Background: Psoriasis is a chronic, immune-mediated skin disease characterized by lifelong persistence and fluctuating symptoms. The clinical similarities among its subtypes and the diversity of symptoms present challenges in diagnosis. Early diagnosis plays a vital role in preventing the spread of lesions and improving patients’ quality of life. Methods: This study proposes a hybrid model combining multiple transfer learning and ensemble learning methods to classify psoriasis subtypes accurately and efficiently. The dataset includes 930 images labeled by expert dermatologists from the Dermatology Clinic of Fırat University Hospital, representing four distinct subtypes: generalized, guttate, plaque, and pustular. Class imbalance was addressed by applying synthetic data augmentation techniques, particularly for the rare subtype. To reduce the influence of nonlesion environmental factors, the images underwent systematic cropping and preprocessing steps, such as Gaussian blur, thresholding, morphological operations, and contour detection. DenseNet-121, EfficientNet-B0, and ResNet-50 transfer learning models were utilized to extract feature vectors, which were then combined to form a unified feature set representing the strengths of each model. The feature set was divided into 80% training and 20% testing subsets and evaluated using a hard voting classifier consisting of logistic regression, random forest, support vector classifier, k-nearest neighbors, and gradient boosting algorithms. Results: The proposed hybrid approach achieved 93.14% accuracy, 96.75% precision, and an F1 score of 91.44%, demonstrating superior performance compared to individual transfer learning models. Conclusions: This method offers significant potential to enhance the classification of psoriasis subtypes in clinical and real-world settings.

Student dropout poses a significant challenge to both individual and societal progress. While artificial intelligence is widely used to identify potential dropouts and analyze their causes, its success relies heavily on well-structured datasets. Imbalanced datasets may limit models from achieving good generalization by adapting to the majority class. This study examines the impact of dataset balancing techniques on dropout prediction using artificial intelligence models and interprets model decisions through explainable artificial intelligence, based on the publicly available Predict Students’ Dropout and Academic Success datasets. Accordingly, four different datasets were created using the SMOTE, SMOTE-ENN, and SMOTE-Tomek balancing techniques and were trained with machine learning models. The SMOTE-ENN + CATBoost combination, which achieved 98% accuracy, precision, recall, F1 score, and an AUC score of 1.00, was selected as the best-performing combination and was subjected to LIME and SHAP analyses for model interpretability. The analyses showed that low academic performance increases the risk of dropping out; in addition, support mechanisms such as scholarships encourage students to complete their education. Compared to similar studies, the findings address both class balancing techniques and model explainability within a broader scope and examine the underlying causes of student dropout through explainable artificial intelligence.

Normalization is utilized to remove outliers from the dataset and address network bias. In this research, Mean-Variance-Softmax-Rescale (MVSR) and Min-Max normalizations are employed in various combinations for the diagnosis of COVID-19 using a Convolutional Neural Network (CNN)-based Deep Learning (DL) model, aimed at enhancing network accuracy. To accomplish this, the CNN model is developed within the Google Colab environment and trained using a publicly available dataset consisting of chest X-ray images related to COVID-19. The dataset is normalized using different combinations of the MVSR and Min-Max normalization algorithms to compare model accuracy. Each normalized dataset is used for model training, and subsequently, each trained model is integrated into the Kria KV260 Vision AI Starter Kit FPGA for the testing phase. The most accurate results are obtained when both MVSR and Min-Max normalizations are applied simultaneously. This high-performing scenario is re-evaluated with real-time camera and FPGA configuration. During real-time implementations, Min-Max normalization is performed within the Colab environment, while the MVSR normalization algorithm is executed using the Kria KV260 Vision AI Starter FPGA Kit. Experimentally, the highest accuracy is achieved in real-time with the MVSR+Min-Max scenario, reaching 93%. The model's precision, recall, and F1-Score values are determined as 0.91, 0.96, and 0.93, respectively.