Deep learning-based atrial fibrillation determination system using PPG signal sensing ring

Provided is an atrial fibrillation determination system based on deep learning, which uses a photoplethysmography (PPG) signal to sense a ring, and a method for determining atrial fibrillation based on deep learning. The system includes a sensor including a signal quality classification component configured to classify a quality of a PPG signal as good or bad using a first deep learning model, and an atrial fibrillation determination component configured to determine whether the quality of the PPG signal is poor or good using a second deep learning model. And an atrial fibrillation determination section configured to determine whether or not atrial fibrillation occurs from the PPG signal using a second deep learning model, the PPG signal sensing ring including a plurality of sensors configured to simultaneously measure a plurality of PPG signals at different positions, respectively, each of the plurality of sensors includes a light source and a photoelectric conversion device, the PPG signal is measured using