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.

Mechanomyography (MMG) signals have extensive applications in muscle function assessment and human intention recognition. However, during signal acquisition, MMG signals are easily contaminated by noise and artifacts, which seriously affects the recognition of their characteristics. To address these issues, a novel noise suppression and artifact removal method based on recursive least square (RLS), improved Gray Wolf Optimizer-optimized variable mode decomposition (IGWO-VMD), and complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is proposed. In this paper, the RLS algorithm is first applied to adaptively filter out the power line interference (PLI). Then, IGWO is designed to select the appropriate VMD parameters and use the VMD to decompose the noisy signal into band-limited intrinsic mode functions (BLIMFs). In addition, the BLIMFs are classified into the low-frequency part and high-frequency part according to the given correlation coefficient (CC) threshold value. The effective components of the low-frequency part are identified by the center frequency. Meanwhile, the high-frequency part is decomposed by CEEMDAN, and its effective components are obtained according to the proposed sample entropy threshold range. Finally, the effective components of the low and high-frequency parts are reconstructed to obtain the denoised signal to realize the extraction of useful signals. Simulation experiment results demonstrate that the proposed method outperforms the classical methods and the designed IGWO-VMD method in terms of denoising performance. The effectiveness of the proposed method is verified through the measured MMG signal experiments. The proposed method not only effectively suppresses noise and artifacts but also overcomes the limitations of VMD and CCEMDAN.

Muscle force is an important physiological parameter of the human body. Accurate estimation of the muscle force can improve the stability and flexibility of lower limb joint auxiliary equipment. Nevertheless, the existing force estimation methods can neither satisfy the accuracy requirement nor ensure the validity of estimation results. It is a very challenging task that needs to be solved. Among many optimization algorithms, gray wolf optimization (GWO) is widely used to find the optimal parameters of the regression model because of its superior optimization ability. Due to the traditional GWO being prone to fall into local optimum, a new nonlinear convergence factor and a new position update strategy are employed to balance local and global search capability. In this paper, an improved gray wolf optimization (IGWO) algorithm to optimize the support vector regression (SVR) is developed to estimate knee joint extension force accurately and timely. Firstly, mechanomyography (MMG) of the lower limb is measured by acceleration sensors during leg isometric muscle contractions extension training. Secondly, root mean square (RMS), mean absolute value (MAV), zero crossing (ZC), mean power frequency (MPF), and sample entropy (SE) of the MMG are extracted to construct feature sets as candidate data sets for regression analysis. Lastly, the features are fed into IGWO-SVR for further training. Experiments demonstrate that the IGWO-SVR provides the best performance indexes in the estimation of knee joint extension force in terms of RMSE, MAPE, and R compared with the other state-of-art models. These results are expected to become the most effective as guidance for rehabilitation training, muscle disease diagnosis, and health evaluation.

During lower-extremity rehabilitation training, muscle activity status needs to be monitored in real time to adjust the assisted force appropriately, but it is a challenging task to obtain muscle force noninvasively. Mechanomyography (MMG) signals offer unparalleled advantages over sEMG, reflecting the intention of human movement while being noninvasive. Therefore, in this paper, based on MMG, a combined scheme of gray relational analysis (GRA) and support vector regression optimized by an improved cuckoo search algorithm (ICS-SVR) is proposed to estimate the knee joint extension force. Firstly, the features reflecting muscle activity comprehensively, such as time-domain features, frequency-domain features, time–frequency-domain features, and nonlinear dynamics features, were extracted from MMG signals, and the relational degree was calculated using the GRA method to obtain the correlation features with high relatedness to the knee joint extension force sequence. Then, a combination of correlated features with high relational degree was input into the designed ICS-SVR model for muscle force estimation. The experimental results show that the evaluation indices of the knee joint extension force estimation obtained by the combined scheme of GRA and ICS-SVR were superior to other regression models and could estimate the muscle force with higher estimation accuracy. It is further demonstrated that the proposed scheme can meet the need of muscle force estimation required for rehabilitation devices, powered prostheses, etc.

Accurate and long-term prediction of elbow flexion force can be used to recognize the intended movement and help wearable power-assisted robots to improve control performance. Our study aimed to find a proper relationship between electromyography and flexion force. However, the existing methods must incorporate biomechanical models to produce accurate and timely predictions of flexion force. Elbow flexion force is largely determined by the contractile properties of muscles, and the relationship between flexion force and the motor function of muscles has to be thoroughly analyzed. Therefore, based on the investigation on the contributions of different muscles to the flexion force, original electromyography signals were decomposed into non-linear and non-stationary parts. We selected the mean absolute value (MAV) of the non-linear part and the variance of the non-stationary part as inputs for an Informer prediction model that does not require detailed a priori knowledge of biomechanical models and is optimized for processing time sequences. Finally, a long-term flexion force probability interval is proposed. The proposed framework performs well in predicting long-term flexion force and outperforms other state-of-the-art models when compared to experimental results.

Electrical impedance tomography (EIT) is a nondestructive testing technique, which has great potential in the fields of muscle force estimation, human motion intent recognition, and human-machine interaction. To enhance the performance of muscle force estimation system based on EIT raw signals, we propose a electrical impedance tomography spatial-frequency feature fusion network (ESF-Net), which aims to promote adequate fusion and collaboration between spatial and frequency features. Proposed ESF-Net employs a dual-branch self-attention mechanism based on the Transformer framework, to enhance the extraction of key information features. Specifically, the spatial encoder employs a Vision Transformer-based architecture to effectively capture spatial-domain features, while the frequency encoder utilizes a 1D Transformer-based architecture to adeptly extract frequency-domain features, allowing the network to emphasize significant frequency channels. Additionally, an Attention Spatial-Frequency Fusion Module (ASFF Module) are proposed to guide network feature fusion process in proposed ESF-Net. The ASSF Module integrates spatial-frequency features from both encoders to enhance the aggregation of global context information. During these experiments, we collected EIT raw voltage signals using eight electrodes positioned around the human arm. Ten healthy subjects gradually increased their strength from 0 to 100% Maximum Voluntary Contraction (MVC) during elbow flexion, with EIT raw voltage signals being recorded and actual muscle force measured using a six-axis force sensor. When the proposed method was used, the Root Mean Squared Error (RMSE) of the estimated force relative to the measured force was 0.245N, significantly outperforming other commonly used force estimation methods, demonstrating its efficacy. The experimental results confirmed the feasibility of this method in human-computer interaction tasks.