LiteEMG-FM is an efficient hybrid CNN‑Transformer foundation model designed for electromyography (EMG) sensing. It is pretrained on 16 diverse upper‑ and lower‑limb EMG datasets, enabling representations that generalize across users and datasets. The model incorporates a lightweight, always‑on 1D‑CNN wake‑up module that filters rest and non‑target activity, activating LiteEMG‑FM only for valid gestures, and is evaluated in full inference offloading, split inference, and full on‑device processing scenarios, showing superior performance over state‑of‑the‑art time‑series foundation models and supervised baselines, especially in zero‑calibration cross‑participant and data‑scarce conditions.
arXiv:2609.25582v1 Announce Type: new Abstract: Public surface electromyography (EMG) datasets vary widely in electrode layout, channel count, frequency support, and size. Simply mixing them for pret...
arXiv:2601. 04181v2 Announce Type: replace Abstract: Reliable long-term decoding of gestures from surface electromyography (EMG) is hindered by signal drift caused by electrode displacement, muscle fatigue, and/or posture changes.
NanoSleep is a compact hybrid temporal convolutional network designed for single‑channel EEG sleep stage classification. It integrates a learnable Sinc‑convolutional front end, dual‑branch feature extraction for multi‑scale temporal and spectral representations, a gated dilated temporal convolutional backbone with channel recalibration, and a conditional random field for sequence‑level decoding. Evaluated on Sleep‑EDF and Sleep‑EDF‑Expanded datasets, NanoSleep consistently outperforms six baseline methods and demonstrates that each major component contributes to its performance.
BRIDGE-EEG is an efficient multi‑task EEG classification pipeline that leverages self‑supervised pretraining while dramatically reducing model size. It maps heterogeneous EEG recordings to a unified 62‑channel time‑frequency representation, pretrains an SE‑ResNet18 teacher with SimCLR, and distills it into smaller SE‑ResNet8 and SE‑ResNet4 students. The compact models achieve accuracy comparable to or better than larger foundation models on abnormality detection and emotion recognition, and they consume up to three times less energy on edge devices, enabling deployment on wearable hardware.
arXiv:2607. 22779v1 Announce Type: cross Abstract: Hand gesture recognition via surface electromyography (sEMG) is fundamental to prosthetic control.
arXiv:2508. 11664v2 Announce Type: replace-cross Abstract: Sleep stage classification is critical for diagnosing and managing disorders like sleep apnea and insomnia.
arXiv:2607. 10784v1 Announce Type: cross Abstract: Deploying deep learning models for automated electrocardiogram classification on resource-constrained wearable devices remains challenging due to high computational costs.
arXiv:2608. 13316v1 Announce Type: cross Abstract: Foundation models (FMs) trained on large-scale accelerometer data have been proposed as general-purpose feature extractors for health monitoring, but systematic evidence of their advantages is lacking.
arXiv:2606. 14604v1 Announce Type: cross Abstract: Wearable devices and smartphones generate rich behavioural time series that can support proactive health interventions, yet systematic comparisons of modern forecasting architectures for these data are lacking.
NanoSleep is a compact hybrid temporal convolutional network designed for single‑channel EEG sleep stage classification. It integrates a learnable Sinc‑convolutional front end, dual‑branch feature extraction combining multi‑scale temporal and spectral representations, a gated dilated temporal convolutional backbone with channel recalibration, and a conditional random field for sequence decoding. Evaluated on Sleep‑EDF datasets, NanoSleep consistently outperforms six baseline methods, with ablation studies confirming the contribution of each component.
arXiv:2608. 09421v1 Announce Type: cross Abstract: Wearable human activity recognition (HAR) remains challenging due to the computational and energy constraints of deep learning models on resource-limited devices.
arXiv:2510. 18668v4 Announce Type: replace Abstract: Wearable cardiovascular sensor patches promise continuous, unobtrusive monitoring, but their tight energy, memory, and compute budgets make it unclear whether physiological signals should be analyzed on the device or streamed to the cloud for processing.