Smart Prompting Device for Health and Monitoring System Using Cloud Integration

Early anomaly detection and patient monitoring are being transformed by intelligent systems in healthcare. Leveraging advanced machine learning, a Smart Prompting Device for Health and Monitoring System with Cloud Integration is proposed to enhance real-time health assessment. Traditional monitoring often struggles with complex temporal data and limited real-time analysis, causing delays inaccuracies. This system uses a robust preprocessing pipeline featuring the Gramian Angular Field (GAF) method to capture temporal patterns for deep learning. Recursive Feature Elimination identifies the most relevant health features, improving prediction accuracy while reducing computational cost. A hybrid deep learning model that combines Gated Recurrent Units and Convolutional Neural Networks achieves high classification accuracy of 97.8 %, precision of 96.9 %, recall of 97.2 %, and an F1-score of 97.0 % on real-world datasets. Its strong discriminative power is supported by an AUC of 0.985. Cloud integration ensures scalability, remote access, real-time processing, and timely health alerts for continuous patient care.