Browsing by Author "Kuskapan, Emre"

Now showing 1 - 19 of 19

Analysing Traffic Accidents in Terms of Driver Violation Behaviour Types: Machine Learning and Sensitivity Analysis Approaches
(Wiley, 2025) Kuskapan, Emre; Codur, Muhammed Yasin; Dissanayake, Dilum
Traffic accidents have become a major concern for governments, organizations and individuals worldwide due to the material and moral losses they cause. It is possible to reduce this concern by taking into account the research conducted by relevant institutions and organizations in this field. The main objective of this study is to categorize traffic accidents according to driver violation types and analyse them using machine learning algorithms and feature sensitivity to identify the most influential variables in each category. For this purpose, traffic accident reports that occurred in Erzurum province in the last 1 year were used to categorize and classify driver violation behaviour types. Five different machine learning algorithms, namely k-nearest neighbour, support vector machines, naive Bayes, multilayer perception and random forest, were used to examine the success performance of the classification. Among these, 91% successful classification was obtained with the random forest algorithm. Based on the classification obtained from this algorithm, sensitivity analysis was used to reveal the variables that most affect each violation category. The results of the analysis revealed that driver age and vehicle type were the most influential variables for many types of violations. Thanks to this study, the problems were clearly identified by going into the details of driver violation behaviours. At the end of the study, measures to reduce driver violation behaviours were proposed. If the recommendations that can reduce driver behaviour are taken into consideration by transportation authorities and policy makers, traffic accidents can be significantly reduced.
An Assessment of the Relationship Between Micro-Mobility Use and Air Quality in Selected Cities
(Elsevier, 2024) Kuskapan, Emre
Air pollution causes serious health problems and environmental impacts in many countries around the world. This study aims to reveal the relationship between the micro-mobility usage frequency and air pollution in cities. In order to reveal this relationship, the micro-mobility usage frequency and air quality index values of PM2.5 and PM10 pollutants for 6 different cities with similar population from different parts of the world were used. According to the results of Pearson correlation analysis, a correlation coefficient of -0.961 and - 0.917 was obtained between the micro-mobility usage frequency and the air quality index of PM2.5 and PM10, respectively. This result shows that the micro-mobility usage frequency affects the air quality with a very strong relationship. Cities with high micro-mobility use, such as Singapore and Philadelphia, have less air pollution, while cities with low micro-mobility use, such as Ankara and Milano, have more air pollution. It is believed that the results obtained from the study provide important ideas for policy makers and transportation planners to design cities with sustainable transportation infrastructure. By increasing investment in the use of micro-mobility vehicles in cities and encouraging people to use this type of transportation, air pollution can be significantly reduced.
Comparison of Modern and Conventional Methods at the Entrance and Exit of Tunnels
(City Net Scien Res Ctr Ltd-belgrade, 2018) Alemdar, K. Diler; Kaya, Omer; Kuskapan, Emre; Codur, M. Yasin; Tortum, Ahmet
Turkey has gained importance especially highway transport since 1950. For this reason, the number of vehicles on the highways has rapidly increased and this increase has brought many problems. The most important problem is traffic accidents which cause material and spiritual loss. The Winter conditions that are effective in some regions of the country occur disruptions in highway transportation. Particularly in winter when the temperatures are below 0 degrees C accidents happen due to the snow and icing. Although millions of dollars are spent every year to struggle against snow and icing, existing methods are insufficient. Conventional methods used in the struggle against snow and ice damage to pavements, metal parts, environment, human health and economy of the country. Tunnels are often used because of Turkey's geographical situation. 'Traffic accidents are often seen at the entrance and exit of tunnels, especially during the winter seasons because of snow and icing. In these areas, the ice detection and prevention systems as an application of intelligent transportation system can be used instead of conventional methods to reduce the number of traffic accidents. In this study, it is compared that conventional method with the ice detection and prevention system in terms of advantages and disadvantages.
Enhancing Energy Management in Railway Transportation: A High-Accuracy Prediction Approach Using Ensemble Machine Learning
(Wiley, 2026) Kuskapan, Emre; Codur, Muhammed Yasin; Codur, Merve Kayaci; Dissanayake, Dilum
Predicting energy consumption helps countries make strategic decisions in many critical areas such as energy management, economic development, energy security, environmental sustainability and infrastructure investments. Therefore, accurate and reliable energy consumption predictions are vital to ensure the sustainability and prosperity of countries. This study aims to contribute to the proper planning of transportation policies and energy management by successfully predicting T & uuml;rkiye's railway energy consumption. In this direction, energy prediction values were obtained from 18 different machine learning methods using the country's railway line length, number of passengers, freight amount and energy consumption values from 1977 to 2024. To further strengthen the results obtained with these methods, bagging, boosting, stacking and blending ensemble learning methods were utilized. With the improvements, the R-squared value was increased up to 0.9667 and energy predicting was achieved with very high accuracy. Based on the results obtained from this study, it is possible to provide investment planning more efficiently. In addition, the implementation of energy management strategies, infrastructure planning and sustainable energy policies will be provided more efficiently as a result of obtaining more successful results by using ensemble machine learning methods instead of traditional machine learning methods for energy consumption predictions in different sectors.
Estimating the Bitumen Ratio to Be Used in Highway Asphalt Concrete by Machine Learning
(Riga Technical Univ-RTU, 2024) Codur, Muhammed Yasin; Kasil, Halis Bahadir; Kuskapan, Emre
Hot mix asphalt, which is frequently used in road pavements, contains bitumen in certain proportions. This bitumen ratio varies according to the layers in the road pavements. The bitumen ratio in each pavement is usually estimated by the Marshall design method. However, this method is costly as well as time-consuming. In this study, the Naive Bayes method, which is a machine learning algorithm, was used to estimate the bitumen ratio practically. In the study, a total of 102 asphalt concrete designs were examined, which were taken from the wearing course, binder course, and asphalt concrete base course and stone mastic asphalt wearing course layers. Each road pavement layer was divided into three different classes according to the bitumen ratios and the algorithm was trained with machine learning. Then the bitumen ratio was estimated for each data set. As a result of this process, the bitumen ratios of the layers were estimated with an accuracy between 75% and 90%. In this study, it was revealed that the bitumen ratio in the road pavement layers could be estimated practically and economically.
Exploring the Influence of Socio-Economic Aspects on the Use of Electric Scooters Using Machine Learning Applications: A Case Study in the City of Palermo
(Elsevier, 2024) Campisi, Tiziana; Kuskapan, Emre; Codur, M. Yasin; Dissanayake, Dilum
Most European countries have been committed to reducing their carbon footprint, combating climate change, and reducing the air pollution typical in large cities over the past decade. Among current solutions that can be adopted are the replacement of fuel-powered means of transport with electric ones, as well as the introduction of car sharing, bike sharing and electric scooters. The post-pandemic phase was characterized by a greater propensity to use these means of transport as they were perceived as a healthier choice (for a greater possibility of implementing social distancing) and cheaper (for the diffusion of shared services). The study of modal choice depends on socio-economic structures. The present work analyses data related to socio-economic factors (work, income and other) to examine the tendency to use electric scooters in the metropolis of Palermo, Sicily, through machine learning algorithms. The comparison of different algorithms allowed us to underline how the multilayer perceptron algorithm obtained the best classification among the minimal sequential optimization algorithms. The findings also highlight middle-income and freelancer people as being more likely to use micro-mobility than others. Contrary to what was thought, these findings revealed that micro-mobility is not just a preferred mode of transport for low-income people or students. These trends will be able to encourage continuous monitoring of the relevant factors and will be able to help political decision-makers to increase and improve the diffusion of micro-mobility and to direct marketing campaigns to the groups identified here.
Identifying the Most Critical Intersections in Transportation Networks
(Univ Osijek, Tech Fac, 2021) Kuskapan, Emre; Codur, M. Yasin; Tortum, Ahmet
With the increasing population worldwide, the number of vehicles is increasing day by day. This increase also creates different traffic problems. Various analysis methods are developed to solve traffic problems and to better examine the road transport network. Especially with the development of technology and intelligent transportation systems entering our lives, analyses can be made using computer software and programs. In this study; using the social network analysis method, the use of which has increased in the field of transportation in recent years, the highway network structure of Erzurum Province - which consists of district connection roads has been analyzed. While making the analysis, the network structure was examined through five different centrality concepts and the critical sequence of the intersections in the district connection roads was determined. Accuracy percentages of the concepts of centrality were determined by comparing the sequences obtained with the sequences actually applied. Then, it was determined that the most suitable centrality concept for the study was Bonacich Power.
Impact of COVID-19 on Public Transportation Usage and Ambient Air Quality in Turkey
(Sveuciliste U Zagrebu, Fakultet Prometnih Znanosti, 2021) Sahraei, Mohammad Ali; Kuskapan, Emre; Codur, Muhammed Yasin
COVID-19 caused by the SARS-CoV-2 virus is a global health concern due to the quick spread of the disease. In Turkey, the first confirmed COVID-19 case and death occurred on 11 and 15 March 2020, respectively. There is a lack of research on the impact of COVID-19 on public transportation mobility and the Air Quality Index (AQI) around the world. The objective of this research is to consider the impact of COVID-19 on public transportation usage and consequently the AQI level in Turkey. Data collection for the analysis of public transportation usage and the air quality status during pre-lockdown and lockdown was carried out using the public transportation applications Moovit and World's Air Pollution. The results demonstrated that during the lockdown in Ankara and Istanbul, public transportation usage dramatically decreased by more than 80% by the end of March and did not change significantly until the end of May. As regards air quality, the results confirmed that air quality improved significantly during the lockdown. For Ankara and Istanbul, the improvement was estimated at about 9% and 47%, respectively.
Improving the Management of Operations of the E-Scooter Services in Sicily: A First Step of a Descriptive Statistical Survey
(Univ Zilina, 2023) Campisi, Tiziana; Vianello, Chiara; Kuskapan, Emre; Codur, Muhammed Yasin; De Cet, Giulia
The recent pandemic has changed the modal choices of users in the urban context, highlighting in the last two years an increase in the diffusion of electric scooters, which is not homogeneous in the Italian context. At the beginning of 2020, the first e-scooter services were launched in Sicily, with the city of Palermo leading the way. A survey was therefore conducted in Sicily involving approximately 550 regular users of e-scooter services. The descriptive statistical analysis undertaken compared three different periods pre, during and post pandemic, with particular attention to the gender and age gap and different trends in the diffusion of multimodality. The results provide not only some suggestions for the improvement of services by managers but some suggestions to local administrators for implementation of democratic and sustainable planning steps, as well.
Investigation of Physical and Chemical Properties of Bitumen Modified with Waste Vegetable Oil and Waste Agricultural Ash for Use in Flexible Pavements
(MDPI, 2023) Colak, Muhammed Ali; Zorlu, Elif; Codur, Muhammed Yasin; Bas, Fatih Irfan; Yalcin, Ozgen; Kuskapan, Emre
The rapid growth of the world population and the rapid diversification of consumption habits due to technological advancements have increased waste production. An investigation of the effects of biomass products, such as waste vegetable oil and waste agricultural ash, on bitumen's physical and chemical properties was conducted in this study. By recycling biomass products, this study aimed to improve the performance and stability of bituminous hot mixtures, optimize the number of additives, and create more economical designs. Using the Taguchi method, 0%, 2%, 4% by weight of waste vegetable oil and 0%, 3%, and 6% by weight of waste agricultural ash were added to 70/100 penetration pure bitumen with an orthogonal array of L9. For 10, 20, and 30 min, modified bitumen samples were prepared at 170 degrees C, 180 degrees C, and 190 degrees C with a constant mixing speed of 3000 RPM. The samples were tested for penetration, softening point, flash point, rolling thin film oven (RTFOT), FTIR, and Marshall Design stability and flow. Based on the obtained performance statistics, 95% confidence levels were assigned to the predictions. The stability and softening point values decreased as the oil content increased, while flash and penetration values increased. With increasing ash content, stability, flash, and softening point values increased, and penetration values decreased. Compared to oil and ash additives, mixing temperature and time had relatively little effect on the modification process. Overall, the optimum parameter levels were 4% for oil, 0% for ash, 170 degrees C for temperature, and 10 min for time.
Investigation of the Effect of Slope and Road Surface Conditions on Traffic Accidents Occurring in Winter Months: Spatial and Machine Learning Approaches
(MDPI, 2024) Kuskapan, Emre; Codur, Muhammed Yasin; Sahraei, Mohammad Ali
Winter weather can cause extremely dangerous road conditions. In order to analyze traffic accidents occurring in winter months in more detail, it is very important to evaluate the slope and the condition of road surfaces together. For this purpose, this study analyzed the accidents that occur during these months in Erzurum, one of the cities in Turkey with long winter months. A total of nine different classes of road conditions were created according to these two factors. In accordance with these classes, the accidents were analyzed using machine learning algorithms, and the success of the classification was analyzed. As a result of the analysis, it was found that the J48 algorithm gave more accurate results. J48 processes both continuous and categorical attributes and is a decision tree algorithm that can effectively manage missing data. According to the results of this algorithm, a map of accident density in the city was created using ArcGIS 10.5 software. Accordingly, it was found that the highest risk of accidents during the winter months occurred on road sections with a slope of more than 6% and covered with ice. Another important result of the study is that the slope of the road is a more effective factor than the surface condition.
Long-Term Impact of Micro-Mobility on Air and Noise Pollution: A GIS Approach
(Elsevier, 2026) Kuskapan, Emre
This study examines the current status of air and noise pollution along Erzurum's micro-mobility route and the expected changes under the 2030 sustainable transportation scenario. Measurements were conducted at 64 points, considering PM2.5 concentrations for air pollution and sound levels for noise pollution. Using Turkey's 2030 sustainability targets, a scenario was developed for 14 different areas to assess the potential impact of increased micro-mobility use on pollution levels. The results indicate a general decrease in PM2.5 values, with reductions reaching up to 24 % in certain areas, while noise pollution levels declined by up to 18 %. Spatial distribution maps were created using ArcGIS 10.3.1 to compare current conditions and future projections. The findings highlight the significant role of micro-mobility in reducing urban pollution and emphasize its potential in sustainable urban planning. This study provides valuable insights for policymakers in developing environmentally friendly transportation strategies.
Machine Learning Applications for Pedestrian Safety in Urban Transportation
(Emerald Group Publishing Ltd, 2026) Kuskapan, Emre; Codur, Muhammed Yasin
Pedestrian crossings have a crucial role in urban transportation. The design of pedestrian crossings in accordance with standards enables the reduction of financial losses, air pollution and delays in traffic, as well as improvements in pedestrian safety. In this study, the aim is to examine, using machine learning, whether all pedestrian crossings in a city are designed according to standards. Eleven basic variables were determined for a total of 719 pedestrian crossings in the city centre of Erzurum, Turkey. The problems detected in the pedestrian crossings in the city were divided into nine different classes using these variables. Problems in pedestrian crossings were classified by machine learning algorithms: decision tree, naive Bayes, k nearest neighbours, regression, multilayer perceptron and support vector machine. In classification results, the decision tree algorithm gave more successful results than other algorithms. It was determined that approximately 74% of pedestrian crossings have some problem. According to the results obtained with this algorithm, it was determined that a lack of marking is frequently encountered in pedestrian crossings and that there is an insufficiency of wheelchair ramps. In the last part of the study, suggestions for solutions for all these problems detected in pedestrian crossings are presented.
Pedestrian Safety at Signalized Intersections: Spatial and Machine Learning Approaches
(Elsevier Sci Ltd, 2022) Kuskapan, Emre; Sahraei, Mohammad Ali; Codur, Merve Kayaci; Codur, Muhammed Yasin
Introduction: The major goal of the present research is to determine hotspot areas by the generation of a geospatial model and develop a model associated with pedestrian-vehicle crash injuries (severe, moderate, slight) at signalized intersections in Erzurum, Turkey.& nbsp;Methodology: This study used the comprehensive algorithm in Artificial Neural Network (ANN). Data from 197 crashes injury (2015-2019) at 57 intersections depending on the mix of variables such as driver, road and vehicle characteristics, and environment data were collected.& nbsp;Results: Within the four candidate models, the first one including pedestrian density, level of education, traffic congestion, type of vehicle, presence of bus stop, age, and gender had the lowest RMSE and MAE values and the greatest R-2 value. Lastly, sensitivity analyses were conducted to evaluate the impact of independent parameters.& nbsp;Conclusions: The importance of the study lies in the expected outcomes to assist the experts to address the pedestrian-vehicle crash risk factors by conducting appropriate countermeasures for facilities management/improvement.
Public Transit Usage and Air Quality Index During the COVID-19 Lockdown
(Academic Press Ltd- Elsevier Science Ltd, 2021) Sahraei, Mohammad Ali; Kuskapan, Emre; Codur, Muhammed Yasin
The people suffering from coronavirus have to lead unprecedented actions including limiting travel especially using public transportation. Therefore, lockdown measures and social distancing to decelerate the distribution of the COVID-19 has become the new norm. Nevertheless, improvement in the ambient air quality of the cities globally has appeared as a key advantage of this lockdown. There is a lack of research in the field of public transportation mobility and the Air Quality Index (AQI) during the COVID-19 lockdown globally. Consequently, this research aims to examine the overall impact of the public transit usage and ambient air quality, i.e. both AQI and indicatory air pollutants, during the lockdown in 12 countries. Data collections for analysis of public transportation usage and air quality status during the lockdown and one year before this period were carried out utilizing public transportation application Moovit and World?s Air Pollution. The results demonstrated that the lockdowns of 12 countries led to dramatically decreased human movements and public transit usage up to -90% until the end of March and it had no major changes until the end of May. In the case of ambient air quality, the average values of AQI in the 12 countries within lockdown 2020 for classes I(AQI:0-50), II(AQI:51-100), and III (AQI:101-150) increased by 12%, 9%, and 13% while for classes IV(AQI:151-200), V(AQI:201-300) and VI (AQI:301-greater) decreased by 10%, 27%, and 3% in comparison with the identical time throughout 2019. The results also indicate that throughout lockdown 2020, in the 12 countries, the percentages of indicatory air pollutants of PM2.5, PM10, SO2, CO, and NO2 were decreased by 16%, 21%, 41%, 48%, and 35% lower than those in the same time in 2019. Mechanism analysis and comparisons highlighted that the lockdowns of 12 countries led to decreased human mobility and improvement in the AQI around the world.
Speed Violation Analysis of Heavy Vehicles on Highways Using Spatial Analysis and Machine Learning Algorithms
(Pergamon-Elsevier Science Ltd, 2021) Kuskapan, Emre; Codur, M. Yasin; Atalay, Ahmet
With the development of technology in the world, vehicles that reach high speeds are produced. In addition, with the increase of road width and quality, faster and more comfortable transportation can be provided. These developments also increase the speed violation rates of road vehicles. Drivers who violate speed limits can endanger both their own lives and the lives of others. Speed violations, of especially heavy vehicles, involve much greater risks than that of light vehicles. Heavy vehicles can cause more serious losses of lives and property in accidents, compared to the ones caused by light vehicles, as they can carry much more freight or passengers than light vehicles. In this study, data regarding the speed violations committed by heavy vehicles in Turkey, were used. Speed violations were divided into 10 classes according to the intensity of speed violation rates. After this process, all provinces were classified according to support vector machines (SVM), naive bayes (NB) and knearest neighbors (KNN) algorithms. When the accuracy values and error scales of all three algorithms are examined, it has been determined that the algorithm that gives the most accurate results is the NB algorithm. Based on the classification of this algorithm, speed violation density maps of types of heavy vehicles in Turkey were created by using spatial analysis. According to the density maps, the provinces with the highest speed violations were identified. In the results, it was determined that the rate of heavy vehicle speed violation was highest in the cities such as Erzurum, Konya, and Mug?la. Later, these cities were examined in terms of heavy vehicle mobility. At the end of this study, measures were proposed to reduce these violations in cities where speeding violations are intense. Material and moral damages can be prevented, to a great extent, with the implementation of recommendations of policymakers which can reduce speed violations.
A Study on the Examination of the Geologic Structure in Terms of Rail Transportation
(National Inst Science Communication-NISCAIR, 2021) Kuskapan, Emre; Aydin, OmerLutfu; Codur, Muhammed Yasin
Rail systems have an important place among the types of transportation. Although it was preferred for intercity transportation in the past, but now-a-days it is frequently preferred in urban roads. Some rail system structures move from the ground surface, while others move under the ground. Various geotechnical researches have been carried out for rail systems moving under the ground. However, for the rail vehicles moving on the ground surface are generally placed on the highway route, ground parameters are not taken into consideration. This situation can cause serious rail system accidents. This study has been conducted in Turkey's Erzurum drilling planned light rail system in terms of soil properties, it was evaluated by survey results of drilling borehole, microtremor, and multichannel analysis of surface waves (MASW). According to the results of this study, a part of the light rail system (LRS) route was found to be insufficient in terms of ground safety. For this reason, improvement in the ground or revision of the route has been suggested.
Turkey Railway Transport History and Policies
(City Net Scien Res Ctr Ltd-belgrade, 2018) Kaya, Omer; Kuskapan, Emre; Alemdar, K. Diler; Codur, M. Yasin; Atalay, Ahmet
The railways constructed and operated during the Ottoman Empire period were realized with the external capital that foreign entrepreneurs execute. Humanitarian Anatolia was introduced in 1856, 33 years after the first use of steam locomotives in the world. The total length of the railway network transferred to the Republic of Turkey, founded in 1923, it is 4,136 kilometers from the Ottoman Empire. During the period of 1923-1950, when railway transportation was considered as a state policy, a total of 3,764 kilometers of railways were built, average of 139 kilometers per year. Railways in this period were considered as a modernization project with all social aspects surrounding development and reconstruction. Due to seasonal problems, the railway was abandoned from 1950 to 2000. In these years when a recession period experienced, railways were completely neglected and only 945 kilometers of railways were built. Important investment projects to be put into practice after 2000 were planned and investment projects on railways were determined. Between 2004 and 2016, a total of 1,805 kilometers of railways were built an average of 138 kilometers per year. Currently, 4,053 km of railway is under construction. The studies that the country have carried out by focusing on the 2023 goals are now giving positive results. Efforts to increase the length of the railway network are under construction. Integration of the railway network with other transport systems must be ensured. It is aimed to reach the desired levels in railway freight and passenger transportation. Therefore, the study has presented suggestions about the improvement and development of Turkish railways and country policies.
Urban Road Transport Network Analysis: Machine Learning and Social Network Approaches
(Univ Zilina, 2022) Kuskapan, Emre; Codur, M. Yasin; Tortum, Ahmet; Tesoriere, Giovanni; Campisi, Tiziana
Traffic congestion is one of the most significant problems in urban transportation. It has been increasing, especially in regions close to intersections. Several methods have been developed to reduce the traffic congestion. One of the analysis methods is social network analysis (SNA). This method, which has increased use in transportation, can quickly identify the most central intersections in transportation networks. Improvements to central intersections, identified in a road network structure, speed up the traffic flow across the entire network structure. In this study, the Istanbul highway transportation network has been examined and values for a series of network centrality measures have been calculated using the SNA. The accuracy and error scales of the centrality values were compared using a machine learning algorithm. The Bonacich power centrality has been the best performance. Based on the study results the most central intersections in Istanbul have been determined.