Multi-Day Muscle Fatigue Estimation During Dynamic Exercise Using sEMG E-Tattoo and BH-IEEMD Processing

Dynamic surface electromyography (sEMG)-based muscle fatigue assessment is often compromised by sensor instability, motion artifacts, and signal nonstationarity during dynamic exercise. Here, we integrate a noninvasive, skin-conformal e-tattoo sensor with a bandpass-Hampel-iterative ensemble empirical mode decomposition (BH-IEEMD) processing pipeline to suppress impulsive noise and stabilize fatigue-related features. Twenty participants wore the e-tattoo continuously for five days while performing daily dynamic exercises, with sEMG signals benchmarked against conventional gel electrodes. The e-tattoo maintained stable contact impedance, a noise floor comparable to gel electrodes, and higher signal-to-noise and signal-to-motion ratios during movement, without inducing skin irritation. BH-IEEMD significantly attenuated sub-20-Hz motion-induced power and transient artifacts, leading to improved window-level autocovariance stationarity. Relative to bandpass-only baselines, features extracted using BH-IEEMD exhibited tighter distributions, improved Normal-versus-Fatigue separability, and greater reproducibility of fatigue trends across days and subjects. Leave-one-subject-out evaluation confirmed model-agnostic performance gains, with the best-performing model achieving an average R ${}^{{2}} =0.70$ (RMSE = 0.157) and best-subject performance reaching R ${}^{{2}} =0.93$ (RMSE = 0.074). Together, long-term skin-conformable sensing and artifact-aware signal processing establish a robust framework for reliable multi-day muscle fatigue monitoring, enabling practical deployment in real-world rehabilitation, training, and wearable exoskeleton control.