Shuai Cao

Muscle Synergy Analysis in Children with Cerebral Palsy

OBJECTIVE To explore the mechanism of lower extremity dysfunction of cerebral palsy (CP) children through muscle synergy analysis. APPROACH Twelve CP children were involved in this study, ten adults (AD) and eight typically developed (TD) children were recruited as a control group. Surface electromyographic (sEMG) signals were collected bilaterally from eight lower limb muscles of the subjects during forward walking at a comfortable speed. A nonnegative matrix factorization algorithm was used to extract muscle synergies. In view of muscle synergy differences in number, structure and symmetry, a model named synergy comprehensive assessment (SCA) was proposed to quantify the abnormality of muscle synergies. MAIN RESULTS There existed larger variations between the muscle synergies of the CP group and the AD group in contrast with the TD group. Fewer mature synergies were recruited in the CP group, and many abnormal synergies specific to the CP group appeared. Specifically, CP children were found to recruit muscle synergies with a larger difference in structure and symmetry between two legs of one subject and different subjects. The proposed SCA scale demonstrated its great potential to quantitatively assess the lower-limb motor dysfunction of CP children. SCA scores of the CP group (57.00 ± 16.78) were found to be significantly less (p < 0.01) than that of the control group (AD group: 95.74 ± 2.04; TD group: 84.19 ± 11.76). SIGNIFICANCE The innovative quantitative results of this study can help us to better understand muscle synergy abnormality in CP children, which is related to their motor dysfunction and even the physiological change in their nervous system.

Random Forest-Based Recognition of Isolated Sign Language Subwords Using Data from Accelerometers and Surface Electromyographic Sensors

Sign language recognition (SLR) has been widely used for communication amongst the hearing-impaired and non-verbal community. This paper proposes an accurate and robust SLR framework using an improved decision tree as the base classifier of random forests. This framework was used to recognize Chinese sign language subwords using recordings from a pair of portable devices worn on both arms consisting of accelerometers (ACC) and surface electromyography (sEMG) sensors. The experimental results demonstrated the validity of the proposed random forest-based method for recognition of Chinese sign language (CSL) subwords. With the proposed method, 98.25% average accuracy was obtained for the classification of a list of 121 frequently used CSL subwords. Moreover, the random forests method demonstrated a superior performance in resisting the impact of bad training samples. When the proportion of bad samples in the training set reached 50%, the recognition error rate of the random forest-based method was only 10.67%, while that of a single decision tree adopted in our previous work was almost 27.5%. Our study offers a practical way of realizing a robust and wearable EMG-ACC-based SLR systems.

Development of an EMG-ACC-Based Upper Limb Rehabilitation Training System

This paper focuses on the development of an upper limb rehabilitation training system designed for use by children with cerebral palsy (CP). It attempts to meet the requirements of in-home training by taking advantage of the combination of portable accelerometers (ACC) and surface electromyography (SEMG) sensors worn on the upper limb to capture functional movements. In the proposed system, the EMG-ACC acquisition device works essentially as wireless game controller, and three rehabilitation games were designed for improving upper limb motor function under a clinician’s guidance. The games were developed on the Android platform based on a physical engine called Box2D. The results of a system performance test demonstrated that the developed games can respond to the upper limb actions within 210 ms. Positive questionnaire feedbacks from twenty CP subjects who participated in the game test verified both the feasibility and usability of the system. Results of a long-term game training conducted with three CP subjects demonstrated that CP patients could improve in their game performance through repetitive training, and persistent training was needed to improve and enhance the rehabilitation effect. According to our experimental results, the novel multi-feedback SEMG-ACC-based user interface improved the users’ initiative and performance in rehabilitation training.

Muscle-tendon units localization and activation level analysis based on high-density surface EMG array and NMF algorithm.

OBJECTIVE Some skeletal muscles can be subdivided into smaller segments called muscle-tendon units (MTUs). The purpose of this paper is to propose a framework to locate the active region of the corresponding MTUs within a single skeletal muscle and to analyze the activation level varieties of different MTUs during a dynamic motion task. APPROACH Biceps brachii and gastrocnemius were selected as targeted muscles and three dynamic motion tasks were designed and studied. Eight healthy male subjects participated in the data collection experiments, and 128-channel surface electromyographic (sEMG) signals were collected with a high-density sEMG electrode grid (a grid consists of 8 rows and 16 columns). Then the sEMG envelopes matrix was factorized into a matrix of weighting vectors and a matrix of time-varying coefficients by nonnegative matrix factorization algorithm. MAIN RESULTS The experimental results demonstrated that the weightings vectors, which represent invariant pattern of muscle activity across all channels, could be used to estimate the location of MTUs and the time-varying coefficients could be used to depict the variation of MTUs activation level during dynamic motion task. SIGNIFICANCE The proposed method provides one way to analyze in-depth the functional state of MTUs during dynamic tasks and thus can be employed on multiple noteworthy sEMG-based applications such as muscle force estimation, muscle fatigue research and the control of myoelectric prostheses.

An isometric muscle force estimation framework based on a high-density surface EMG array and an NMF algorithm.

OBJECTIVE To realize accurate muscle force estimation, a novel framework is proposed in this paper which can extract the input of the prediction model from the appropriate activation area of the skeletal muscle. APPROACH Surface electromyographic (sEMG) signals from the biceps brachii muscle during isometric elbow flexion were collected with a high-density (HD) electrode grid (128 channels) and the external force at three contraction levels was measured at the wrist synchronously. The sEMG envelope matrix was factorized into a matrix of basis vectors with each column representing an activation pattern and a matrix of time-varying coefficients by a nonnegative matrix factorization (NMF) algorithm. The activation pattern with the highest activation intensity, which was defined as the sum of the absolute values of the time-varying coefficient curve, was considered as the major activation pattern, and its channels with high weighting factors were selected to extract the input activation signal of a force estimation model based on the polynomial fitting technique. MAIN RESULTS Compared with conventional methods using the whole channels of the grid, the proposed method could significantly improve the quality of force estimation and reduce the electrode number. SIGNIFICANCE The proposed method provides a way to find proper electrode placement for force estimation, which can be further employed in muscle heterogeneity analysis, myoelectric prostheses and the control of exoskeleton devices.

Assessment of Upper Limb Motor Dysfunction for Children with Cerebral Palsy Based on Muscle Synergy Analysis

Muscle synergies are considered to be building blocks underlying motor behaviors. The goal of this study is to explore an objective and effective method to assess the upper limb motor dysfunction of cerebral palsy (CP) children from the aspect of muscle synergy analysis. Fourteen CP children and 10 typically developed (TD) children were recruited to perform three similar upper limb motion tasks related to the movements of elbow and shoulder joints, and surface electromyographic (sEMG) signals were recorded from 10 upper arm and shoulder muscles involved in the defined tasks. Non-negative matrix factorization algorithm was used to extract muscle synergies and the corresponding activation patterns during three similar tasks. For each subject in TD group, four muscle synergies were extracted in each task. Whereas, fewer mature synergies were recruited in CP group, and many abnormal synergy structures specific to CP group appeared. In view of neuromuscular control strategy differences, three synergy-related parameters were proposed and synergy structure similarity coefficient was found to have high ability in depicting the inter-subject similarity within task and the intra-subject similarity between tasks. Seven upper limb assessment (UPA) metrics, which were defined as the combinations of synergy structure similarity coefficients of three tasks, were proposed to assess the upper limb motor function of CP children. The experimental results demonstrated that these UPA metrics were able to assess upper limb motor function comprehensively and effectively. The proposed assessment method can serve as a promising approach to quantify the abnormality of muscle synergies, thus offering potential to derive a physiologically based quantitative index for assessing upper limb motor function in CP clinical diagnosis and rehabilitation.

A Component-Based Vocabulary-Extensible Sign Language Gesture Recognition Framework

Sign language recognition (SLR) can provide a helpful tool for the communication between the deaf and the external world. This paper proposed a component-based vocabulary extensible SLR framework using data from surface electromyographic (sEMG) sensors, accelerometers (ACC), and gyroscopes (GYRO). In this framework, a sign word was considered to be a combination of five common sign components, including hand shape, axis, orientation, rotation, and trajectory, and sign classification was implemented based on the recognition of five components. Especially, the proposed SLR framework consisted of two major parts. The first part was to obtain the component-based form of sign gestures and establish the code table of target sign gesture set using data from a reference subject. In the second part, which was designed for new users, component classifiers were trained using a training set suggested by the reference subject and the classification of unknown gestures was performed with a code matching method. Five subjects participated in this study and recognition experiments under different size of training sets were implemented on a target gesture set consisting of 110 frequently-used Chinese Sign Language (CSL) sign words. The experimental results demonstrated that the proposed framework can realize large-scale gesture set recognition with a small-scale training set. With the smallest training sets (containing about one-third gestures of the target gesture set) suggested by two reference subjects, (82.6 ± 13.2)% and (79.7 ± 13.4)% average recognition accuracy were obtained for 110 words respectively, and the average recognition accuracy climbed up to (88 ± 13.7)% and (86.3 ± 13.7)% when the training set included 50~60 gestures (about half of the target gesture set). The proposed framework can significantly reduce the user’s training burden in large-scale gesture recognition, which will facilitate the implementation of a practical SLR system.

Myoelectric Pattern Recognition Based on Muscle Synergies for Simultaneous Control of Dexterous Finger Movements

Motor activities during daily life always involve simultaneous control of multiple degrees of freedom (DOFs), which has not yet been fully explored in myoelectric control due to difficulty in sufficiently decoding the complex neural control information. This study presents a novel framework for simultaneous myoelectric control based on pattern recognition incorporated with a muscle synergy motor control strategy for each DOF. An experiment for discriminating 18 dexterous finger movement tasks was designed to evaluate the performance of the framework for the simultaneous control of 5 DOFs. Task discrimination was assessed with 18 neurologically intact subjects, and the framework exhibited high accuracy (96.79% ±2.46%), outperforming three other methods, including the routine myoelectric pattern-recognition approach for conventional sequential control (p<0.001). Furthermore, the feasibility of the proposed framework is also demonstrated with data from paretic muscles of two stroke subjects. This study offers a feasible solution for simultaneous myoelectric control of multiple DOFs, which has great potential for natural implementation in prosthetic hand devices and robotic training systems, especially for dexterous finger movements.

Two New Shrinking-Circle Methods for Source Localization Based on TDoA Measurements

Time difference of arrival (TDoA) measurement is a promising approach for target localization based on a set of nodes with known positions, with high accuracy and low complexity. Common localization algorithms include the maximum-likelihood, non-linear least-squares and weighted least-squares methods. These methods have shortcomings such as high computational complexity, requiring an initial guess position, or having difficulty in finding the optimal solution. From the point of view of geometrical analysis, this study proposes two new shrinking-circle methods (SC-1 and SC-2) to solve the TDoA-based localization problem in a two-dimensional (2-D) space. In both methods, an optimal radius is obtained by shrinking the radius with a dichotomy algorithm, and the position of the target is determined by the optimal radius. The difference of the two methods is that a distance parameter is defined in SC-1, while an error function is introduced in SC-2 to guide the localization procedure. Simulations and indoor-localization experiments based on acoustic transducers were conducted to compare the performance differences between the proposed methods, algorithms based on weighted least-squares as well as the conventional shrinking-circle method. The experimental results demonstrate that the proposed methods can realize high-precision target localization based on TDoA measurements using three nodes, and have the advantages of speed and high robustness.

ICA-based muscle–tendon units localization and activation analysis during dynamic motion tasks

This study proposed an independent component analysis (ICA)-based framework for localization and activation level analysis of muscle–tendon units (MTUs) within skeletal muscles during dynamic motion. The gastrocnemius muscle and extensor digitorum communis were selected as target muscles. High-density electrode arrays were used to record surface electromyographic (sEMG) data of the targeted muscles during dynamic motion tasks. First, the ICA algorithm was used to decompose multi-channel sEMG data into a weight coefficient matrix and a source matrix. Then, the source signal matrix was analyzed to determine EMG sources and noise sources. The weight coefficient vectors corresponding to the EMG sources were mapped to target muscles to find the location of the MTUs. Meanwhile, the activation level changes in MTUs during dynamic motion tasks were analyzed based on the corresponding EMG source signals. Eight subjects were recruited for this study, and the experimental results verified the feasibility and practicality of the proposed ICA-based method for the MTUs’ localization and activation level analysis during dynamic motion. This study provided a new, in-depth way to analyze the functional state of MTUs during dynamic tasks and laid a solid foundation for MTU-based accurate muscle force estimation, muscle fatigue prediction, neuromuscular control characteristic analysis, etc.