Road traffic accidents are among the top ten major causes of fatalities in the world, taking millions of lives annually. Machine-learning ensemble classifiers have been frequently used for the prediction of traffic injury severity. However, their inability to comprehend complex models due to their “black box” nature may lead to unrealistic traffic safety judgments. First, in this research, we propose three state-of-the-art Dynamic Ensemble Learning (DES) algorithms including Meta-Learning for Dynamic Ensemble Selection (META-DES), K-Nearest Oracle Elimination (KNORAE), and Dynamic Ensemble Selection Performance (DES-P), with Random Forest (RF), Adaptive Boosting (AdaBoost), Classification and Regression Tree (CART), and Binary Logistic Regression (BLR) as the base learners. The DES algorithm automatically chooses the subset of classifiers most likely to perform well for each new test instance to be classified when generating a prediction, making it more efficient and flexible. The META-DES model using RF as the base learner outperforms other models with accuracy (75%), recall (69%), precision (71%), and F1-score (72%). Afterwards, the risk factors are analyzed with SHapley Additive exPlanations (SHAP). The driver’s age, month of the year, day of the week, and vehicle type influence SHAP estimation the most. Young drivers are at a heightened risk of fatal accidents. Weekends and summer months see the most fatal injuries. The proposed novel META-DES-RF algorithm with SHAP for predicting injury severity may be of interest to traffic safety researchers.

The growth of the construction industry has led to the greater consumption of natural resources, which has a direct or indirect negative impact on the environment. To mitigate this, recycled or waste materials are being used as a partial substitute in the manufacture of concrete. Among these waste materials is cement kiln dust (CKD), which is produced during cement production. This study investigated the potential benefits of replacing part of the cement with CKD in two construction applications, i.e., plain concrete and cement blocks. This reflects positively on cost, energy, and the environment, since putting CKD in a landfill damages agricultural soil and plant respiration. In this study, an experimental program was carried out to study how replacing various percentages of ordinary portland cement (OPC) with CKD affected the compressive strengths, the tensile strengths, and the air contents of concrete and cement blocks. Although the results showed that the compressive and tensile strengths decreased as the amount of CKD increased, the air content of the concrete increased, which showed that 5% CKD was suitable for such applications. The results were used to propose two equations that approximate the concrete and cement block compressive strengths according to the CKD replacement percentage.

In this paper, the recycled fine aggregates and powders produced from crushing old basaltic concrete and natural basalt were used to produce new concrete. The sand was partially replaced by two types of recycled wastes at five percentages: 0%, 20%, 40%, 60%, and 80%. The cement was partially replaced by recycled powders and silica fume (SF) at four percentages: 0, 5%, 10%, and 20%. The concrete strengths and water absorption were obtained at several curing ages. The obtained results emphasized the positive effects of increasing the curing time on enhancing the concrete properties, regardless of the types or the waste sources. Moreover, the recycled powders retarded the hydration reaction. In addition, the recycled fine aggregates and powders could achieve about 99.5% and 99.3% of the ordinary concrete strength and enhance the tensile strength. Furthermore, the mix containing 40% of recycled fine concrete aggregate diffused the highest contents of both calcium and silicate, which led to enhancing the interfacial transition zone (ITZ) and concrete properties, compared to the other tested mixes. Finally, the water absorption of all tested concrete mixes decreased with an increase in the curing age, while the mixes integrating 10% and 20% of SF experienced the lowest values of water absorption.

The use of corrugated webs increases web shear stability and eliminates the need for transverse stiffeners in steel beams. Optimised regression learner techniques (ORLTs) are rarely used for calculating shear capacity in steel beam research. This study proposes a new approach for calculating the maximum shear capacity of steel beams with trapezoidal corrugated webs (SBCWs) by using ORLTs. A new shear model is proposed using ORLTs in accordance with plate buckling theory and previously developed formulas for predicting the shear strength of SBCWs. The proposed ORLT models are implemented using the regression learner toolbox of MATLAB software (2020b). The available data of more than 125 test results from different specimens prepared by previous researchers are used to create the model. In this study, web geometry and relevant web steel grades determine the shear capacity of SBCWs. Four regression methods are adopted. Results are compared with those of an artificial neural network model. The model output factor represents the ratio of the web vertical shear stress to the normalised shear stress. Shear capacity can be estimated on the basis of the resulting factor from the model. The proposed model is verified using two methods. In the first method, a series of tests are performed by the authors. In the second method, the results of the model are compared with the shear values obtained experimentally by other researchers. On the basis of the test results of previous studies and the current work, the proposed model provides an acceptable degree of accuracy for predicting the shear capacity of SBCWs. The results obtained using Gaussian process regression are the most appropriate because its recoded mean square error is 0.07%. The proposed model can predict the shear capacity of SBCWs with an acceptable percentage of error. The recoded percentage of error is less than 5% for 93% of the total specimens. By contrast, the maximum differential obtained is ±10%, which is recorded for 3 out of 125 specimens.

Literature of Steel Beams with a thin-walled trapezoidal Corrugated Web (SBCWs) shows that the capacity of SBCWs is affected by both the fatigue cracks initiated along the inclined folds (IFs) and the maximal additional stress located in the middle of the IFs. An experimental investigation on the behaviour of hybrid SBCWs under flexure is presented in this paper. This study focuses on the effect of the welding IF between the web and flanges (IFs welded or non-welded), the horizontal-fold length (200, 260, and 350 mm), and transversal flange stiffeners on the failure mechanism of the SBCW under three line load. Accordingly, six hybrid specimens were fabricated, instrumented, and tested (five SBCW specimens and one specimen with a flat web). The test setup was designed to generate shear and a moment in the testing zone via three-point bending. The results indicated that non-welded IFs specimens with or without flange stiffeners failed owing to web tearing after web and flange local buckling. The failure mode of the specimen with continuous welding between the web and flanges was local flange buckling. Finally, the paper presents a comparison between the experimental results and the European Code to predict the capacity of the flange towards local buckling. It was concluded that the non-welding the IFs affected the inelastic behaviour and the capacity of the SBCWs. In addition, the bending resistance equations presented by EN 1993-1-5 can safely predict the test results of the non-welded inclined fold and yield a high safe variation.

The huge amounts of old and damaged tires spread worldwide has caused many complex environmental risks. The old tires have been converted to crumb rubber (CR) and tire recycled steel fiber (RSF) to facilitate their use. This study used CR to partially replace natural sand in reinforced (RC) columns. Externally bonded (EB) carbon-fiber-reinforced polymer (CFRP) laminates, welded wire mesh (WWM), and RSF were used to enhance the axial behavior of the tested columns to overcome the concrete deficiencies resulting from the inclusion of the CR instead of natural sand. Eighteen columns were prepared and tested to discuss the effects of strengthening type, CR content, RSF, and strengthening area on the axial behavior of the RC columns. Certain columns were internally reinforced with WWM, while others were externally strengthened with EB CFRP laminates. Partially or fully EB CFRP laminates were used to strengthen the columns. Moreover, one column was cast with NC and 0.2% RSF to investigate the role of RSF in confining the column. The results demonstrated a concrete strength reduction for the rubberized concrete (CRC) as the CR content increased. Conversely, the strengthened columns experienced higher load capacities than the corresponding un-strengthened ones cast with the same concrete mix. Moreover, adding 2% RSF to the NC mix could enhance the column capacity, although it decreased the concrete strength. Furthermore, using two CFRP layers increased the load capacity and ductility of the strengthened columns. The strengthened column cast with 50% CR showed the highest load efficiency (334.3% compared to the un-strengthened one).