PanLUNA: An Efficient and Robust Query-Unified Multimodal Model for Edge Biosignal Intelligence

TL;DR

PanLUNA is a compact, multimodal biosignal foundation model that efficiently processes EEG, ECG, and PPG data, achieving high accuracy and low-power inference suitable for edge devices.

Contribution

It introduces PanLUNA, a small yet powerful multimodal model with a shared encoder that handles missing modalities and outperforms larger models on biosignal tasks.

Findings

Achieves 81.21% accuracy on EEG abnormality detection.

Sets state-of-the-art 0.7416 accuracy on sleep staging.

Runs efficiently on low-power microcontrollers with minimal latency.

Abstract

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.