In real-world clinical settings, the growing number of patients and the shortage of experienced ophthalmologists make early and accurate diagnosis of retinal diseases increasingly challenging. Cataracts, diabetic retinopathy, and glaucoma are some of the most common causes of lifelong blindness around the world. This is why there is a need for automated diagnostic systems that can accurately diagnose and interpret clinical data. The major goal of this work is to find out if a deep learning architecture based on EfficientNetB3 and Explainable Artificial Intelligence (XAI) can accurately classify multiple types of retinal diseases while still being clear to doctors. The proposed system categorizes retinal fundus images into four groups: cataract, diabetic retinopathy, glaucoma, and normal. The dataset consisted of a balanced and publicly accessible collection of 4,217 retinal fundus pictures, processed using standard preprocessing techniques to enhance their generalizability. We chose EfficientNetB3 as the main architecture since it is better at extracting features, and we compared it to the standard convolutional neural network baselines to show how useful it is. The suggested model was 97% accurate in classifying better than Residual Network 50 (ResNet50) is 91% and Visual Geometry Group 16 (VGG 16) is 87%. The high precision, recall, and F1-scores (0.94 – 1.00), the Cohen’s kappa of 0.95, and the low logarithmic loss of 0.10 all point to reliable predictions. The receiver operating characteristic analysis yielded an AUC of 1.00 across all illness categories. Gradient-weighted Class Activation Mapping (Grad-CAM) was utilized to address the interpretability deficit in deep learning-based medical systems and to pinpoint clinically significant retinal regions that influence model predictions. The results indicate that employing XAI alongside EfficientNetB3 enhances both diagnostic precision and interpretability, hence validating its suitability as a transparent decision-support system for the automated screening of retinal disorders. 

Optimizing energy management for household appliances is essential for maximizing domestic energy utilization and enabling preventive maintenance. Recent studies indicate that traditional forecasting approaches frequently lack the necessary accuracy and real-time learning capabilities required for effective management of household energy. This study demonstrates the implementation of a comprehensive strategy that integrates Internet of Things (IoT) data, machine learning (ML), and explainable artificial intelligence (XAI) to improve the accuracy and interpretability of predicting energy usage in residential buildings. Our research focuses on the rising issues faced by IoT-based smart systems, partic- ularly the deficiencies in the performance of current solutions. Therefore, as compared to the other 17 models that were examined, polynomial regression demonstrated outstanding performance. Our solution utilizes a non-intrusive sensor to collect data without disrupting its operation. Real-time data collecting is achieved through a Flask-based web page with Ngrok for external access.The efficacy of the proposed system was assessed using many metrics, yielding highly satisfac- tory results: the root mean square error (RMSE) was 0.03, the mean absolute error (MAE) was 0.02, the mean absolute percentage error (MAPE) was 0.04, and the coefficient of determination (R²) was 0.9989. However, modern cutting-edge methods still face considerable hurdles when it comes to interpretability. In order to tackle these problems, we include XAI techniques such as SHAP and LIME. Explainable Artificial Intelligence (XAI) improves the interpretability of the model by elucidating the impact of various variables on energy consumption forecasts. Not only does this increase the effectiveness of the model, but it also promotes comprehension of the data and enables them to identify the elements that influence home energy usage.