Modeling the severity of accidents based on the most effective variables accounts for developing a high-precision model presenting the possibility of occurrence of each category of future accidents, and it could be utilized to prioritize the corrective measures for authorities. The purpose of this study is to identify the variables affecting the severity of the injury, fatal, and property damage only (PDO) accidents in Rasht city by collecting information on urban accidents from March 2019 to March 2020. In this regard, the multiple logistic regression and the pattern recognition type of artificial neural network (ANN) as a machine learning solution are used to recognize the most influential variables on the severity of accidents and the superior approach for accident prediction. Results show that the multiple logistic regression in the forward stepwise method has R² of 0.854 and an accuracy prediction power of 89.17. It turns out that the accidents occurred between 18 and 24 and KIA Pride vehicle has the highest effect on increasing the severity of accidents, respectively. The most important result of the logit model accentuates the role of environmental variables, including poor lighting conditions alongside unfavorable weather and the dominant role of unsafe and poor quality of vehicles on increasing the severity of accidents. In addition, the machine learning model performs significantly better and has higher prediction accuracy (98.9) than the logit model. In addition, the ANN models greater power to predict and estimate future accidents is confirmed through performance and sensitivity analysis.

The purpose of this study was to develop models to predict the severity of pedestrian accidents on rural roads of Guilan, Iran. Therefore, the probability of occurrence of any type of accidents was measured using the accident data from March 2014 to March 2019. Eleven independent variables affecting the severity of pedestrian accidents as well as statistical analysis such as the frequency analysis, Friedman test and factor analysis, and modeling including multiple logistic regression and artificial neural networks using multi-layer perceptron (MLP) and radius basis function (RBF) have been used. Results of modeling and analysis of pedestrian accidents in different methods showed each of the methods depending on their function investigated the severity of accidents with different point of view and had different results. As a result, putting the output results together, the best measures can be suggested to increase the safety of pedestrians on the rural roads of Guilan.

The construction of suitable roads in rainy areas has created problems in the construction process due to the low resistance of asphalt to moisture. To solve this problem, materials are commonly used that make mixtures resistant to moisture; however, these materials may reduce the dynamic resistance of asphalt. Therefore, materials should be used that, in addition to increasing the dynamic resistance, also increase the moisture resistance of asphalt mixtures. One of these materials used in this research is steel wool fiber (SWF), which in addition to creating conductive roads also could have a significant effect on moisture resistance. In this study, the impact of 2%, 4%, 6%, 8%, and 10% SWF on the Marshall stability and moisture sensitivity of mixtures was investigated using the Marshall stability and indirect tensile strength (ITS) tests, respectively. Moreover, using SWF as a conductive fiber, the conductivity properties of asphalt mixtures were explored to find the optimal amount of electrical conductivity. The results of the Marshall stability test indicated that by increasing SWF contents, the stability of mixtures increased, compared with the base sample, and greater amounts of 6% SWF resulted in the reduction of the Marshall stability. The results of ITS showed that modification of bitumen by SWF increased ITS and tensile strength ratio (TSR) amounts of mixtures. 6% SWF was the optimal amount for enhancing the resistance of asphalt mixtures to moisture sensitivity. The results of the electrical resistivity test showed that the resistivity had three phases: high resistivity, transit, and low resistivity. Mixtures containing less than 4% SWF illustrated an insulating behavior, with electrical resistivity greater than 7.62 × 10⁸ Ω.m. At the transit phase, the resistivity of mixtures had a sharp reduction from 7.62 × 10⁸ Ω.m to 6.17 × 10⁴ Ω.m. Finally, 8% SWF was known as the optimal content for the electrical conductivity of mixtures.

Moisture damage is known to be a key factor influencing the durability of asphalt pavements. This phenomenon will reduce the mechanical properties of asphalt mixtures due to its destructive effects on the adhesion of the bitumen‐aggregate system and the cohesion of the bitumen membrane. The mineral properties of the aggregates of asphalt mixtures are one of the factors affecting moisture susceptibility. Therefore, the surface free energy (SFE) method, as one of the thermodynamic methods, and indirect tensile strength test (ITST) have been used to determine the failure mechanism and the rate of change of adhesion properties of asphalt mixtures under the influence of mineralogical characteristics. Prior to the above tests, an X‐ray fluorescence spectrometry (XRF) test was performed to identify aggregate‐forming minerals in eight different types of aggregates with various minerals from eight mines, and also the apparent bitumen film thickness was measured. XRF test results showed that most parts of the aggregates in mines 1– 6 were composed of SiO₂, which had strong acidic properties, according to the SFE results. ITST results showed that samples constructed with aggregates of mine 7 and 8 (with high CaO mineral content) experienced a higher TSR than other mixtures in all freeze‐thaw (F‐T) cycles. Results of the SFE method showed that aggregates with more calcareous properties had a smaller acidic component and a larger basic component. In mines 7 and 8, where the nonpolar component of their aggregates was larger, the tendency of the aggregates to adherence and wettability by water decreased. The adhesion free energy (AFE) between bitumen and aggregates with higher CaO and less SiO₂ amounts was more than AFE between bitumen and aggregates with lower CaO and higher SiO₂ amounts, in dry conditions. The presence of higher amounts of CaO in aggregates increased AFE of bitumen‐aggregate in presence of water from a negative value to zero. In linear regression analysis, due to the positive regression coefficient of the CaO mineral, this mineral had a positive impact on TSR; on the other hand, due to the negative regression coefficient of the SiO₂ mineral, this mineral had a negative impact on the TSR of asphalt mixtures.