The measurements of mechanomyography (MMG) are commonly contaminated by motion artifacts due to limb movement, and artifacts are unavoidable when an acceleration (ACC) sensor is used in dynamic conditions. Conventionally, the Fourier-based approach is used to eliminate artifacts from the single-channel MMG signal by applying a Butterworth bandpass filter. A noise-assisted multivariate empirical mode decomposition (NA-MEMD) approach is proposed for the suppression of motion artifacts in multichannel MMG signals. The sample autocorrelation and the energy of each intrinsic mode function (IMF) were analyzed to identify the noise-IMF and artifact-IMF, respectively. We describe the proposed method and compare its performance with that of other conventional approaches (Butterworth filter, wavelet denoising) for the multichannel MMG signals recorded from both isometric and dynamic muscle contraction. The experimental results reveal the superiority of the proposed approach due to a lower level of distortion introduced in the MMG data after the suppression of motion artifacts. Additionally, MEMD provides a novel basis for MMG signal feature extraction as well as frequency and crosstalk investigations.

With the growth of the number of elderly and disabled with motor dysfunction, the demand for assisted exercise is increasing. Wearable power assistance robots are developed to provide athletic ability of limbs for the elderly or the disabled who have weakened limbs to better self-care ability. Existing wearable power-assisted robots generally use surface electromyography (sEMG) to obtain effective human motion intentions. Due to the characteristics of sEMG signals, it is limited in many applications. To solve the above problems, we design a long short-term memory (LSTM) neural network model based on human mechanomyography (MMG) signals to estimate the motion acceleration of knee joint. The acceleration can be further calculated by the torque required for movement control of the wearable power assistance robots for the lower limb. We detect MMG signals on the clothed thigh, extract features of the MMG signals, and then, use principal component analysis to reduce the features’ dimensions. Finally, the dimension-reduced features are inputted into the LSTM neural network model in time series for estimating the acceleration. The experimental results show that the average correlation coefficient (R) is 94.48 ± 1.91% for the estimation of acceleration in the process of continuously performing under approximately π/4 rad/s. This approach can be applied in the practical applications of wearable field.