ARCHIVES

Cardiovascular diseases require continuous and real-time monitoring to enable early detection and timely medical intervention. Traditional cardiac monitoring systems depend heavily on cloud-based processing, which introduces latency, increases privacy risks, and limits immediate emergency response. In addition, existing wearable and hospital-based solutions often lack accurate continuous monitoring and real-time intelligent decision-making. To address these challenges, this project proposes an edge computing enabled hardware architecture for intelligent cardiac risk detection. The system integrates wearable biomedical sensors such as ECG, heart rate, and SpO₂ with an embedded edge processing unit capable of local signal analysis and machine learning–based risk prediction. By processing physiological data at the edge,