为心电图时间序列建立全面评估基准，解决传统方法的不足。
A Comprehensive Benchmark for Electrocardiogram Time-Series
- 将心电图下游任务分为四类，构建系统化评估框架
- 提出新指标，显著优于传统度量在心电分析中的表现
- 设计新模型架构，提升心电图信号处理能力，适合临床研究者
心电图（ECG）是一种关键的生物电信号时间序列，对评估心脏健康和诊断多种疾病至关重要。由于其时间序列特性，ECG 数据常被用于大规模时间序列模型的预训练。然而，现有研究往往忽视其独特属性和专用下游应用，这些与一般时间序列数据差异显著，导致对其特性的理解不完整。本文对 ECG 信号进行了深入研究，并建立了综合性基准，包括：(1) 将其下游应用划分为四类评估任务；(2) 识别传统评估指标在心电分析中的局限性，并引入一种新型指标；(3) 对当前先进时间序列模型进行基准测试，并提出一种新架构。大量实验表明，所提出的基准具有全面性和鲁棒性。结果验证了新指标与模型架构的有效性，为推进心电图信号分析研究奠定了坚实基础。
原文摘要 · Abstract (English)
Electrocardiogram~(ECG), a key bioelectrical time-series signal, is crucial for assessing cardiac health and diagnosing various diseases. Given its time-series format, ECG data is often incorporated into pre-training datasets for large-scale time-series model training. However, existing studies often overlook its unique characteristics and specialized downstream applications, which differ significantly from other time-series data, leading to an incomplete understanding of its properties. In this paper, we present an in-depth investigation of ECG signals and establish a comprehensive benchmark, which includes (1) categorizing its downstream applications into four distinct evaluation tasks, (2) identifying limitations in traditional evaluation metrics for ECG analysis, and introducing a novel metric; (3) benchmarking state-of-the-art time-series models and proposing a new architecture. Extensive experiments demonstrate that our proposed benchmark is comprehensive and robust. The results validate the effectiveness of the proposed metric and model architecture, which establish a solid foundation for advancing research in ECG signal analysis.
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。