跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 16 天前AI 評分51

PhysioWave-T:面向生理訊號的高 token 效率小波基礎模型系列

PhysioWave-T: Token-Efficient Wavelet Foundation Models for Biosignals

AI 導讀

PhysioWave-T 論文提出面向 EEG、ECG 及 sEMG 的小波基礎模型系列,透過動態尺度折疊減少 token 數量。其 30M 參數 EEG 模型以超過 15M 個窗口預訓練;在四種 EEG 路線中,尺度折疊相較尺度擴展使 Transformer 延遲降低 4.0–7.2 倍、峯值記憶體降低 6.8–12.7 倍,準確度沒有下降。

正文

Published on Nov 6

Authors:

,

,

,

Abstract

We present PhysioWave-T, a token-efficient wavelet foundation model family for EEG, ECG, and sEMG. Dynamic scale folding recombines J+1 wavelet subbands prior to tokenization, compressing sequence length from (J+1)CS to CS tokens for J levels, C channels, and S temporal patches. Route-specific front ends and learned channel-name embeddings allow one Transformer per modality to handle diverse montages and sampling rates, while unseen setups reuse the backbone via lightweight adapters. We pre-train a 30M-parameter EEG model on over 15M windows (19--128 channels), alongside ECG (30M) and sEMG (12M) encoders. Across four EEG routes, scale folding cuts Transformer latency by 4.0--7.2x and peak memory by 6.8--12.7x over scale expansion without accuracy loss. Our EEG encoder leads 8 of 9 metrics against BENDR, BIOT, LaBraM, and EEGPT, and surpasses LUNA-L on wearable seizure detection with fewer parameters. Reliability-aware latent fusion (RALF) further integrates summary tokens from independently pre-trained encoders via sample-adaptive weights. On SeizeIT2, RALF raises event sensitivity at 11 false alarms/h from 61.4% to 74.4% and window AUPRC from 0.321 to 0.399 over the best unimodal baseline, outperforming weighted-logit and concatenation fusion across all variants. PhysioWave-T also achieves state-of-the-art sEMG accuracies and top macro-F1 on PTB-XL Super and Chapman-Shaoxing. Code and models: https://github.com/ForeverBlue816/PhysioWave.

View arXiv page View PDF Project page GitHub 215 Add to collection

Get this paper in your agent:

hf papers read 2611.08969

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 4

ForeverBlue/EEG

Feature Extraction •

Updated about 20 hours ago

•

1

ForeverBlue/EMG

Feature Extraction •

Updated about 20 hours ago

•

1

ForeverBlue/ECG

Feature Extraction •

Updated about 20 hours ago

•

1

ForeverBlue/RALF-SeizeIT2

Other •

Updated about 20 hours ago

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.08969 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.08969 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co