Reproduce “Efficient and Robust Spiking Neural Networks for sEMG-Based Muscle Fatigue Detection” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Kaiwen Tang, Jiaqi Dong, Zhanglu Yan, Weng-Fai Wong
The authors develop a wearable fatigue-monitoring method for noisy surface electromyography signals using sparse spiking neural networks, noise-robust training, and low-bit weight quantization. On SPE, with QAF post-processing, their SNN reaches 90.14% F1, versus 87.00% for an MLP. Across seven test-time perturbations, SDH is more stable than comparison methods; energy savings up to 201.77× are estimates, not wearable measurements.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.