A neuromorphic based median frequency tracker for muscle fatigue monitoring

Surface Electromyography (sEMG) analysis can provide useful information about a muscle's fatigue state by estimating the median frequency of the signal. The Power Spectral Density (PSD) of the sEMG spectrum undergoes continuous compression and change of shape during sustained contractions. This paper presents a novel circuit implementation of a median frequency tracker using neuromorphic circuits. The circuit is simulated and evaluated using retrospective sEMG signals and the results are compared with a MATLAB ideal median frequency function to achieve an error of less than 0.64% compared to MATLAB. The system has been implemented in a commercially available 0.35 μm CMOS technology with a power consumption of 150μW from a 3.3 V supply.