轻量级CNN实现神经信号实时分类，适合植入设备
Low-Complexity CNN-Based Classification of Electroneurographic Signals
- 设计轻量网络MobilESCAPE-Net，大幅降低计算开销
- 参数减少99.9%，每秒浮点运算降低92.47%，精度相当
- 适合嵌入式、低功耗神经接口实时处理
外周神经接口（PNIs）可用于神经信号记录与刺激，治疗神经损伤，但实时分类电神经图（ENG）信号仍面临复杂度与延迟的挑战，尤其在植入式设备中。本文提出MobilESCAPE-Net，一种轻量级架构，在保持并小幅提升分类性能的同时显著降低计算成本。相比现有最优的ESCAPE-Net，MobilESCAPE-Net在准确率和F1分数相当的情况下，训练参数减少99.9%，每秒浮点运算量降低92.47%，实现更快推理与实时处理。其高效性使其适用于资源受限环境下的低复杂度ENG信号分类，如植入式设备。
原文摘要 · Abstract (English)
Peripheral nerve interfaces (PNIs) facilitate neural recording and stimulation for treating nerve injuries, but real-time classification of electroneurographic (ENG) signals remains challenging due to constraints on complexity and latency, particularly in implantable devices. This study introduces MobilESCAPE-Net, a lightweight architecture that reduces computational cost while maintaining and slightly improving classification performance. Compared to the state-of-the-art ESCAPE-Net, MobilESCAPE-Net achieves comparable accuracy and F1-score with significantly lower complexity, reducing trainable parameters by 99.9\% and floating point operations per second by 92.47\%, enabling faster inference and real-time processing. Its efficiency makes it well-suited for low-complexity ENG signal classification in resource-constrained environments such as implantable devices.
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。