle Accidents: A Multi-Institutional Model2309233823602410.22119/ijte.2025.532957.1702ENSmaeilEhsanpoorAssistant Professor, Traffic Safety Department, Amin Police Comprehensive University, IranHabibzadehAshabProfessor of Communication Sciences, Department of Educational Administration, Farhangian University of Tehran, Iran0000-0001-9849-9038MehdiJavidAssistant Professor, Department foreign Languages, Amin Police Comprehensive University, Iran0009-0001-2774-3934Journal Article20250716As urban traffic becomes increasingly dense, the use of motorcycles has increased in metropolitan areas. Given the multifaceted nature of traffic accidents, there is a pressing need for constructive interaction among the various institutions involved in managing motorcycle traffic safety. The aim of this study is to present a multi-institutional prevention model for motorcycle accidents. This applied research used a mixed-methods approach, combining qualitative content analysis and quantitative descriptive-survey methods. In the qualitative phase, the statistical population consisted of experts and managers from organizations related to motorcycle traffic safety. Participants were selected using non-probability purposive sampling until theoretical saturation was achieved. In the quantitative phase, the statistical population included 9,223 individuals selected via convenience sampling. The statistical population in the quantitative section consisted of Judicial Experts, Traffic Accident Experts from the Iran Highway and Traffic Police Department, Traffic Police Headquarters of Iranian National Police, the Ministry of Roads and Urban Development, and the Civil Affairs Department of the Ministry of Interior, who were selected based on their availability. Sampling in the qualitative section was conducted purposefully based on criteria, while in the quantitative section, it was done using stratified random sampling proportional to the size of each stratum in the total population, resulting in a sample size of 384 individuals according to the Morgan table.The multi-institutional prevention model includes the following dimensions: organizational structure (t = 26.894), inter-institutional communication (t = 25.251), multifaceted cultural development (t = 25.392), technical factors (t = 12.436), and comprehensive education (t = 10.281). The organizational structure dimension had the highest impact, while comprehensive education had the lowest. All factor loadings were above 0.50 and statistically significant at the 95% confidence level. The prerequisites for a multi-institutional approach to preventing motorcycle accidents include developing an appropriate organizational structure, fostering inter-institutional communication, promoting multifaceted cultural development, implementing intelligent control systems, and providing comprehensive education. Emphasizing these dimensions and adopting an interdisciplinary approach to traffic management can lead to improved safety for motorcyclists.http://www.ijte.ir/article_236024_cdd578f929af0e944dd033f735bdceec.pdfTarrahan Parseh Transportation Research InstituteInternational Journal of Transportation Engineering2322-259X13420260401Estimating Urban Travel Times from Sparse GPS Data: A Practical ArcGIS-Python Framework2339235324287110.22119/ijte.2026.538463.1704ENAlirezaGanjkhanlooSchool of Civil Engineering, College of Engineering, University of Tehran, Tehran, IranMojtabaRajabi-BahaabadiDepartment of Civil Engineering, Yazd University, Yazd, IranJournal Article20250802<span lang="EN-GB">Accurate estimation of travel time across urban road networks is essential for effective traffic management, efficient route planning, and the development of intelligent transportation systems (ITS). In practice, GPS data is recorded at low sampling frequencies (sparse GPS data) due to limitations such as data storage and transmission costs. The low frequency of data poses significant challenges for traditional travel time estimation techniques, which often rely on continuous trajectories. To address this issue, the present study proposes a practical framework for estimating travel times at both the link and route levels using sparse GPS data. The methodology is implemented using Python scripting within the ArcGIS environment. A case study using GPS data collected from Tehran, Iran, is conducted to assess the performance of the proposed framework. The estimated travel times are validated against high-frequency GPS records, demonstrating that the approach yields accurate and reliable results despite the data sparsity. The integration of Python within ArcGIS enhances automation and makes the proposed framework both effective and accessible for real-world transportation analysis and planning.</span>http://www.ijte.ir/article_242871_6b21bb37ae77ac673c420859b14cbb8e.pdfTarrahan Parseh Transportation Research InstituteInternational Journal of Transportation Engineering2322-259X13420260401Investigation of the Factors Affecting the Unconfined Compressive Strength (UCS) of the Subgrade Soil Stabilized with Copolymers2355237224700410.22119/ijte.2026.541849.1705ENZohrehGhafori FardFaculty of Civil Engineering, University of Yazd, Yazd, Iran0000-0002-9084-982XMaryamMokhtariFaculty of Civil Engineering, University of Yazd, Yazd, IranMohammad MehdiKhabiriFaculty of Civil Engineering, University of Yazd, Yazd, Iran0000-0003-3434-7603Seyyed MehrdadJalilianIran Polymer and Petrochemical Institute, Tehran, IranJournal Article20250822Since transportation plays a crucial role in the economic and social development of a country and affects many aspects of life, it is considered as a vital artery there. Stabilizing the subgrade soil of roads improves their physical and mechanical properties and increases resistance to traffic load, moisture, and temperature changes. The goal is to extend the service life of roads, reduce maintenance costs, prevent premature failures, and enhance transportation. Most soils are stabilized with additives like cement, lime, and bitumen to improve their strength and durability, but these traditional stabilizers cause significant environmental pollution. Therefore, using environmentally friendly materials is important. This study examined the unconfined compressive strength (UCS) of the soil stabilized with styrene-acrylate and styrene-butadiene, as two eco-friendly emulsion copolymers, in dry and wet conditions and then in wet-dry and freeze-thaw cycles. The results were analyzed using the SPSS and Design-Expert software programs. It was indicated that increasing a pure polymer initially increases UCS, followed by a decrease. Also, moisture, wet-dry and freeze-thaw cycles reduce UCS. According to the independent t-test results, only the reduction of strength due to moisture was statistically significant. Using the equations proposed in this study, it is possible to estimate the UCS of the soil stabilized with the mentioned copolymers under different conditions and determine the optimal type and amount of polymers based on project requirements.http://www.ijte.ir/article_247004_7eaef0b6792f04e9534c0ff2f922ee89.pdfTarrahan Parseh Transportation Research InstituteInternational Journal of Transportation Engineering2322-259X13420260401Effects of Aging and Rest Periods on the Self-Healing Properties of Asphalt Mixtures2373238523602510.22119/ijte.2025.553085.1713ENMasoudJilanchiFaculty of Engineering and Technology, University of Zabol, IranMahmood RezaKeymaneshFaculty Member, School of Engineering, Payame Noor University, IranAlirezaKhavandiFaculty Member, School of Engineering, University of Zanjan, IranJournal Article20251013<span>Aging of asphalt mixtures is one of the main causes of reduced durability and performance in flexible pavements. The self-healing ability of asphalt materials plays an important role in extending their service life. This study examines the impact of short-term and long-term aging, using two standard methods (R30 and NCHRP), as well as the influence of different rest periods on the self-healing capacity of asphalt mixtures. Specimens were prepared with PG 64-16 binder and siliceous aggregates, and self-healing was assessed using three indicators: stiffness ratio difference, fatigue life ratio, and failure rate. The results show that longer rest periods significantly improve self-healing indices. Samples aged with the R30 method generally performed better than those aged with the NCHRP method, while unaged samples consistently exhibited the highest self-healing potential. The findings suggest that employing multiple indices provides a more complete picture of asphalt mixture behavior, and systematic comparison of aging methods can serve as a valuable guide for optimizing materials and designing long life pavements.</span>http://www.ijte.ir/article_236025_31601f242ccbf3ae5e81329457384183.pdf