LSTrans通过轻量架构与知识蒸馏，实现可穿戴设备上高效精准的心电图分类。
LSTrans: Efficient Knowledge Transfer for Lightweight and Automated ECG Classification
- 采用1D卷积与Transformer级联结构，兼顾心电波形细节与长期时序依赖。
- 引入低秩适配与混合知识蒸馏，参数量减少且诊断敏感度保持领先。
- 适合资源受限的可穿戴医疗设备部署，训练快、内存占用低。
在资源受限的可穿戴设备上部署深度学习模型进行自动化心电图分类仍面临计算成本高的挑战。为此，我们提出LSTrans，一种轻量级混合模型，旨在实现高效且灵敏的心电图分析。LSTrans采用专用的一维卷积主干网络，结合交错层结构，以捕捉宏观节律趋势与微观形态变化；该主干网络与Transformer编码器级联，建模长程时间依赖关系，并在关键层引入低秩适配（Low-Rank Adaptation）以压缩模型并减少可训练参数空间。此外，我们还使用同质与异质知识蒸馏，将高容量教师模型的诊断专长传递给学生模型。在多个基准数据集上的实验表明，LSTrans在诊断敏感性与资源效率之间实现了良好平衡，显著降低了下游适应过程中的峰值内存占用与训练延迟。源代码已公开于https://github.com/zyee00128/LSTrans4BIBM。
原文摘要 · Abstract (English)
Deploying deep learning models for automated electrocardiogram classification on resource-constrained wearable devices remains challenging due to high computational costs. To address this, we propose LSTrans, a lightweight hybrid model designed for efficient and sensitive ECG analysis. LSTrans introduces a specialized 1D convolutional backbone with an interleaved layer architecture to capture both macroscopic rhythmic trends and microscopic morphological variations. This backbone is cascaded with a Transformer encoder to model long-range temporal dependencies, incorporating Low-Rank Adaptation across critical layers to compress the model and reduce the trainable parameter space. We further employ homogeneous and heterogeneous knowledge distillation to transfer diagnostic expertise from high-capacity teacher models to the student. Experimental results on multiple benchmark datasets demonstrate that LSTrans achieves a competitive balance between diagnostic sensitivity and resource efficiency, substantially reducing peak memory footprints and training latency during downstream adaptation. The source code is available for review at https://github.com/zyee00128/LSTrans4BIBM.
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。