Preprocessed CPSC Data

<pre><pre>This dataset is a preprocessed version of the CPSC 2018 dataset, which contains 6877 ECG recordings.<br>We preprocessed the dataset by resampling the ECG signals to 250 Hz and equalizing the ECG signal length to 60 seconds, <br>yielding a signal length of T=15,000 data points per recording. <br>For the hyperparameter study, we employed a fixed train-valid-test split with ratio 60-20-20,<br>while for the final evaluations, including the comparison with the state-of-the-art methods and ablation studies, <br>we used a 10-fold cross-validation strategy.<br><br>The raw CPSC 2018 dataset can be downloaded from the website of the <br>PhysioNet/Computing in Cardiology Challenge 2020 (License: Creative Commons Attribution 4.0 International Public License).</pre></pre>

本数据集为CPSC 2018数据集的预处理版本，共包含6877条心电图（Electrocardiogram, ECG）记录。我们通过将心电图信号重采样至250Hz，并统一所有记录的信号时长为60秒完成预处理流程，最终每条记录的信号长度为T=15000个数据点。在超参数研究阶段，我们采用固定的训练集-验证集-测试集划分比例60-20-20；而在最终评估阶段（包括与当前最优方法的对比实验及消融实验），我们采用10折交叉验证策略。

原始CPSC 2018数据集可从PhysioNet/Computing in Cardiology Challenge 2020官网下载，其授权协议为Creative Commons Attribution 4.0 International Public License。