小模型实现多模态生理信号统一分析，边缘设备部署快且省电。
PanLUNA: An Efficient and Robust Query-Unified Multimodal Model for Edge Biosignal Intelligence
- 用统一查询机制融合脑电、心电、脉搏波信号，支持缺模运行。
- 5.4M参数模型在脑电异常检测上达81.21%准确率，睡眠分期超主流水平。
- 可量化到INT8，适合可穿戴设备实时处理，功耗低至18.8mJ/10秒。
生理基础模型（FMs）在生物信号表征学习中展现潜力，但多数局限于单一模态（如EEG、ECG或PPG），主要因配对多模态数据稀缺。本文提出PanLUNA，一个仅5.4M参数的通用多模态基础模型，通过共享编码器联合处理EEG、ECG和PPG信号。基于LUNA的通道统一模块，将多模态通道视为带传感器类型嵌入的统一查询集，实现高效跨模态早期融合，并具备推理时对缺失模态的内在鲁棒性。尽管模型小巧，其性能媲美甚至超越最大达57倍的模型：在TUAB数据集上异常脑电检测平衡准确率达81.21%，在HMC多模态睡眠分期任务上达到0.7416的先进平衡准确率。采用INT8量化的感知训练可恢复≥96%全精度性能；部署于GAP9超低功耗RISC-V微控制器后，12导联10秒心电推理延迟为325.6毫秒，功耗18.8毫焦；30秒周期的5通道多模态睡眠分期延迟1.206秒，功耗68.65毫焦。
原文摘要 · Abstract (English)
Physiological foundation models (FMs) have shown promise for biosignal representation learning, yet most remain confined to a single modality such as EEG, ECG, or PPG, largely because paired multimodal datasets are scarce. In this paper, we present PanLUNA, a compact 5.4M-parameter pan-modal FM that jointly processes EEG, ECG, and PPG within a single shared encoder. Extending LUNA's channel-unification module, PanLUNA treats multimodal channels as entries in a unified query set augmented with sensor-type embeddings, enabling efficient cross-modal early fusion while remaining inherently robust to missing modalities at inference time. Despite its small footprint, PanLUNA matches or exceeds models up to 57$\times$ larger: 81.21% balanced accuracy on TUAB abnormal EEG detection and state-of-the-art 0.7416 balanced accuracy on HMC multimodal sleep staging. Quantization-aware training with INT8 weights recovers $\geq$96% of full-precision performance, and deployment on the GAP9 ultra-low-power RISC-V microcontroller for wearables achieves 325.6 ms latency and 18.8 mJ per 10-second, 12-lead ECG inference, and 1.206 s latency at 68.65 mJ for multimodal 5-channel sleep staging over 30-second epochs.
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。