基于MIT-BIH数据构建高质量心拍数据集，提升分类准确率与效率
High quality ECG dataset based on MIT-BIH recordings for improved heartbeats classification
- 通过10秒窗口均值法确定最优心拍长度，去除异常值并避免心跳重叠
- 使用1D ResNet模型达99.24%准确率，较现有方法提升5.7%
- 下采样后推理时间减少33%，内存占用降低至1/3，适合实际部署
心电图（ECG）是医疗专业人员检测和诊断可能引发心血管疾病的异常心波的可靠工具。本文提出一种新方法，从全部48个MIT-BIH记录中构建高质量心拍数据集。该方法通过剔除异常值并在10秒窗口内计算均值，确定最优心拍尺寸，从而生成以QRS波为中心的独立心拍，有效避免连续心拍混叠问题。新数据集的质量经评估并与现有数据集对比。为此，我们构建并训练了一个PyTorch 1-D ResNet模型，在测试中达到99.24%的准确率，相比其他方法提升5.7%。此外，对数据集进行下采样后，模型执行时间减少33%，内存占用降低至原来的1/3。
原文摘要 · Abstract (English)
Electrocardiogram (ECG) is a reliable tool for medical professionals to detect and diagnose abnormal heart waves that may cause cardiovascular diseases. This paper proposes a methodology to create a new high-quality heartbeat dataset from all 48 of the MIT-BIH recordings. The proposed approach computes an optimal heartbeat size, by eliminating outliers and calculating the mean value over 10-second windows. This results in independent QRS-centered heartbeats avoiding the mixing of successive heartbeats problem. The quality of the newly constructed dataset has been evaluated and compared with existing datasets. To this end, we built and trained a PyTorch 1-D Resnet architecture model that achieved 99.24\% accuracy with a 5.7\% improvement compared to other methods. Additionally, downsampling the dataset has improved the model's execution time by 33\% and reduced 3x memory usage.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。