An Open-Access ECG Database for Algorithm Evaluation of QRS Detection and Heart Rate Estimation

R-peak detection for dynamic electrocardiogram (ECG) signal is still a challenge due to the poor signal quality, which leads to inefficient recognition of the existing R-peak detection technologies. Collected in clinical environment, ECG signals from current widely-used open-access ECG databases are basically provided with high quality. Many methods can achieve high recognition rate on these databases but fail to work properly if the signal quality reduces. This study presents an open-access ECG database comprises of challenging QRS segments. The database is used for the 2nd China Physiological Signal Challenge (CPSC 2019), where participants are expected to identify QRS locations and then estimate HR from these, episodes. All the approved algorithms are evaluated by scoring standards and regulations defined in terms of both R-peak detection and HR estimation, with Pan & Tompkin (P&T) algorithm as a benchmark.