Force Modelling of Upper Limb Biomechanics Using Ensemble Fast Orthogonal Search on High-Density Electromyography

Estimation of Muscle Forces of Lower Limbs Based on CNN-LSTM Neural Network and Wearable Sensor System

Estimation of vivo muscle forces during human motion is important for understanding human motion control mechanisms and joint mechanics. This paper combined the advantages of the convolutional neural network (CNN) and long-short-term memory (LSTM) and proposed a novel muscle force estimation method based on CNN-LSTM. A wearable sensor system was also developed to collect the angles and angular velocities of the hip, knee, and ankle joints in the sagittal plane during walking, and the collected kinematic data were used as the input for the neural network model. In this paper, the muscle forces calculated using OpenSim based on the Static Optimization (SO) method were used as the standard value to train the neural network model. Four lower limb muscles of the left leg, including gluteus maximus (GM), rectus femoris (RF), gastrocnemius (GAST), and soleus (SOL), were selected as the studying objects in this paper. The experiment results showed that compared to the standard CNN and the standard LSTM, the CNN-LSTM performed better in muscle forces estimation under slow (1.2 m/s), medium (1.5 m/s), and fast walking speeds (1.8 m/s). The average correlation coefficients between true and estimated values of four muscle forces under slow, medium, and fast walking speeds were 0.9801, 0.9829, and 0.9809, respectively. The average correlation coefficients had smaller fluctuations under different walking speeds, which indicated that the model had good robustness. The external testing experiment showed that the CNN-LSTM also had good generalization. The model performed well when the estimated object was not included in the training sample. This article proposed a convenient method for estimating muscle forces, which could provide theoretical assistance for the quantitative analysis of human motion and muscle injury. The method has established the relationship between joint kinematic signals and muscle forces during walking based on a neural network model; compared to the SO method to calculate muscle forces in OpenSim, it is more convenient and efficient in clinical analysis or engineering applications.

Home-based upper limb stroke rehabilitation mechatronics: challenges and opportunities

Interest in home-based stroke rehabilitation mechatronics, which includes both robots and sensor mechanisms, has increased over the past 12 years. The COVID-19 pandemic has exacerbated the existing lack of access to rehabilitation for stroke survivors post-discharge. Home-based stroke rehabilitation devices could improve access to rehabilitation for stroke survivors, but the home environment presents unique challenges compared to clinics. The present study undertakes a scoping review of designs for at-home upper limb stroke rehabilitation mechatronic devices to identify important design principles and areas for improvement. Online databases were used to identify papers published 2010-2021 describing novel rehabilitation device designs, from which 59 publications were selected describing 38 unique designs. The devices were categorized and listed according to their target anatomy, possible therapy tasks, structure, and features. Twenty-two devices targeted proximal (shoulder and elbow) anatomy, 13 targeted distal (wrist and hand) anatomy, and three targeted the whole arm and hand. Devices with a greater number of actuators in the design were more expensive, with a small number of devices using a mix of actuated and unactuated degrees of freedom to target more complex anatomy while reducing the cost. Twenty-six of the device designs did not specify their target users' function or impairment, nor did they specify a target therapy activity, task, or exercise. Twenty-three of the devices were capable of reaching tasks, 6 of which included grasping capabilities. Compliant structures were the most common approach of including safety features in the design. Only three devices were designed to detect compensation, or undesirable posture, during therapy activities. Six of the 38 device designs mention consulting stakeholders during the design process, only two of which consulted patients specifically. Without stakeholder involvement, these designs risk being disconnected from user needs and rehabilitation best practices. Devices that combine actuated and unactuated degrees of freedom allow a greater variety and complexity of tasks while not significantly increasing their cost. Future home-based upper limb stroke rehabilitation mechatronic designs should provide information on patient posture during task execution, design with specific patient capabilities and needs in mind, and clearly link the features of the design to users' needs.

Towards Evaluating Pitch-Related Phonation Function in Speech Communication Using High-Density Surface Electromyography

Pitch, as a sensation of the sound frequency, is a crucial attribute toward constructing a natural voice for communication. Producing intelligible sounds with normal pitches depend on substantive interdependencies among facial and neck muscles. Clarifying the interrelations between the pitches and the corresponding muscular activities would be helpful for evaluating the pitch-related phonating functions, which would play a significant role both in training pronunciation and in assessing dysphonia. In this study, the speech signals and the high-density surface electromyography (HD sEMG) signals were synchronously acquired when phonating [a:], [i:], and [ә:] vowels with increasing pitches, respectively. The HD sEMG energy maps were constructed based on the root mean square values to visualize spatiotemporal characteristics of facial and neck muscle activities. Normalized median frequency (nMF) and root-mean square (nRMS) were correspondingly extracted from the speech and sEMG recordings to quantitatively investigate the correlations between sound frequencies and myoelectric characteristics. The results showed that the frame-wise energy maps built from sEMG recordings presented that the muscle contraction strength increased monotonously across pitch-rising, with left-right symmetrical distribution for the face/neck. Furthermore, the nRMS increased at a similar rate to the nMF when there were rising pitches, and the two parameters had a significant correlation across different vowel tasks [(a:) (0.88 ± 0.04), (i:) (0.89 ± 0.04), and (ә:) (0.87 ± 0.05)]. These findings suggested the possibility of utilizing muscle contraction patterns as a reference for evaluating pitch-related phonation functions. The proposed method could open a new window for developing a clinical approach for assessing the muscular functions of dysphonia.

The Influence of the sEMG Amplitude Estimation Technique on the EMG–Force Relationship

The estimation of the sEMG–force relationship is an open problem in the scientific literature; current methods show different limitations and can achieve good performance only on limited scenarios, failing to identify a general solution to the optimization of this kind of analysis. In this work, this relationship has been estimated on two different datasets related to isometric force-tracking experiments by calculating the sEMG amplitude using different fixed-time constant moving-window filters, as well as an adaptive time-varying algorithm. Results show how the adaptive methods might be the most appropriate choice for the estimation of the correlation between the sEMG signal and the force time course. Moreover, the comparison between adaptive and standard filters highlights how the time constants exploited in the estimation strategy is not the only influence factor on this kind of analysis; a time-varying approach is able to constantly capture more information with respect to fixed stationary approaches with comparable window lengths.

Deep Multi-scale Fusion of Convolutional Neural Networks for EMG-based Movement Estimation

EMG-based motion estimation is required for applications such as myoelectric control, where the simultaneous estimation of kinematic information, namely joint angle and velocity, is challenging and critical. We propose a novel method for accurately modelling the generated joint angle and velocity simultaneously under isotonic, isokinetic (quasi-dynamic), and fully dynamic conditions. Our solution uses two streams of CNN, called TS-CNN to learn informative features from raw EMG data using different scales and estimate the generated motion during elbow flexion and extension. The experimental results show the robustness of our approach in comparison to conventional CNN as well as some methods used in the literature. The best obtained R2 values, are 0.81±0.06, 0.71±0.06, and 0.80±0.13 for joint angle estimation and 0.78±0.05, 0.79±0.07, and 0.71±0.13 for the velocity estimation, during isotonic, isokinetic, and dynamic contractions, respectively. Additionally, our results indicate that the experimental condition can have an impact on the model's performance for motion prediction. EMG-based velocity estimation obtains higher performance than joint angle estimation under isokinetic conditions. Under dynamic conditions, joint angle estimation is more accurate than velocity estimation, and there is no difference between joint angle and velocity estimation in the isotonic case.

Automated Channel Selection in High-Density sEMG for Improved Force Estimation

Accurate and real-time estimation of force from surface electromyogram (EMG) signals enables a variety of applications. We developed and validated new approaches for selecting subsets of high-density (HD) EMG channels for improved and lower-dimensionality force estimation. First, a large dataset was recorded from a number of participants performing isometric contractions in different postures, while simultaneously recording HD-EMG channels and ground-truth force. The EMG signals were acquired from three linear surface electrode arrays, each with eight monopolar channels, and were placed on the long head and short head of the biceps brachii and brachioradialis. After data collection and pre-processing, fast orthogonal search (FOS) was employed for force estimation. To select a subset of channels, principal component analysis (PCA) in the frequency domain and a novel index called the power-correlation ratio (PCR), which maximizes the spectral power while minimizing similarity to other channels, were used. These approaches were compared to channel selection using time-domain PCA. We selected one, two, and three channels per muscle from the original seven differential channels to reduce the redundancy and correlation in the dataset. In the best case, we achieved an approximate improvement of 30% for force estimation while reducing the dimensionality by 57% for a subset of three channels.

An Investigation of Dimensionality Reduction Techniques for EMG-based Force Estimation

In this paper, extracted features in time and frequency domain, from high-density surface electromyogram (HD-sEMG) signals acquired from the long head and short head of biceps brachii, and brachioradialis during isometric elbow flexion are used to estimate force induced at the wrist using an artificial neural network (ANN). Different hidden layer sizes were considered to investigate its effect on the model accuracy. Also, we applied two dimensionality reduction techniques, principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE), on the feature set and investigated their effects on force estimation accuracy.

PCA-Based Channel Selection in High-Density EMG for Improving Force Estimation

In this paper, a method for selecting channels to improve estimated force using fast orthogonal search (FOS) has been proposed. Surface electromyogram (sEMG) signals acquired from linear surface electrode arrays, placed on the long head and short head of biceps brachii, and brachioradialis during isometric contractions are used to estimate force induced at the wrist using the FOS algorithm. The method utilizes principle component analysis (PCA) in the frequency domain to select the channels with the highest contribution to the first principal component (PC). Our analysis demonstrates that our proposed method is capable of reducing the dimensionality of the data (the number of channels was reduced from 21 to 9) while improving the accuracy of the estimated force.

A Novel HD-sEMG Preprocessing Method Integrating Muscle Activation Heterogeneity Analysis and Kurtosis-Guided Filtering for High-Accuracy Joint Force Estimation

This study proposes a novel preprocessing method integrating muscle activation heterogeneity analysis and kurtosis-guided filtering to realize high-accuracy surface electromyogr-aphy (sEMG)-based force estimation. A total of 10 subjects were recruited. Each subject performed isometric elbow flexion tasks at 20%, 40%, and 60% maximum voluntary contraction (MVC) target force levels, and the joint force and high-density sEMG (HD-sEMG) signals from biceps brachii and brachialis were collected synchronously. The force estimation model was built using three-order polynomial fitting technique. The input signal extraction of the force model, also named as the preprocessing of HD-sEMG signal, was carried out in the following procedures: first, HD-sEMG signals were decomposed by principal component analysis into principal components and weight vectors; second, the first several weight maps were segmented to obtain heterogeneity information by the Otsu and Moore-Neighbor tracing methods, and the principal component covering the most activated areas was selected; and last, a kurtosis-guided filter was designed to process the selected principal component to obtain the input signal. For the sake of comparison, the joint force estimation experiments based ON five preprocessing methods were conducted. The experimental results demonstrated that the proposed method obtained 52%, 53%, and 59% reduction in the mean root mean square difference at 20% MVC, 40% MVC, and 60% MVC force-level tasks, respectively, compared to the preprocessing method with the first principal component plus fixed parameter filtering. This proposed HD-sEMG pre-processing method has reliable neuromuscular electro-physiological foundation, and has good application value for realizing high-accuracy muscle/joint force estimation in the fields of rehabilitation engineering, sports biomechanics, and muscle disease diagnosis etc.

A SEMG-Force Estimation Framework Based on a Fast Orthogonal Search Method Coupled with Factorization Algorithms

A novel framework based on the fast orthogonal search (FOS) method coupled with factorization algorithms was proposed and implemented to realize high-accuracy muscle force estimation via surface electromyogram (SEMG). During static isometric elbow flexion, high-density SEMG (HD-SEMG) signals were recorded from upper arm muscles, and the generated elbow force was measured at the wrist. HD-SEMG signals were decomposed into time-invariant activation patterns and time-varying activation curves using three typical factorization algorithms including principal component analysis (PCA), independent component analysis (ICA), and nonnegative matrix factorization (NMF). The activation signal of the target muscle was obtained by summing the activation curves, and the FOS algorithm was used to create basis functions with activation signals and establish the force estimation model. Static isometric elbow flexion experiments at three target levels were performed on seven male subjects, and the force estimation performances were compared among three typical factorization algorithms as well as a conventional method for extracting the average signal envelope of all HD-SEMG channels (AVG-ENVLP method). The overall root mean square difference (RMSD) values between the measured forces and the estimated forces obtained by different methods were 11.79 ± 4.29% for AVG-ENVLP, 9.74 ± 3.77% for PCA, 9.59 ± 3.81% for ICA, and 9.51 ± 4.82% for NMF. The results demonstrated that, compared to the conventional AVG-ENVLP method, factorization algorithms could substantially improve the performance of force estimation. The FOS method coupled with factorization algorithms provides an effective way to estimate the combined force of multiple muscles and has potential value in the fields of sports biomechanics, gait analysis, prosthesis control strategy, and exoskeleton devices for assisted rehabilitation.