Functional assessment is an essential part of rehabilitation protocols after stroke. Conventionally, the assessment process relies heavily on clinical experience and lacks quantitative analysis. In order to objectively quantify the upper-limb motor impairments in patients with post-stroke hemiparesis, this study proposes a novel assessment approach based on motor synergy quantification and multi-modality fusion. Fifteen post-stroke hemiparetic patients and fifteen age-matched healthy persons participated in this study. During different goal-directed tasks, kinematic data and surface electromyography (sEMG) signals were synchronously collected from these participants, and then motor features extracted from each modal data can be fed into the respective local classifiers. In addition, kinematic synergies and muscle synergies were quantified by principal component analysis (PCA) and k weighted angular similarity (kWAS) algorithm to provide in-depth analysis of the coactivated features responsible for observable movement impairments. By integrating the outputs of local classifiers and the quantification results of motor synergies, ensemble classifiers can be created to generate quantitative assessment for different modalities separately. In order to further exploit the complementarity between the evaluation results at kinematic and muscular levels, a multi-modal fusion scheme was developed to comprehensively analyze the upper-limb motor function and generate a probability-based function score. Under the proposed assessment framework, three types of machine learning methods were employed to search the optimal performance of each classifier. Experimental results demonstrated that the classification accuracy was respectively improved by 4.86% and 2.78% when the analysis of kinematic and muscle synergies was embedded in the assessment system, and can be further enhanced to 96.06% by fusing the characteristics derived from different modalities. Furthermore, the assessment result of multi-modality fusion framework exhibited a significant correlation with the score of standard clinical tests (R= –0.87, P=1.98e–5). These promising results show the feasibility of applying the proposed method to clinical assessments for post-stroke hemiparetic patients.

Robot-assisted rehabilitation has been a promising solution to improve motor learning of neurologically impaired patients. State-of-the-art control strategies are typically limited to the ignorance of heterogeneous motor capabilities of poststroke patients and therefore intervene suboptimally. In this article, we propose a control framework for robot-assisted motor learning, emphasizing the detection of human intention, generation of reference trajectories, and modification of robotic assistance. A real-time trajectory generation algorithm is presented to extract the high-level features in active arm movements using an adaptive frequency oscillator (AFO) and then integrate the movement rhythm with the minimum-jerk principle to generate an optimal reference trajectory, which synchronizes with the motion intention in the patient as well as the motion pattern in healthy humans. In addition, a subject-adaptive assistance modification algorithm is presented to model the patient’s residual motor capabilities employing spatially dependent radial basis function (RBF) networks and then combining the RBF-based feedforward controller with the impedance feedback controller to provide only necessary assistance while simultaneously regulating the maximum-tolerated error during trajectory tracking tasks. We conduct simulation and experimental studies based on an upper limb rehabilitation robot to evaluate the overall performance of the motor-learning framework. A series of results showed that the difficulty level of reference trajectories was modulated to meet the requirements of subjects’ intended motion, furthermore, the robotic assistance was compliantly optimized in response to the changing performance of subjects’ motor abilities, highlighting the potential of adopting our framework into clinical application to promote patient-led motor learning.

Introduction: During electroencephalography (EEG)-based motor imagery-brain-computer interfaces (MI-BCIs) task, a large number of electrodes are commonly used, and consume much computational resources. Therefore, channel selection is crucial while ensuring classification accuracy.Methods: This paper proposes a channel selection method by integrating the efficient channel attention (ECA) module with a convolutional neural network (CNN). During model training process, the ECA module automatically assigns the channel weights by evaluating the relative importance for BCI classification accuracy of every channel. Then a ranking of EEG channel importance can be established so as to select an appropriate number of channels to form a channel subset from the ranking. In this paper, the ECA module is embedded into a commonly used network for MI, and comparative experiments are conducted on the BCI Competition IV dataset 2a.Results and discussion: The proposed method achieved an average accuracy of 75.76% with all 22 channels and 69.52% with eight channels in a four-class classification task, outperforming other state-of-the-art EEG channel selection methods. The result demonstrates that the proposed method provides an effective channel selection approach for EEG-based MI-BCI.

Spasticity is a common disabling complication caused by the upper motor neurons dysfunction following neurological diseases such as stroke. Currently, the assessment of the spastic hypertonia triggered by stretch reflexes is manually performed by clinicians using perception-based clinical scales, however, their reliability is still questionable due to the inter-rater and intra-rater variability. In order to objectively quantify the complex spasticity phenomenon in post-stroke patients, this study proposed a multi-layer assessment system based on a novel measurement device. The exoskeletal device was developed to synchronously record the kinematic, biomechanical and electrophysiological information in sixteen spastic patients and ten age-matched healthy subjects, while the spastic limb was stretched at low, moderate and high velocities. The mechanical impedance of the elbow joint was identified using a modified genetic algorithm to quantify the alterations in viscoelastic properties underlying pathological resistance. Simultaneously, the time-frequency features were extracted from the surface electromyography (sEMG) signals to reveal the neurophysiological mechanisms of the spastic muscles. By concatenating these single-layer decisions, a support vector regression (SVR)-based fusion model was developed to generate a more comprehensive quantification of spasticity severity. Experimental results demonstrated that the stiffness and damping components of the spastic arm significantly deviated from the nonspastic baseline, and strong correlations were observed between the proposed spasticity assessment and the severity level measured by clinical scales ( ${R = {0.86},\;{P} = {1.67}{e} - {5}}$ ), as well as the tonic stretch reflex threshold (TSRT) value ( ${R = - {0.89},\;{P} = {3.54}{e} - {6}}$ ). These promising results suggest that the proposed assessment system holds great potential to support the clinical diagnosis of motor abnormalities in spastic patients, and ultimately enables optimal adjustment of treatment protocols.

Parkinson’s disease (PD) is the second most common neurodegenerative disorder and the heterogeneity of early PD leads to inter-rater and intra-rater variability in observation-based clinical assessment. Thus, objective monitoring of PD-induced motor abnormalities has attracted significant attention to manage disease progression. Here, we proposed a hierarchical architecture to reliably detect abnormal characteristics and comprehensively quantify the multi-symptom severity in patients with PD. A novel wearable device was designed to measure motor features in fifteen PD patients and fifteen age-matched healthy subjects, while performing five types of motor tasks. The abnormality classes of multi-modal measurements were recognized by hidden Markov models (HMMs) in the first layer of the proposed architecture, aiming at motivating the evaluation of specific motor manifestations. Subsequently, in the second layer, three single-symptom models differentiated PD motor characteristics from normal motion patterns and quantified the severity of cardinal PD symptoms in parallel. In order to further analyze the disease status, the multi-level severity quantification was fused in the third layer, where machine learning algorithms were adopted to develop a multi-symptom severity score. Experimental results demonstrated that the quantification of three cardinal symptoms were highly accurate to distinguish PD patients from healthy controls. Furthermore, strong correlations were observed between the Unified Parkinson’s Disease Rating Scale (UPDRS) scores and the predicted sub-scores for tremor (R=0.75, P=1.40e-3), bradykinesia (R=0.71, P=2.80e-3) and coordination impairments (R=0.69, P=4.20e-3), and the correlation coefficient can be enhanced to 0.88 (P=1.26e-5) based on the fusion schemes. In conclusion, the proposed assessment architecture holds great promise to push forward the in-home monitoring of clinical manifestations, thus enabling the self-assessment of disease progression.

With the rapid development of intelligent mining technology, remote operated underground inspection and rescue robot have been widely used. This paper recognized the operator’s emergency gestures basing on forearm sEMG. First, a wireless 6-channel sEMG acquisition device is built and a date set named CMMG (coal Mine Inspection Manipulator Gestures) is acquired, then the features of each channel signal are extracted to a two-dimensional graph by continue wavelet transform method. The multi-stream CNN model is built to analyze the feature graphs so as to detect action segments. The comparative experiments showed that the method improved the accuracy, showed better performance on both the CMMG dataset and public Ninapro DB1 dataset.