Road traffic accidents are one of the world’s most serious problems, as they result in numerous fatalities and injuries, as well as economic losses each year. Assessing the factors that contribute to the severity of road traffic injuries has proven to be insightful. The findings may contribute to a better understanding of and potential mitigation of the risk of serious injuries associated with crashes. While ensemble learning approaches are capable of establishing complex and non-linear relationships between input risk variables and outcomes for the purpose of injury severity prediction and classification, most of them share a critical limitation: their “black-box” nature. To develop interpretable predictive models for road traffic injury severity, this paper proposes four boosting-based ensemble learning models, namely a novel Natural Gradient Boosting, Adaptive Gradient Boosting, Categorical Gradient Boosting, and Light Gradient Boosting Machine, and uses a recently developed SHapley Additive exPlanations analysis to rank the risk variables and explain the optimal model. Among four models, LightGBM achieved the highest classification accuracy (73.63%), precision (72.61%), and recall (70.09%), F1-scores (70.81%), and AUC (0.71) when tested on 2015–2019 Pakistan’s National Highway N-5 (Peshawar to Rahim Yar Khan Section) accident data. By incorporating the SHapley Additive exPlanations approach, we were able to interpret the model’s estimation results from both global and local perspectives. Following interpretation, it was determined that the Month_of_Year, Cause_of_Accident, Driver_Age and Collision_Type all played a significant role in the estimation process. According to the analysis, young drivers and pedestrians struck by a trailer have a higher risk of suffering fatal injuries. The combination of trailers and passenger vehicles, as well as driver at-fault, hitting pedestrians and rear-end collisions, significantly increases the risk of fatal injuries. This study suggests that combining LightGBM and SHAP has the potential to develop an interpretable model for predicting road traffic injury severity.

To undertake a reliable analysis of injury severity in road traffic accidents, a complete understanding of important attributes is essential. As a result of the shift from traditional statistical parametric procedures to computer-aided methods, machine learning approaches have become an important aspect in predicting the severity of road traffic injuries. The paper presents a hybrid feature selection-based machine learning classification approach for detecting significant attributes and predicting injury severity in single and multiple-vehicle accidents. To begin, we employed a Random Forests (RF) classifier in conjunction with an intrinsic wrapper-based feature selection approach called the Boruta Algorithm (BA) to find the relevant important attributes that determine injury severity. The influential attributes were then fed into a set of four classifiers to accurately predict injury severity (Naive Bayes (NB), K-Nearest Neighbor (K-NN), Binary Logistic Regression (BLR), and Extreme Gradient Boosting (XGBoost)). According to BA’s experimental investigation, the vehicle type was the most influential factor, followed by the month of the year, the driver’s age, and the alignment of the road segment. The driver’s gender, the presence of a median, and the presence of a shoulder were all found to be unimportant. According to classifier performance measures, XGBoost surpasses the other classifiers in terms of prediction performance. Using the specified attributes, the accuracy, Cohen’s Kappa, F1-Measure, and AUC-ROC values of the XGBoost were 82.10%, 0.607, 0.776, and 0.880 for single vehicle accidents and 79.52%, 0.569, 0.752, and 0.86 for multiple-vehicle accidents, respectively.

The traditional method to obtain optimum bitumen content and the relevant parameters of asphalt pavements entails time-consuming, complicated and expensive laboratory procedures and requires skilled personnel. This research study uses innovative and advanced machine learning techniques, i.e., Multi-Expression Programming (MEP), to develop empirical predictive models for the Marshall parameters, i.e., Marshall Stability (MS) and Marshall Flow (MF) for Asphalt Base Course (ABC) and Asphalt Wearing Course (AWC) of flexible pavements. A comprehensive, reliable and wide range of datasets from various road projects in Pakistan were produced. The collected datasets contain 253 and 343 results for ABC and AWC, respectively. Eight input parameters were considered for modeling MS and MF. The overall performance of the developed models was assessed using various statistical measures in conjunction with external validation. The relationship between input and output parameters was determined by performing parametric analysis, and the results of trends were found to be consistent with earlier research findings stating that the developed predicted models are well trained. The results revealed that developed models are superior and efficient in terms of prediction and generalization capability for output parameters, as evident by the correlation coefficient (R) (in this case >0.90) for both ABC and AWC.

This study evaluates the performance of Polyethylene Terephthalate (PET)-modified hot mix asphalt. Aggregate, bitumen of grade 60/70 and crushed plastic bottle waste were utilized in this study. Polymer Modified Bitumen (PMB) was prepared using a high shear laboratory type mixer rotating at a speed of 1100 rpm with varying PET content of 2%, 4%, 6%, 8% and 10%, respectively. Overall, the results of preliminary tests suggested that bitumen hardened with the addition of PET. Following optimum bitumen content determination, various modified and controlled HMA samples were prepared as per wet and dry mixing techniques. This research presents an innovative technique to compare the performance of HMA prepared via dry and wet mixing techniques. Performance evaluation tests, which include the Moisture Susceptibility Test (ALDOT-361-88), Indirect Tensile Fatigue Test (ITFT-EN12697-24) and Marshall Stability and Flow Tests (AASHTO T245-90), were conducted on controlled and modified HMA samples. The dry mixing technique yielded better results in terms of resistance against fatigue cracking, stability and flow; however, the wet mixing technique yielded better results in terms of resistance against moisture damage. The addition of PET at more than 4% resulted in a decreased trend for fatigue, stability and flow due to the stiffer nature of PET. However, for the moisture susceptibility test optimum PET content was noted to be 6%. Polyethylene Terephthalate-modified HMA is found to be the economical solution for high volume road construction and maintenance, besides having other significant advantages such as increased sustainability and waste reduction.

Using Reclaimed Asphalt Pavement (RAP) not only reduces the cost of new asphalt mixtures but also conserve the natural resources. To incorporate RAP in asphalt mix design, it is vital to know the amount and quality of the residual binder. In this research both conventional and Superpave methods were used to determine the virgin and residual binder properties. The residual binders obtained from two RAP sources using solvent extraction and abson recovery methods were blended with a virgin binder in different proportions. Penetration, ductility, dynamic modulus, stiffness and viscosity of the different blends were compared. Penetration, viscosity and PG grading blending charts were developed based on the corresponding test data. It was concluded that the properties of the blends depend on the individual properties of the binders. The stiffness of the binder is increasing with increasing RAP binder. This research only address the binder related study so to quantify RAP in asphalt mix design the other factors like aggregate and volumetric properties need proper considerations