There have been numerous studies on traffic accidents and their severity, particularly in relation to weather conditions and road geometry. In these studies, traditional statistical methods have been employed, such as linear regression, logistic regression, and negative binomial regression modeling, which are the most common linear and non-linear regression analysis methods. In this research, machine learning architecture was applied to this problem using the random forest, artificial neural network, and decision tree techniques to ascertain the strengths and weaknesses of these methods. Three data sets were used: road geometry data, precipitation data, and traffic accident data over nine years corresponding to the Naebu Expressway, which is located in Seoul, Korea. For the model evaluation, three measures were employed: the out-of-bag estimate of error rate (OOB), mean square error (MSE), and root mean square error (RMSE). The low mean OOB, MSE, and RMSE observed in the results obtained using the proposed random forest model demonstrate its accuracy.

Euro 6 standards impose stringent nitrogen oxide (NO_x) emission limits on diesel cars. NO_x emissions are significantly different between Euro 6 diesel cars and the previous standards in real-world driving. In this research, the NO_x concentrations of Euro 6 diesel engines during real-world driving were studied considering various factors. Real driving emission (RDE) tests were conducted using vehicles equipped with portable emissions measurement systems. Urban, rural, and motorway test routes were utilized. Road environment, atmospheric, and after-treatment performance factors were collected in each case. An artificial neural network was used for evaluation using RDE test data and various statistical parameters. It was found that the proposed method predicted the pollutant emissions effectively. Lastly, the relative importance of each predictor was derived, and the NO_x concentrations were analyzed. These approaches provide accurate emission information for an environmental effect evaluation that reflects more realistic road conditions.

Managing a fleet efficiently to address demand within cost constraints is a challenge. Mismatched fleet size and demand can create suboptimal budget allocations and inconvenience users. To address this problem, many studies have been conducted around heterogeneous fleet optimization. That research has not included an examination of different vehicle types with travel distance constraints. This study focuses on optimizing the University of Tennessee (UT) motor pool which has a heterogeneous fleet that includes electric vehicles (EVs) with a travel distance and recharge time constraint. After assessing UT motor pool trip patterns as a case study, a queuing model was used to estimate the maximum number of each vehicle type needed to minimize the expected customer wait time to near zero. The break-even point is used for the optimization model to constrain the minimum number of years that electric vehicles should be operated under the no-subsidy assumption. The results show that the fleet has surplus vehicles. In addition to reducing the number of vehicles, total fleet costs could be minimized by using electric vehicles for all trips less than 100 miles. The models are flexible and can be applied and help fleet managers make decisions about fleet size and EV adoption.

South Korea has the tenth highest greenhouse gas (GHG) emissions worldwide, of which 16% originates from the road sector. Existing estimation methods of road GHG emissions have various limitations, such as low accuracy or the ability to only estimate GHG emissions within a limited area. Therefore, this study aimed to develop a methodology to estimate GHG emissions while considering various geometric designs of roads, including both vertical and horizontal alignment. The developed method is more objective and reliable than existing methodologies that consider only vertical alignment. First, Lamm's theory on travel speed profiles was applied to predict GHG emissions. Then, this study attempted to overcome the limited spatial estimation capacity of existing methods by considering upstream and downstream geometric design parameters simultaneously. Second, this study used the GHG operation mode extracted from the MOtor Vehicle Emission Simulator (MOVES), a modeling system that estimates emissions for mobile sources at the national, county, and project levels for criteria air pollutants, GHGs, and air toxicity. The operation mode includes vehicle type, fuel, and other factors, and is designed to estimate GHG emissions at 1-s intervals. Based on the results of the analysis, the effectiveness of the new method was compared to existing methods using an economic analysis (e.g., cost-benefits from the reduced emissions). This study presents a method for performing sensitive estimations of GHG emissions according to the geometric design of roads, which can be used to collect more accurate data on GHG emissions.