Intelligent Edge Device for Real Time Cardiac Arrhythmia Detection

Cardiac arrhythmias are irregular heart rhythms that may appear suddenly and remain undetected without continuous monitoring. Conventional monitoring approaches often depend on cloud-based analysis, leading to increased latency, higher power consumption, and concerns regarding data privacy. This work presents a compact intelligent edge device capable of performing real-time arrhythmia detection directly on embedded hardware. The proposed system combines a MAX30003 ECG analog front-end for accurate biopotential acquisition with an ESP32-S3 microcontroller for on device signal processing and classification. Acquired ECG signals undergo filtering, segmentation, and normalization before being analyzed using a lightweight convolutional neural network optimized for resource-constrained environments. The model identifies five classes of arrhythmia defined by AAMI standards (N, S, V, F, Q) without requiring continuous internet connectivity. A local OLED interface provides instant visual alerts, while optional wireless communication enables data transfer when needed. The implementation demonstrates that reliable cardiac monitoring and classification can be achieved using a portable, low-power architecture, making it suitable for wearable and remote healthcare applications where real-time response, energy efficiency, and data security are critical.