Tarrahan Parseh Transportation Research InstituteInternational Journal of Transportation Engineering2322-259X12220241001Developing a Framework for Selecting an Appropriate Model based on the Ensemble Learning1719174520743610.22119/ijte.2024.440299.1660ENAlirezaMahpourFaculty of Civil, Water and Environmental Engineering, Shahid Beheshti University, Tehran, IranMostafaShafaatiFaculty of Civil and Environmental Engineering, Tarbiat Modares University, Tehran, IranJournal Article20240127We present a framework for selecting the optimal ensemble learning model based on 143310 crash observations with five classes. For non-ensemble models, we use five common models. 26 ensemble learning models are derived from these five models. We suggest Diff2 and Diff3 measures for choosing the right model. The diff2 is the difference between observations classified incorrectly as class 1 and incorrectly classified as class 3, 4, or 5. In Diff3, we compare observations misclassified as class 1 or 2 with observations misclassified as class 4 or 5. We select the best model based on the following criteria: for class 1, the largest R1, for class 2, the largest "Diff2", for class 3, a negative "Diff3", and for classes 4 and 5, the highest "F1-score". The paper ranks 31 models based on its criteria. There are five ranking series. By comparing these rankings, we can determine, for example, whether the 3rd best model for class 1 corresponds to the best model for class 2. For each model, 5 "Ranks" are determined. Relationships between the ranks were then evaluated. Rank1 and Rank2, Rank3 and 5 have a relatively strong relationship. A negative and relatively strong correlation exists between Rankings 2 and 3, as well as Rankings 2 and 5.http://www.ijte.ir/article_207436_da54265874a02443505f3c7aefb38ad3.pdfTarrahan Parseh Transportation Research InstituteInternational Journal of Transportation Engineering2322-259X12220241001Covid-19 Impact on Rail and Air Modes: a SARIMA Model of Duration and Severity (Case Study: Iran)1747176120743710.22119/ijte.2024.430752.1656ENMohammad AminEmamiPhD candidate in Transportation Planning, Faculty of Civil & Environmental Eng. Tarbiat Modares University, Tehran, IranAmirRezaMamdoohiAssociate Professor of Transportation Planning, Faculty of Civil & Environmental Eng. Tarbiat Modares University, Tehran, Iran0000-0002-5339-9807Journal Article20231215People’s outdoor activities changed significantly as a result of the spread of the COVID-19 pandemic. People’s travel behavior was greatly affected by the change in their activities, and as a result, the demand for public transportation systems such as rail and air was dramatically reduced. Despite the existence of numerous studies relating to the impact of COVID-19 on rail and air travel demand, the extent of the impact of the pandemic on non-high-speed railway (HSR) and air travel is still unknown in developing countries in terms of intensity and duration. In this research, two SARIMA models have been calibrated to forecast travel demand for rail and air modes. This is done using monthly data on the number of passengers carried up to the date before COVID-19 outbreak. The forecasts from the mentioned models are assumed to represent travel demand in the absence of pandemic. According to the results, the demand for rail transportation has decreased by 46%, resulting in a reduction of 31.924 million passengers, while the demand for air travel has decreased by 34%, resulting in a reduction of 9.588 million passengers. Also, rail transportation reached normal conditions eight months later than air transportation (lack of pandemic impact on demand). This study is important to identify the behavior of non-HSR and air transportation modes in the face of future crises similar to COVID-19, which can lead to the optimal distribution of limited resources of developing countries in future crises.http://www.ijte.ir/article_207437_5e4e2baad7ad79218abf6aa4dd7e40ba.pdfTarrahan Parseh Transportation Research InstituteInternational Journal of Transportation Engineering2322-259X12220241001Laboratory Evaluation of the Fracture Resistance of Asphalt Mixtures Containing Carbon Fibers1763178320743810.22119/ijte.2024.443084.1661ENMonireZokaeiPhD Candidate, Department of Civil Engineering, Babol Noshirvani University of Technology, Babol, IranSaeedHesamiAssociate Professor, Department of Civil Engineering, Babol Noshirvani University of Technology, Babol, IranJournal Article20240218The most common distresses of asphalt pavements are fatigue and cracking, which can lead to stripping and structural failure. The fracture mechanic concepts can be used to evaluate pavement material's resistance to crack initiation and propagation. The cracking behavior of asphalt mixtures can be improved by fiber reinforcement. The addition of carbon fibers can strengthen asphalt binders or mixtures. The optimum length and content of carbon fibers in asphalt binders and mixtures need to be investigated to improve their cracking behavior. In this paper, carbon fibers with different contents and lengths were added to asphalt binders and mixtures, and their fracture, fatigue, resilient modulus, tensile strength, and flexural bending strength were investigated. The results showed that adding up to 1.5% of fibers leads to an increase in the fracture and fatigue performance of the mixtures. The mixtures containing fibers with lengths between 15 mm to 20 mm indicated the best performance in terms of fatigue, fracture, and tensile strength. The results of the mixed-mode SCB fracture and the RSCB tests of the mixtures reinforced with the optimum fiber length and content show that the highest fatigue and fracture resistance happens in the pure mode II condition. The effective fracture toughness and fatigue life decline by approaching the mode I condition Asphalt binder test results showed that fiber reinforcement was significantly effective in improving the flexural strength of the asphalt binders and mastics.http://www.ijte.ir/article_207438_607e54b0a3c00e3b4e42e2da2b4c6bfc.pdfTarrahan Parseh Transportation Research InstituteInternational Journal of Transportation Engineering2322-259X12220241001Determination of Factors Affecting Rural Crash Frequency at Marginal Areas around Cities1785180220743910.22119/ijte.2024.452279.1665ENHamidShamanian EsfahaniDepartment of Civil Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran0000-0001-5000-6687Seyed TeimourHoseiniAmin University, Tehran, IranRezaSakhaeiAmin University, Tehran, IranMajidEhsani SohiAmin University, Tehran, IranJournal Article20240426<span lang="EN-GB">The high rate of traffic crashes and consequent losses have caused many social and economic problems in developing countries like Iran. According to previous studies, 60-70% of rural damages in Iran occur in marginal areas around cities. Hence, identifying effective factors in rural crashes around cities is of great importance to take proper safety measures in such areas. This requires developing exclusive models to predict rural crash frequency around cities. Given the limitations of fixed-parameters models, such as Poisson and negative binomial regression, the present study uses a random-parameter approach, including the random parameters negative binomial (RPNB) and random effects negative binomial (RENB) models to determine the factors affecting rural crash frequency at marginal areas around cities. The data on rural crashes on roads leading to Isfahan over 3 years, were used to develop the models. The random-parameter models were used to consider the unobserved heterogeneity among crash observations. The goodness-of-fit measures indicated the acceptable accuracy of the developed models. Meanwhile, the likelihood ratio test revealed a slight difference between the RPNB and RENB. According to the outcomes, the factors influencing crashes around cities included traffic volume, the ratio of local and non-local vehicles, the proportion of longitudinal distance-limit violations, access points controlling, and access to rest area facilities.</span>http://www.ijte.ir/article_207439_0e188b54e56c76f6fc0631ad4e894eb1.pdfTarrahan Parseh Transportation Research InstituteInternational Journal of Transportation Engineering2322-259X12220241001Presenting a Strategic Model of Traffic Reduction using the Analysis of the Implementation Models of Successful Countries (Case Study: Central Roads of Yazd City)1803181920897810.22119/ijte.2024.467198.1668ENHamidDehghan BanadakiPhD, Department of Civil Engineering, faculty of civil and earth resources engineering, Central Tehran Branch, Islamic Azad University, Tehran, Iran0000-0003-3652-8272ShahabadinHajforoushPhD in Geography and Urban Planning, Yazd University, Yazd, IranSeyed SaeedMazloomy MahmoodabadProfessor, Social Science Research Center of Health, School of Public Health, Shahid Sadoughi University of Medical Science, Yazd, IranMehdiHamidiPhD student, Department of Computer Engineering, Faculty of Technology and Engineering, Islamic Azad University Yazd Branch, Yazd, IranJournal Article20240710<span lang="EN-GB">Transportation and moving is one of the main aspects of urban life, and organizing transportation is one of the primary needs of any healthy and good city. The existence of traffic problems in the central border of the cities is an issue that unfortunately is not given due attention by the city management, while the traffic problem causes irreparable damage to the economy of the city and the country. Therefore, the purpose of this research is to achieve a strategic model of traffic reduction in the central roads of Yazd city by using the analysis of implementation models of successful countries. The current research is applied in terms of purpose and descriptive-analytical in terms of nature and method. In order to analyse the data and to adopt the strategic model necessary to reduce the traffic of the central roads of Yazd city, the SWOT model has been used. The results of this research show that the total weighted score of internal factors is 1/93, which is less than the average of 2/5. As a result, it can be said that the weak points in the area of traffic reduction in the central roads of Yazd city are superior to its strong points. Also, the total weighted score of external factors is 1/6, which is less than the average of 2/5. It can be said that the threats in the field of reducing the traffic of the central roads of Yazd city are superior to its opportunities. And according to the internal and external factors of the central roads of Yazd city as well as the implementation models of successful countries, defensive strategies should be prioritized to reduce the traffic of the central roads of Yazd city.</span>http://www.ijte.ir/article_208978_090e9119582550d721c3e7a7e04f56ae.pdfTarrahan Parseh Transportation Research InstituteInternational Journal of Transportation Engineering2322-259X12220241001Evaluation of Factors Affecting Pedestrian Walking Speed in Pedestrianized Areas (Case Study: Tehran City)1821183421051610.22119/ijte.2024.469042.1670ENAmirarfaShiraniMs.c, Department of Civil Engineering, Science and Research Branch, Islamic Azad University, Tehran, IranGholam RezaShiranDepartment of Civil Engineering and Transportation, University of Isfahan, Isfahan, IranAliNaderanDepartment of Civil Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran0000-0001-5842-0188Journal Article20240721<span lang="EN-GB">The behavior and reaction of pedestrians play a special role in the development and management of pedestrian facilities, especially in the central business district of cities. Pedestrianized areas increase the welfare and safety of pedestrians and help improve economic viability and environmental criteria. Through a comprehensive review of relevant studies, it is shown that no study has been conducted so far to evaluate the effect of different parameters such as age, gender, weight, rainfall, and umbrella carrying on the walking speed on crowded and walkable streets in Tehran, Iran. Additionally, to the best of our knowledge, no study has been conducted to determine the average speed of pedestrians under normal and rainy conditions. Therefore, the present study applies the walking speed of 5805 pedestrians through the crowded pedestrianized areas of Tehran in the year 2019 to compare the walking speed of the pedestrians between normal and rainy conditions. Further, factors such as gender, weight, and rainfall on the walking speed of pedestrians are analyzed using the t-test. According to the obtained results, it can be found that based on a 95% confidence level, the difference in speed between men and women is statistically significant for all age and weight groups except teenagers and elderly pedestrians, and males walk faster than females in all conditions. Rainfall has shown to have an effect on the walking speed of male pedestrians, and females tend to walk slower than males. The values of 0.79 and 0.99 m/s for the 15th percentile speed and the mean speed of 1.09 and 1.12 through the walkable facilities are recommended for normal and rainy weather, respectively. Based on increasing the 15th percentile and the mean speed of pedestrians under rainy conditions, it is suggested that implementing safety measures such as weather-appropriate signage to control walking speed in order to reduce potential hazards and accidents in pedestrianized areas. The results of the present study can also lead to safer and more user-centric urban spaces that prioritize pedestrian comfort, convenience, and inclusivity under various weather conditions.</span>http://www.ijte.ir/article_210516_4f6543f06eb835fb78c8bce37161e65f.pdf