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.

Supervised learning algorithms are a recent trend for the prediction of mechanical properties of concrete. This paper presents AdaBoost, random forest (RF), and decision tree (DT) models for predicting the compressive strength of concrete at high temperature, based on the experimental data of 207 tests. The cement content, water, fine and coarse aggregates, silica fume, nano silica, fly ash, super plasticizer, and temperature were used as inputs for the models’ development. The performance of the AdaBoost, RF, and DT models are assessed using statistical indices, including the coefficient of determination (R²), root mean squared error-observations standard deviation ratio (RSR), mean absolute percentage error, and relative root mean square error. The applications of the above-mentioned approach for predicting the compressive strength of concrete at high temperature are compared with each other, and also to the artificial neural network and adaptive neuro-fuzzy inference system models described in the literature, to demonstrate the suitability of using the supervised learning methods for modeling to predict the compressive strength at high temperature. The results indicated a strong correlation between experimental and predicted values, with R² above 0.9 and RSR lower than 0.5 during the learning and testing phases for the AdaBoost model. Moreover, the cement content in the mix was revealed as the most sensitive parameter by sensitivity analysis.

Urban population growth and urbanization with its impact on urban planning require continuous research in order to address the challenges posed by transportation requirements. Identifying transportation capacity (road and railways) is an important task that can identify whether the network is capable of sustaining the present volume of traffic and whether it can handle the future intended traffic flow. A new city, XiongAn, will be built in the coming years in order to relieve the pressure of population on Beijing and disperse the economic growth, business activity, and opportunities across the country. The focus of this research is to generate a transportation model between Beijing and XiongAn, in order to increase connection and connectivity, reduce travel time, and increase transfer capacity between the two hubs (Beijing-XiongAn). The existing transportation network between two cities is analyzed and a network which can handle future demand has been proposed. The first stage has been the investigation of a variety of options using geographic information system (GIS). Planning and implementing a mass transit system requires choosing among options such as an existing intercity railway line, a new high-speed railway line, and/or motorway options. In the second phase of our analysis, we assess these options relative to multiple criteria, using the analytic hierarchy process (AHP). The options were evaluated using various criteria responsible for selection of alternative; it is found that travel time, cost of travel, safety, reliability, accessibility, and environment are key criteria for selecting the best alternative. The GIS and multicriteria analysis suggested that the best option is to build a new high speed railway line.

Individual effect of aging and rejuvenator recycling on basic properties of asphalt is readily recognized, but there is only limited understanding about whether the recycling of SBS‐ (styrene‐butadiene‐styrene‐) modified asphalt is an inverse process of aging or not. To compare the effects of aging and rejuvenator on microproperties and molecular composition of SBS‐modified asphalt, comprehensive performance tests and physical‐chemistry experiments were conducted. The results of infrared spectroscopy tests demonstrate that the reticular crosslinking structure of asphalt was destroyed and SBS’s modification effect was gradually lost after aging. This can cause the strengthening of high‐temperature performance and reduction of the low‐temperature anticrack property of SBS‐modified asphalt. Scanning electron microscope shows that the island structure of SBS‐modified asphalt disappeared after aging. Energy spectrum analysis shows that the C (carbon) content of aged SBS‐modified asphalt has decreased, while the O (oxygen) content and S (sulfur) content have increased obviously. Results of the fluorescence microscope, SEM, and rheological tests show that the epoxy functional group compounds of aliphatic glycidyl ether resin had high reactivity; the triblock molecular structure of SBS and the mechanical performance of SBS‐modified asphalt were recovered.

Beijing has an enormous transportation challenge: to relieve the extreme congestion that has arisen, largely due to overpopulation. To meet this challenge, the city administration has decided to extend its territory; a new city will be planned and built. This new city, Xiongan, will reduce the burden on the capital. A new high‐speed railway (HSR) line is designed to transport millions of people every day within less than an hour. This study applies the potential of Geographical Information Systems (GIS) and multicriteria methods, Analytic Hierarchy Process (AHP) and Preference Ranking Organization Method for Enrichment Evaluations (PROMETHEE II), to determine the best alternative of transportation for the new high‐speed railway line between Beijing and Xiongan, comparing different ones. The methodology consists of two stages. In the first stage remote sensing datasets such as ASTER DEM and LANDSAT images and GIS software such as ERDAS IMAGINE and ArcGIS have been used to determine settlement distribution, station location, elevation model, slope percentage, vegetation percentage, and route alignment for a new high‐speed railway line for better understanding of its spatial distribution pattern over the study area. The second phase of the study focusing on assessing the various alternatives of transportation has been determined, and three approaches to choosing the best alternative have been introduced. In the paper we examine criteria associated with travel and economic criteria: travel time, the number of train stops, public satisfaction with transport, the number of seats per day, connectivity, operating costs, profit, and the payback period. Six alternatives of transportation have been studied. The stops in Guan and stations in the metro’s rings have been investigated. In the second stage, the Analytic Hierarchy Process (AHP) and PROMETHEE II methods have been used to select the best alternative. The first approach uses only criteria related to the trip, as the criterion to choose the best alternative is the maximum of the net outranking flows by PROMETHEE II method; the second approach applies two independent criteria: the ratio of normalized operating costs and the normalized net outranking flows, and the ratio of the normalized payback period and the normalized net outranking flows; the third approach includes all defined criteria, and the criterion of choosing the best alternative is the maximum of net outranking flows as calculated by the PROMETHEE II method. The approaches have been analyzed with the purpose of comparing the results. The result indicates that it is expedient to have a station in Guan, which will increase the connection and connectivity among the cities while providing fast mobility options for a large number of inhabitants of Guan city. Furthermore, the result from Remote Sensing and GIS analysis demonstrates that the proposed high‐speed railway line will be environmentally sustainable and is economically/socially feasible and that it will certainly attract current and future passengers because of their needs.

Expansive soils are found in numerous regions of the world explicitly in arid and semiarid zones. These soils expand when absorbed moisture and shrink when released water. Such soil is viewed as a characteristic risk for infrastructures due to the shrink and swell behavior. These soils become more problematic when lightly or moderately loaded structures are built on them. The swelling and shrinkage in these soils chiefly happen due to the presence of montmorillonite minerals. The mineralogical and swell behavior of foundation soils is playing a vital role in the overall stability of a structure. These parameters are often ignored in the geotechnical report writing stage specifically in small projects, due to which, the durability and service life of the facilities are reduced and the maintenance cost is increased. To mitigate the potential damages in structures constructed on expansive soil, it is necessary to assess the mineralogical and swelling characteristics of expansive soil. The current study aims to determine the geotechnical, mineralogical, and swell behavior of the local expansive soils. Based on the results, the Karak soil has the highest plasticity index (PI) of 37% with a clay fraction of 28%, while the D.I. Khan soil has the least PI of 23% with a clay fraction of 17%. Similarly, Karak’s soil contained a higher percentage of montmorillonite (Rp = 8.9%). The maximum values of swell pressure, swell potential, and 1D deformation are 280 kPa, 12.5%, and 1.92 mm for the Karak soil, 6.45% 150 kPa, and 1.38 mm for D.I. Khan soil, and 10.5%, 245 kPa, and 1.64 mm for Kohat soil, respectively. This concludes that Karak’s soil has high plasticity and swell characteristics than Kohat and D.I. Khan soil. The swell characteristic of expansive soils increases with the increase in the percentage of the fine specifically the clay fraction. Furthermore, the Karak soil is more critical than Kohat and D.I. khan soil for lightly loaded structures.