Real-time R-peak detection in wearable electrocardiography using a deep learning model

Official URL: https://dx.doi.org/10.1109/SIU66497.2025.11111997

Electrocardiography (ECG) is a crucial diagnostic measurement technique to map the electrical activity of the heart and provide essential insights on cardiac activity. This study presents a wearable ECG monitoring solution using graphene conductive textile electrodes integrated into a neckband for continuous ECG monitoring with real-time R-peak detection based on a long short-term memory (LSTM)-based deep-learning model. To enhance R-peak detection accuracy, raw ECG data from the MIT-BIH Arrhythmia Database were utilized. Following the training, the model was also tested on a 30-minute-long ECG data collected from the prototyped wearable neckband, with excellent R-peak detection accuracy of up to 97.2%.