An ICA-EBM-Based sEMG Classifier for Recognizing Lower Limb Movements in Individuals With and Without Knee Pathology

Combining enhanced spectral resolution of EMG and a deep learning approach for knee pathology diagnosis

Knee osteoarthritis (OA) is a prevalent, debilitating joint condition primarily affecting the elderly. This investigation aims to develop an electromyography (EMG)-based method for diagnosing knee pathologies. EMG signals of the muscles surrounding the knee joint were examined and recorded. The principal components of the proposed method were preprocessing, high-order spectral analysis (HOSA), and diagnosis/recognition through deep learning. EMG signals from individuals with normal and OA knees while walking were extracted from a publicly available database. This examination focused on the quadriceps femoris, the medial gastrocnemius, the rectus femoris, the semitendinosus, and the vastus medialis. Filtration and rectification were utilized beforehand to eradicate noise and smooth EMG signals. Signals' higher-order spectra were analyzed with HOSA to obtain information about nonlinear interactions and phase coupling. Initially, the bicoherence representation of EMG signals was devised. The resulting images were fed into a deep-learning system for identification and analysis. A deep learning algorithm using adapted ResNet101 CNN model examined the images to determine whether the EMG signals were conventional or indicative of knee osteoarthritis. The validated test results demonstrated high accuracy and robust metrics, indicating that the proposed method is effective. The medial gastrocnemius (MG) muscle was able to distinguish Knee osteoarthritis (KOA) patients from normal with 96.3±1.7% accuracy and 0.994±0.008 AUC. MG has the highest prediction accuracy of KOA and can be used as the muscle of interest in future analysis. Despite the proposed method's superiority, some limitations still require special consideration and will be addressed in future research.

Active Human-Following Control of an Exoskeleton Robot With Body Weight Support

This article presents an active human-following control of the lower limb exoskeleton for gait training. First, to improve safety, considering the human balance, the OpenPose-based visual feedback is used to estimate the individual's pose, then, the active human-following algorithm is proposed for the exoskeleton robot to achieve the body weight support and active human-following. Second, taking the human's intention and voluntary efforts into account, we develop a long short-term memory (LSTM) network to extract surface electromyography (sEMG) to build the estimation model of joints' angles, that is, the multichannel sEMG signals can be correlated with flexion/extension (FE) joints' angles of the human lower limb. Finally, to make the robot motion adapt to the locomotion of subjects under uncertain nonlinear dynamics, an adaptive control strategy is designed to drive the exoskeleton robot to track the desired locomotion trajectories stably. To verify the effectiveness of the proposed control framework, several recruited subjects participated in the experiments. Experimental results show that the proposed joints' angles estimation model based on the LSTM network has a higher estimation accuracy and predicted performance compared with the existing deep neural network, and good simultaneous locomotion tracking performance is achieved by the designed control strategy, which indicates that the proposed control can assist subjects to perform gait training effectively.

Diagnosis of motor function injury based on near-infrared spectroscopy brain imaging (fNIRS) technology

Most clinical stroke patients may have difficulty moving, affecting their self-care ability and quality of life, and causing serious interference with the normal life and work of other family members. At present, in clinical literature, researchers provide functional training for patients with motor disorders through repeated and effective training, which can ultimately effectively promote the recovery of limb function. Therefore, the near-infrared spectroscopy imaging technology (fNIRS) used in this study combines the diagnosis of sports injury with the mechanism of brain function. FNIRS technology has many advantages, such as fast, and non-invasive, and has shown great value in detecting brain activity. Therefore, it has become a promising method in the biomedical field, especially in the field of brain science. Based on the clinical effects of sports injury treatment, fNIRS technology is used to detect the hemodynamic changes of hemoglobin circulation in the patient's brain tissue during training, and to detect the brain activity mechanism in the exercise mechanism, providing a basis for the clinical application of this method.

Estimation of Knee Joint Angle from Surface EMG Using Multiple Kernels Relevance Vector Regression

In wearable robots, the application of surface electromyography (sEMG) signals in motion intention recognition is a hot research issue. To improve the viability of human-robot interactive perception and to reduce the complexity of the knee joint angle estimation model, this paper proposed an estimation model for knee joint angle based on the novel method of multiple kernel relevance vector regression (MKRVR) through offline learning. The root mean square error, mean absolute error, and R2_score are used as performance indicators. By comparing the estimation model of MKRVR and least squares support vector regression (LSSVR), the MKRVR performs better on the estimation of the knee joint angle. The results showed that the MKRVR can estimate the knee joint angle with a continuous global MAE of 3.27° ± 1.2°, RMSE of 4.81° ± 1.37°, and R² of 0.8946 ± 0.07. Therefore, we concluded that the MKRVR for the estimation of the knee joint angle from sEMG is viable and could be used for motion analysis and the application of recognition of the wearer's motion intentions in human-robot collaboration control.

A novel attention-guided ECA-CNN architecture for sEMG-based gait classification

Gait recognition and classification technology is one of the essential technologies for detecting neurodegenerative dysfunction. This paper presents a gait classification model based on a convolutional neural network (CNN) with an efficient channel attention (ECA) module for gait detection applications using surface electromyographic (sEMG) signals. First, the sEMG sensor was used to collect the experimental sample data, and various gaits of different persons were collected to construct the sEMG signal data sets of different gaits. The CNN is used to extract the features of the one-dimensional input sEMG signal to obtain the feature vector, which is input into the ECA module to realize cross-channel interaction. Then, the next part of the convolutional layer is input to learn the signal features further. Finally, the model is output and tested to obtain the results. Comparative experiments show that the accuracy of the ECA-CNN network model can reach 97.75%.

Motion Intent Recognition in Intelligent Lower Limb Prosthesis Using One-Dimensional Dual-Tree Complex Wavelet Transforms

The motion intent recognition via lower limb prosthesis can be regarded as a kind of short-term action recognition, where the major issue is to explore the gait instantaneous conversion (known as transitional pattern) between each two adjacent different steady states of gait mode. Traditional intent recognition methods usually employ a set of statistical features to classify the transitional patterns. However, the statistical features of the short-term signals via the instantaneous conversion are empirically unstable, which may degrade the classification accuracy. Bearing this in mind, we introduce the one-dimensional dual-tree complex wavelet transform (1D-DTCWT) to address the motion intent recognition via lower limb prosthesis. On the one hand, the local analysis ability of the wavelet transform can amplify the instantaneous variation characteristics of gait information, making the extracted features of instantaneous pattern between two adjacent different steady states more stable. On the other hand, the translation invariance and direction selectivity of 1D-DTCWT can help to explore the continuous features of patterns, which better reflects the inherent continuity of human lower limb movements. In the experiments, we have recruited ten able-bodied subjects and one amputee subject and collected data by performing five steady states and eight transitional states. The experimental results show that the recognition accuracy of the able-bodied subjects has reached 98.91%, 98.92%, and 97.27% for the steady states, transitional states, and total motion states, respectively. Furthermore, the accuracy of the amputee has reached 100%, 91.16%, and 90.27% for the steady states, transitional states, and total motion states, respectively. The above evidence finally indicates that the proposed method can better explore the gait instantaneous conversion (better expressed as motion intent) between each two adjacent different steady states compared with the state-of-the-art.

Voting-based 1D CNN model for human lower limb activity recognition using sEMG signal

Surface electromyography (sEMG) signal classification has many applications such as human-machine interaction, diagnosis of kinesiological studies, and neuromuscular diseases. However, these signals are complicated because of different artifacts added to the sEMG signal during recording. In this study, a multi-stage classification technique is proposed for the identification of distinct movements of the lower limbs using sEMG signals acquired from leg muscles of healthy knee and abnormal knee subjects. This investigation involves 11 subjects with a knee abnormality and 11 without knee abnormality for three distinct activities viz. walking, leg extension from sitting position (sitting), and flexion of the leg (standing). Discrete wavelet denoising to fourth level decomposition has been implemented for the artifact reduction and the signal has been segmented using overlapping windowing technique. A study of four different architectures of 1D convolutional neural network models is undertaken for the prediction of lower limb activities and the final prediction is achieved via a voting mechanism of all four model results. The performance parameters of CNN models have been calculated for three different cases: (1) healthy subjects (2) subjects with knee abnormality (3) Pooled data (combination of abnormal knee and healthy knee subjects) using nested threefold cross-validation. It has been found that the voting mechanism yields an average classification accuracy as 99.35%, 97.63%, and 97.14% for healthy subjects, knee abnormal subjects, and pooled data, respectively. The result validates that the proposed voting-based 1D CNN model is efficient and useful in lower limb activity recognition using the sEMG signal.

A Novel sEMG-Based Gait Phase-Kinematics-Coupled Predictor and Its Interaction With Exoskeletons

The interaction between human and exoskeletons increasingly relies on the precise decoding of human motion. One main issue of the current motion decoding algorithms is that seldom algorithms provide both discrete motion patterns (e.g., gait phases) and continuous motion parameters (e.g., kinematics). In this paper, we propose a novel algorithm that uses the surface electromyography (sEMG) signals that are generated prior to their corresponding motions to perform both gait phase recognition and lower-limb kinematics prediction. Particularly, we first propose an end-to-end architecture that uses the gait phase and EMG signals as the priori of the kinematics predictor. In so doing, the prediction of kinematics can be enhanced by the ahead-of-motion property of sEMG and quasi-periodicity of gait phases. Second, we propose to select the optimal muscle set and reduce the number of sensors according to the muscle effects in a gait cycle. Finally, we experimentally investigate how the assistance of exoskeletons can affect the motion intent predictor, and we propose a novel paradigm to make the predictor adapt to the change of data distribution caused by the exoskeleton assistance. The experiments on 10 subjects demonstrate the effectiveness of our algorithm and reveal the interaction between assistance and the kinematics predictor. This study would aid the design of exoskeleton-oriented motion-decoding and human–machine interaction methods.

Muscle Synergy of Lower Limb Motion in Subjects with and without Knee Pathology

Surface electromyography (sEMG) has great potential in investigating the neuromuscular mechanism for knee pathology. However, due to the complex nature of neural control in lower limb motions and the divergences in subjects’ health and habits, it is difficult to directly use the raw sEMG signals to establish a robust sEMG analysis system. To solve this, muscle synergy analysis based on non-negative matrix factorization (NMF) of sEMG is carried out in this manuscript. The similarities of muscle synergy of subjects with and without knee pathology performing three different lower limb motions are calculated. Based on that, we have designed a classification method for motion recognition and knee pathology diagnosis. First, raw sEMG segments are preprocessed and then decomposed to muscle synergy matrices by NMF. Then, a two-stage feature selection method is executed to reduce the dimension of feature sets extracted from aforementioned matrices. Finally, the random forest classifier is adopted to identify motions or diagnose knee pathology. The study was conducted on an open dataset of 11 healthy subjects and 11 patients. Results show that the NMF-based sEMG classifier can achieve good performance in lower limb motion recognition, and is also an attractive solution for clinical application of knee pathology diagnosis.

Feature Extraction of Surface Electromyography Based on Improved Small-World Leaky Echo State Network

Surface electromyography (sEMG) is an electrophysiological reflection of skeletal muscle contractile activity that can directly reflect neuromuscular activity. It has been a matter of research to investigate feature extraction methods of sEMG signals. In this letter, we propose a feature extraction method of sEMG signals based on the improved small-world leaky echo state network (ISWLESN). The reservoir of leaky echo state network (LESN) is connected by a random network. First, we improved the reservoir of the echo state network (ESN) by these networks and used edge-added probability to improve these networks. That idea enhances the adaptability of the reservoir, the generalization ability, and the stability of ESN. Then we obtained the output weight of the network through training and used it as features. We recorded the sEMG signals during different activities: falling, walking, sitting, squatting, going upstairs, and going downstairs. Afterward, we extracted corresponding features by ISWLESN and used principal component analysis for dimension reduction. At the end, scatter plot, the class separability index, and the Davies-Bouldin index were used to assess the performance of features. The results showed that the ISWLESN clustering performance was better than those of LESN and ESN. By support vector machine, it was also revealed that the performance of ISWLESN for classifying the activities was better than those of ESN and LESN.

MyoNet: A Transfer-Learning-Based LRCN for Lower Limb Movement Recognition and Knee Joint Angle Prediction for Remote Monitoring of Rehabilitation Progress From sEMG

The clinical assessment technology such as remote monitoring of rehabilitation progress for lower limb related ailments rely on the automatic evaluation of movement performed along with an estimation of joint angle information. In this paper, we introduce a transfer-learning based Long-term Recurrent Convolution Network (LRCN) named as 'MyoNet' for the classification of lower limb movements, along with the prediction of the corresponding knee joint angle. The model consists of three blocks- (i) feature extractor block, (ii) joint angle prediction block, and (iii) movement classification block. Initially, the model is end-to-end trained for knee joint angle prediction followed by transferring the knowledge of a trained model to the movement classification through transfer-learning approach making a memory and computationally efficient design. The proposed MyoNet was evaluated on publicly available University of California (UC) Irvine machine learning repository dataset of the lower limb for 11 healthy subjects and 11 subjects with knee pathology for three movements type-walking, standing with knee flexion movements and sitting with knee extension movements. The average mean absolute error (MAE) resulted in the prediction of joint angle for healthy subjects and subjects with knee pathology are 8.1 % and 9.2 % respectively. Subsequently, an average classification accuracy of 98.1 % and 92.4 % were achieved for healthy subjects and subjects with knee pathology, respectively. Interestingly, the significance of this study in itself is promising with substantial improvement in the performance compared to state-of-the-art methodologies. The clinical significance of such surface electromyography signals (sEMG) based movement recognition and prediction of corresponding joint angle system could be beneficial for remote monitoring of rehabilitation progress by the physiotherapist using wearables.

Towards Control of a Transhumeral Prosthesis with EEG Signals

Robotic prostheses are expected to allow amputees greater freedom and mobility. However, available options to control transhumeral prostheses are reduced with increasing amputation level. In addition, for electromyography-based control of prostheses, the residual muscles alone cannot generate sufficiently different signals for accurate distal arm function. Thus, controlling a multi-degree of freedom (DoF) transhumeral prosthesis is challenging with currently available techniques. In this paper, an electroencephalogram (EEG)-based hierarchical two-stage approach is proposed to achieve multi-DoF control of a transhumeral prosthesis. In the proposed method, the motion intention for arm reaching or hand lifting is identified using classifiers trained with motion-related EEG features. For this purpose, neural network and k-nearest neighbor classifiers are used. Then, elbow motion and hand endpoint motion is estimated using a different set of neural-network-based classifiers, which are trained with motion information recorded using healthy subjects. The predictions from the classifiers are compared with residual limb motion to generate a final prediction of motion intention. This can then be used to realize multi-DoF control of a prosthesis. The experimental results show the feasibility of the proposed method for multi-DoF control of a transhumeral prosthesis. This proof of concept study was performed with healthy subjects.