LiteEMG-FM improves real-time muscle signal recognition for devices
LiteEMG-FM: An Efficient and Deployable Foundation Model for Robust EMG Sensing
Machine Learning
Summary
Muscle electrical signals change a lot depending on who you are, where on the body you measure, and the device used. This makes it hard to build devices that understand these signals well for everyone. The authors created LiteEMG-FM, a smart model trained on many different muscle signal datasets, which works well across people and devices. It also uses a clever method to save battery by only turning on fully when needed. This model performs better than previous ones, especially when there isn’t much training data or no user-specific setup.
What this means in practice
- •For wearable device developers: Build low-power, real-time gesture recognition features that work well across different users without additional calibration.$Commercial implications: Enables more accurate and efficient EMG-based wearable products for human-computer interaction and assistive technology.
- •For assistive technology engineers: Implement robust muscle signal decoding systems that adapt to diverse users and hardware for improved device control.
Authors
Tianhao Wu, Xu Wu, Amirmohammad Radmehr, Jiawei Yu, Yi Wu, Phuc Nguyen, Jian Liu
Abstract
Electromyography (EMG) signals vary substantially across individuals, body regions, recording sessions, and sensing hardware, limiting the generalization of models for assistive devices and human-computer interaction. Existing time-series foundation models are also computationally expensive for real-time wearable deployment and often fail to capture EMG-specific time-frequency characteristics. We present LiteEMG-FM, an efficient hybrid CNN-Transformer foundation model for practical EMG sensing. Pretrained on 16 diverse upper- and lower-limb EMG datasets, LiteEMG-FM learns representations that generalize across users and datasets. For resource-constrained deployment, we implement a hierarchical wake-up architecture in which a lightweight, always-on 1D-CNN filters rest and non-target activity and activates LiteEMG-FM only for valid gestures. We evaluate full inference offloading, split inference, and full on-device processing, characterizing their trade-offs in latency, power consumption, and memory footprint. Across diverse evaluation settings, LiteEMG-FM outperforms state-of-the-art time-series foundation models and supervised baselines, particularly under zero-calibration cross-participant and data-scarce conditions. These results demonstrate that LiteEMG-FM is an effective, efficient, and deployable foundation model for EMG applications.