Estimation of Knee Extension Force Using Mechanomyography Signals Based on GRA and ICS-SVR

Abstract

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.

MMG-Based Knee Dynamic Extension Force Estimation Using Cross-Talk and IGWO-LSTM

“…The experimental setup and quadriceps anatomy are illustrated in Figure 1. The signal acquisition equipment and sensor placement referenced pre-work [31]. The subjects were asked to sit comfortably in a test chair with their right leg fixed and bent at a 90 • angle.…”

“…Therefore, it is necessary to consider time domain features, frequency domain features, time-frequency domain features, and non-linear features to describe MMG signals to adequately reflect muscle activity. To this end, we extracted 25 features from each segment, and a total of 75 features from the three channels [31]. Not all of these features are highly correlated with knee dynamic extension force.…”

“…Not all of these features are highly correlated with knee dynamic extension force. Therefore, in this paper, the grey relational analysis (GRA) method from the previous work was used for feature screening to obtain valid features that are highly correlated with knee dynamic extension force [31]. Valid features screened from different subjects using the GRA method are not the same due to individual differences.…”

“…When MMG signals are employed for muscle force estimation, apart from the consideration of cross-talk, a significant technical difficulty is the development of an appropriate muscle force estimation model. In the previous stage, we constructed knee static extension force estimation models using support vector regression (SVR) [30,31] and achieved high accuracy. However, when applying these models to knee dynamic extension force estimation, the results were not satisfactory.…”

Study on Flexible sEMG Acquisition System and Its Application in Muscle Strength Evaluation and Hand Rehabilitation

“…However, the direct and accurate measurement of muscle force is currently very difficult and complex, and the study of muscle force estimation methods is of great significance. Numerous studies in the literature have shown that sEMG has a high correlation with muscle activity [26][27][28] and that the signal has the advantages of easy acquisition and non-invasiveness, making it suitable for estimating muscle force [29][30][31]. Muscle force is the result of the complex superposition of many muscle groups and it is very difficult to estimate the force of each muscle.…”