This study explores the trade-off between diagnostic performance and computational efficiency in deep learning modelsfor the classification of breast cancer in ultrasound images. To this end, we evaluate three contemporary CNN architectures EfficientNetB7,EfficientNetV2-Small, and RexNet-200 in a multiple comparative study with standardized performance and complexity metrics. Ourevaluations provide evidence that all three models achieved an identical high accuracy of 95.00%, but there were sizeable differences inthe computational resources required to achieve that accuracy. RexNet-200 demonstrated tremendous computational efficiency, achievingidentical performance with the least amount of resources (13.81M parameters; 3.05 GFLOPs) required compared to EfficientNetB7 whichis much more computationally intensive. An examination of the confusion matrix for the models enhances the models clinical validity, asthere are no malignant lesions misclassified as normal. Ultimately, our study clearly demonstrates that diagnostic accuracy is not a goodmetric for practical clinical deployment. RexNet-200, by representing high performance, with minimal resource utilization, is the mostpragmatic and clinically applicable model, creating the opportunity to develop scalable and accessible CAD systems in resource-limitedsettings.

This study examines the use of machine learning and artificial intelligence algorithms to predictindividuals’ annual incomes. In analyses conducted using the Python programming language, the bestperformance was achieved in models utilizing the "Synthetic Minority Over-sampling Technique (SMOTE)" forimbalanced data sets, with an accuracy of 87.45%, precision of 85.74%, recall of 89.31%, and an F1 score of87.30, using the "Light Gradient Boosting Machines" algorithm. Additionally, the impact of parameters andvariables on income prediction was examined using interpretable artificial intelligence algorithms. The resultsof the study emphasize the importance of employing effective methods and explaining machine learning modelpredictions, as well as addressing imbalanced data sets

Breast cancer is one of the most common malignancies among women globally, and it constitutes a significant publichealth problem in terms of morbidity and mortality. Since early-stage diagnosis significantly increases treatment success and survival rates,effective screening and diagnostic methods are of great importance. Various imaging modalities, such as mammography, ultrasonography(US), and magnetic resonance imaging, play a critical role in the detection of breast cancer. Ultrasound, in particular, is a valuable imagingmethod due to its non-ionizing nature, its accessibility, and its role as a complementary tool in dense breast tissue. In recent years,deep learning (DL) algorithms, particularly Convolutional Neural Networks (CNNs), have exhibited promising results in medical imageanalysis, especially in cancer detection. The aim of this research is to investigate and compare the four most common CNN architectures,ResNet50, DenseNet169, InceptionV3 and InceptionV4, for breast ultrasound images to classify breast cancer automatically. We haveutilized publicly available breast ultrasound image datasets for the models and reported results in metrics of accuracy, precision, sensitivity,and F1-score. The InceptionV3 architecture had the best performance across the models examined with metrics of accuracy: 96.67%,precision: 96.55%, sensitivity: 96.38%, and F1-score: 96.41%. It was also noticed that the DenseNet169 model performed similarly to theInceptionV3 model but had substantially fewer parameters. The results of this study suggest that the InceptionV3 DL architecture mayhave significant potential for accuracy in the classification of cancer from breast ultrasound images and can contribute to the developmentof computer aided diagnosis systems for the early detection of breast cancer.

As a strategic global crop, maize productivity is directly threatened by leaf diseases such as Southern Leaf Blight andGray Leaf Spot, making early and accurate detection crucial for food security. Artificial intelligence, particularly deep learning, provides apowerful solution for the automated classification of plant diseases from images. This study developed an intelligent system to address thischallenge, utilizing the publicly available PlantVillage dataset to evaluate five leading Convolutional Neural Network (CNN) architectures:DenseNet121, InceptionV3, MobileNetV2, ResNet-50, and VGG16. The models were optimized with established techniques, includingtransfer learning, data augmentation, and hyper-parameter tuning, while a Soft Voting Ensemble strategy was used to enhance combinedperformance. Evaluation across multiple metrics showed that InceptionV3 achieved the highest test accuracy at 94.47%. However,MobileNetV2 demonstrated the strongest performance across all metrics with a 95% cumulative accuracy and proved highly efficient,making it ideal for deployment on mobile devices. These findings confirm the significant potential of deep learning for building cost-effectiveand efficient diagnostic systems in agriculture, ultimately contributing to the reduction of crop losses and the promotion of sustainablefarming practices.