In recent times, machine learning algorithms have gained significant traction in addressing aerodynamic challenges. These algorithms prove invaluable for predicting the aerodynamic performance, specifically the Lift-to-Drag ratio of airfoil datasets, when the dataset is sufficiently large and diverse. In this paper, we delve into an exploration of five machine learning algorithms: Random Forest, Gradient Boosting Regression, Decision Tree Regressor, AdaBoost Algorithm, and Linear Regression. These algorithms are scrutinized within the context of various train/test ratios to predict a crucial aerodynamic performance metric—the lift-to-drag ratio—for different angle of attack values. Our evaluation encompasses an array of metrics including R², Mean Square Error, Training time, and Evaluation time. Upon analysis, the Random Forest Method, with a train/test ratio of 0.2, emerges as the frontrunner, showcasing superior predictive performance when compared to its counterparts. Conversely, the Linear Regression algorithm distinguishes itself by excelling in training and evaluation times among the algorithms under scrutiny.

The rapid rise in global warming pushes the automobile industry towards adopting Electric vehicles globally. The battery is considered a core element of electric cars and must operate in extreme conditions. Therefore, a suitable heat recovery system must be implemented to make the battery reach its higher performance. This work explores and tests a hybrid-based Battery Thermal Management System under various operating conditions. To enhance the property of paraffin (Phase Change Material) in the passive method, Al₂O₃ nanoparticles have been added with paraffin in three different ratios of 5%, 10%, and 15%. In the case of the active method, the water is circulated in a counterflow direction through the copper coil. A detailed experimental investigation was carried out at free convection, pure paraffin, PCM with Al₂O₃ (5%, 10%, and 15%), and hybrid (both active and passive). Each investigation was carried out under different C rates (0.5 C, 1 C, 2 C, 3 C). The result shows that under natural convection for a 3 C discharge rate, the temperature rises to 51.16 °C, and it is reduced to 40.81 °C for hybrid conditions. Finally, after incorporating the hybrid-based thermal management system, a temperature reduction of around 10.35 °C is observed when compared with natural convection conditions. A detailed computational study was also carried out to validate the experimental results. The maximum temperature of 47 °C is obtained for a pure PCM battery module at a 3 C discharge rate, and it is well matched with experimental results.

Integrating Artificial Intelligence (AI) into Unmanned Aerial Vehicle (UAV) operations has advanced efficiency, safety, and decision-making. This study addresses critical gaps in UAV methods, including insufficient integration of human factors, operator variability, and the lack of systematic error analysis. To overcome these challenges, a novel approach combines the Analytic Hierarchy Process (AHP) with three core human factors models: the Observe-Orient-Decide-Act (OODA) loop, the Human Factors Analysis and Classification System (HFACS), and the SHELL model. An online survey was conducted across diverse UAV operator groups to prioritize critical factors within each model. Additionally, real-time monitoring of heart rate (HR), heart rate variability (HRV), and respiratory rate (RR) was conducted during UAV operations at various automation levels with different experience levels. Visualization through boxplots and percentage change matrices provided insights into operator stress and workload across automation levels. Integrating AHP findings and physiological data revealed significant differences in operator prioritization, highlighting the need for tailored AI-UAV strategies. This research combines survey data with real-time physiological monitoring, offering visions into optimizing human-AI interaction in UAV operations and providing a foundation for improving AI integration and operator strategies.

Particle image velocimetry has been widely used in various sectors from the automotive to aviation, research, and development, energy, medical, turbines, reactors, electronics, education, refrigeration for flow characterization and investigation. In this study, articles examined in open literature containing the particle image velocimetry techniques are reviewed in terms of components, lasers, cameras, lenses, tracers, computers, synchronizers, and seeders. The results of the evaluation are categorized and explained within the tables and figures. It is anticipated that this paper will be a starting point for researchers willing to study in this area and industrial companies willing to include PIV experimenting in their portfolios. In addition, the study shows in detail the advantages and disadvantages of past and current technologies, which technologies in existing PIV laboratories can be renewed, and which components are used in the PIV laboratories to be installed.