Effective water management is crucial in urban and rural settings, requiring efficient usage and timely detection of issues like leakages for sustainability. This paper introduces an integrated framework that combines Digital Twin technology with a multimodal transformer-based model for accurate water usage prediction and leakage detection. The system synchronizes real-time data from various sensors including flow meters, pressure sensors, and thermal imaging devices with a Digital Twin of the water network. Advanced transformer models, specifically the Informer model for long-term time-series prediction and a Water Multimodal Transformer for anomaly detection, process these data to capture complex patterns and dependencies. Experimental results demonstrate the framework’s effectiveness: the Informer model achieved an R² score of 0.9995 and a Mean Squared Error (MSE) of 2.2, outperforming traditional models. For leakage detection, the model attained 98.4% accuracy and precision, an F1 score of 97.6%, a low False Positive Rate of 0.0019, and an Area Under the Curve (AUC) of 0.984. By fusing diverse sensor data and utilizing advanced transformer architectures, the framework provides a comprehensive view of the water network, enabling real-time decision-making, enhancing forecasting accuracy, and reducing water waste. This scalable solution supports sustainable water management practices in both urban and industrial contexts.

This study presents an Auto-Encoder Convolutional Neural Network (AECNNs) approach for anomaly detection in high-dimensional datasets. Unsupervised learning-based algorithms have a strong theoretical foundation and are widely used for anomaly detection in high-dimensional datasets, but some limitations significantly reduce their performance. This study proposes an algorithm to address these limitations. The proposed AECNN combines various convolutional layers, feature extraction, dimensionality reduction, and data preprocessing and was evaluated using accuracy, precision, recall, and F1-score. The performance of the proposed model was evaluated using a large real benchmark dataset. The proposed CNN-based autoencoder distinguished anomalies with an AUC score of 0.83 and remarkable accuracy, precision, recall, and F1 score.

This study focuses on Diabetic Retinopathy (DR), a disease caused by diabetes that affects the retina of the eye and eventually leads to blindness. Diabetes development progresses to retinopathy and must be addressed at an early stage for effective treatment. Currently, DR is classified as Non-Proliferative DR (NPDR) and Proliferative DR (PDR). This study proposes an Enhanced DR (P-EDR) method based on CNN using a high-resolution dataset benchmark of retinal images. Initially, the data were preprocessed by normalization, augmentation, and resizing to improve image quality and feature extraction. Evaluation was based on accuracy, specificity, sensitivity, and AUC-ROC. The proposed CNN-based P-EDR outperformed advanced ML strategies such as Support Vector Machine (SVM), Random Forest (RF), Probabilistic Neural network (PNN), and Gradient Boosting Machine (GBM) that were executed and compared to diagnose and classify DR. The proposed P-EDR extracts features such as a hemorrhage of the NPDR retina image to identify the disease using image processing for classification. P-EDR provides significant features from images in detection and classification, making it a successful model for diagnosing DR with improved accuracy of 93%, sensitivity of 92%, specificity of 94%, and AUC-ROC of 0.97%. These results highlight the potential of a P-EDR-based machine learning model to support ophthalmologists with the early and precise detection of DR, eventually helping with appropriate treatment and prevention of vision loss.

High dropout rates in short-term job skills training programs hinder workforce development. This study applies machine learning to predict program completion while addressing class imbalance challenges. A dataset of 6548 records with 24 demographic, educational, program-specific, and employment-related features was analyzed. Data preprocessing involved cleaning, encoding categorical variables, and balancing the dataset using the Synthetic Minority Oversampling Technique (SMOTE), as only 15.9% of participants were dropouts. six machine learning models—Logistic Regression, Random Forest, Support Vector Machine, K-Nearest Neighbors, Naïve Bayes, and XGBoost—were evaluated on both balanced and unbalanced datasets using an 80-20 train-test split. Performance was assessed using Accuracy, Precision, Recall, F1-score, and ROC-AUC. XGBoost achieved the highest performance on the balanced dataset, with an F1-score of 0.9200 and a ROC-AUC of 0.9684, followed by Random Forest. These findings highlight the potential of machine learning for early identification of dropout trainees, aiding in retention strategies for workforce training. The results support the integration of predictive analytics to optimize intervention efforts in short-term training programs.