The viral disease COVID-19, declared a pandemic by the World Health Organization (WHO), primarily affects the respiratory system and can be fatal. Although the Reverse Transcriptase Polymerase Chain Reaction (RT-PCR) test remains the gold standard for COVID-19 diagnosis, its time-intensive nature limits its effectiveness in urgent situations. To address this, we propose an ensemble of five state-of-the-art transfer learning (TL) models designed to mitigate biases and enhance the classification of COVID-19 from chest radiographs. A weighted optimization strategy combines the models, giving more weight to those with superior performance, ensuring more accurate and robust predictions. Evaluated on a publicly available dataset, the SqueezeNet model achieved the highest accuracy of 94.01% for three-class classification (Normal, COVID-19, Lung Opacity), while the ensemble approach achieved 92.57% accuracy and an F1-score of 92.36%, demonstrating resilience to transfer learning biases. This framework offers reliable diagnostic support, streamlining radiology workflows and enhancing decision-making in high-demand clinical environments. Additionally, it serves as a valuable tool for advancing medical artificial intelligence expertise among graduates.

Airfoils are the key component of aircraft that are used to generate lift force to support its weight. Optimization of airfoils can significantly enhance their aerodynamic efficiency. The present study introduces a novel method of airfoil optimization that integrates Genet-ic Algorithms (GA) with Deep Learning (DL). The dataset was generated using XFOIL by varying angle of attack and Reynold’s number for various airfoil geometries. The geometry of airfoils was represented by Bezier Curve parametrization in the dataset. The generated dataset was used to train a Dual Branch Fully Connected Hybrid Activated Deep Network (DBFC-HA DN) model. The novel approach involves the integration of the trained model with the Genetic Algorithm (GA) to find the optimized solution (geometry) of the airfoil bounded within a pre-defined angle of attack range that is based on a reference airfoil. CFD analyses have been performed to verify the results of the proposed model. For NACA 65(2)-415, a 24.45% increase in lift-to-drag ratio was identified using CFD analysis at 0º angle of attack. The results were also validated using wind tunnel testing. The approach presented in the study saves computational cost and time for the optimisation of airfoils as compared to CFD and provides a basis for its use in the optimisation of airfoil performance for the relevant aerospace engineering applications.