Over the past three decades, more than 8000 pedestrians have been killed in Australia due to vehicular crashes. There is a general assumption that pedestrians are often the most vulnerable to crashes. Sustainable transportation goals are at odds with the high risk of pedestrian fatalities and injuries in car crashes. It is imperative that the reasons for pedestrian injuries be identified if we are to improve the safety of this group of road users who are particularly susceptible. These results were obtained mostly through the use of well-established statistical approaches. A lack of flexibility in managing outliers, incomplete, or inconsistent data, as well as rigid pre-assumptions, have been criticized in these models. This study employed three well-known machine learning models to predict road-crash-related pedestrian fatalities (RCPF). These models included support vector machines (SVM), ensemble decision trees (EDT), and k-nearest neighbors (KNN). These models were hybridized with a Bayesian optimization (BO) algorithm to find the optimum values of their hyperparameters, which are extremely important to accurately predict the RCPF. The findings of this study show that all the three models’ performance was improved using the BO. The KNN model had the highest improvement in accuracy (+11%) after the BO was applied to it. However, the ultimate accuracy of the SVM and EDT models was higher than that of the KNN model. This study establishes the framework for employing optimized machine learning techniques to reduce pedestrian fatalities in traffic accidents.

The lid-driven top wall’s influence combined with the side walls’ waviness map induce the mixed convection heat transfer, flow behavior, and entropy generation of a hybrid nanofluid (Fe₃O₄–MWCNT/water), a process analyzed through the present study. The working fluid occupies a permeable cubic chamber and is subjected to a magnetic field. The governing equations are solved by employing the GFEM method. The results show that the magnetic force significantly affects the working fluid’s thermal and flow behavior, where the magnetic force’s perpendicular direction remarkably improves the thermal distribution at Re = 500. Also, increasing Ha and decreasing Re drops both the irreversibility and the heat transfer rate. In addition, the highest undulation number on the wavy-sided walls gives the best heat transfer rate and the highest irreversibility.

This paper includes a numerical investigation of a hybrid fluid containing 4% of Al₂O₃-Cu nanoparticles in a lid-driven container. The upper wall of the container has a high temperature and is movable. The lower wall is cool and wavy. An obstacle is set in the middle of the container for its effect on thermal activity. The medium is permeable to the fluid, and the entire system is immersed in a fixed-effect magnetic field. The digital simulation is achieved using the technique of Galerkin finite element (GFEM) which solves the differential equations. This investigation aims to know the pattern of heat transfer between the lateral walls and the lower wall of the container through the intervention of a set of conditions and criteria, namely: the strength of the magnetic field changes in the range of (Ha = 0 to 100); the chamber porosity varies in the range of (Da = 10⁻⁵ to 10⁻²); the strength of buoyancy force is varied according to the Grashof number (Gr = 10² to 10⁴); the cross-section of the baffle includes the following shapes—elliptical, square, triangular and circular; the surface of the lower wall contains waves; and the number changes (N = 2 to 8). Through this research, it was concluded that the triangular shape of the baffle is the best in terms of thermal activity. Also, increasing the number of lower-wall waves reduces thermal activity. For example, the change in the shape of the obstacle from the elliptical to triangular raises the value of Nu number at a rate of 15.54% for Ha = 0, N = 8, and Gr = 10⁴.

Thermal energy storage via the use of latent heat and phase transition materials is a popular technology in energy storage systems. It is vital to research different thermal enhancement techniques to further improve phase transition materials’ weak thermal conductivity in these systems. This work addresses the creation of a basic shell and a tube thermal storage device with wavy outer walls. Then, two key methods for thermal augmentation are discussed: fins and the use of a nano-enhanced phase change material (NePCM). Using the enthalpy–porosity methodology, a numerical model is developed to highlight the viability of designing such a model utilizing reduced assumptions, both for engineering considerations and real-time predictive control methods. Different concentrations of copper nanoparticles (0, 2, and 4 vol%) and wavenumbers (4,6 and 8) are investigated in order to obtain the best heat transmission and acceleration of the melting process. The time required to reach total melting in the studied TES system is reduced by 14% and 31% in the examined TES system, respectively, when NePCM (4 vol% nanoparticles) and N = 8 are used instead of pure PCM and N = 4. The finding from this investigation could be used to design a shell-and-tube base thermal energy storage unit.