Real time motion intention recognition method with limited number of surface electromyography sensors for A 7-DOF hand/wrist rehabilitation exoskeleton

The functions of human hand are rich, and the motor dysfunction of hand of chronic stroke patients can be alleviated to some extent through active rehabilitation training. Hand rehabilitation exoskeleton can assist patients to do active rehabilitation training. However, how to realize more motion with less surface electromyogrphy (sEMG) sensors, and how to realize the real-time motion intention recognition are two important issues. This paper introduces real-time motion intention recognition method with limited number of sEMG sensors for a 7-DOF wearable hand/wrist rehabilitation exoskeleton to realize the real-time motion intention recognition and rehabilitation training. Root mean square (RMS) and Bens Spiker Algorithm (BSA) features of three-channel sEMG signals are extracted, and they are mapped to seven different intention movements by combining the Bagging method. The finger structure part of the exoskeleton is composed of a rotary-spatial-spatial-rotary (RSSR) mechanism and a double-parallelogram mechanism, which makes the projection center of exoskeleton coincide with the rotation center of the hand joint. The average real-time motion intention recognition accuracy is 95.37 ± 0.97%.     

Spatial filtering for robust myoelectric control

Pattern recognition techniques have been applied to extract information from electromyographic (EMG) signals that can be used to control electrical powered hand prostheses. In this paper, optimized spatial filters that enhance separation properties of EMG signals are investigated. In particular, different multiclass extensions of the common spatial patterns algorithm are applied to high-density surface EMG signals acquired from the forearms of ten healthy subjects. Visualization of the obtained filter coefficients provides insight into the physiology of the muscles related to the performed contractions. The CSP methods are compared with a commonly used pattern recognition approach in a six-class classification task. Cross-validation results show a significant improvement in performance and a higher robustness against noise than commonly used pattern recognition methods.     

Adaptive fuzzy impedance control of exoskeleton robots with electromyography-based convolutional neural networks for human intended trajectory estimation

Among various uses of exoskeleton robots, the rehabilitation of stroke patients is a more recent application. There is, however, considerable environmental uncertainty in such systems including uncertain robot dynamics, unwanted user reflexes, and, most importantly, uncertainty in user intended trajectory. Hence, it is challenging to develop transparent, stable, and wide-scale exoskeleton robots for rehabilitation. This paper proposes an adaptive fuzzy impedance controller (AFIC) and a convolutional neural network (CNN) which uses electromyographic (EMG) signals for early detection of human intention and better integration with a lower limb exoskeleton robot. Specifically, the primary purpose of the AFIC is to manage the mechanical interaction between human, robot, and environment and to deal with uncertainties in internal control parameters. CNN uses EMG signals, inertial measurement units, foot force sensing resistors, joint angular sensors, and load cells to deal with signal uncertainties and noise through automatic feature processing in order to detect user’s desired joint angles with high accuracy. EMG is particularly effective here since it reflects the human intention to move faster than the other mechanical sensors. In the experimental procedure, signals were sampled at 500 Hz as two healthy individuals walked normally at 0.3, 0.4, 0.5, and 0.6 m/s for eight minutes while wearing a robot with zero inertia. Approximately 70% of the data is used for training and 30% for testing the network. The estimated angle from the trained network is then used as the desired angle in the AFIC loop, which controls the robot online as the desired trajectory. Pearson correlation coefficient and normalized root mean square error are computed to evaluate the accuracy and robustness of the proposed angle estimation with CNN and AFIC algorithms. Experimental results show that the proposed approach successfully obtains the torque of the robot joints despite uncertainties in changing the walking speed.     

Bio-driven system-based virtual reality for prosthetic and rehabilitation systems

Current prosthetic and rehabilitation devices, used for those who are limbless or born with congenital defects or required rehabilitation, are difficult to use. The users have problems to adapt to their new hosts or receiving any bio-feedback despite rehabilitation process and retraining, particularly when working with electromyogram (EMG) signals. In characterizing virtual human limbs, as a potential prosthetic device in three dimensions (3D) virtual reality, patients are able to familiarize themselves with their new appendage and its capabilities or can see their movements’ intention in a Virtual Training Environment. This paper presents a virtual reality (VR)-based design and implementation of a below-shoulder 3D human arm capable of 10-class EMG-based motions driven system of biomedical EMG signal. The method considers a signal classification output as potential control stimulus to drive the virtual limb. A hierarchical design methodology is adopted based on anatomical structure to congruent with virtual reality modeling language (VRML) architecture used in order to progressively build the user interface model and its inherent functionality. The resulting simulation is based on a portable, self-contained VRML prototype implementation paired with an instrumental virtual control-select board capable of actuating any combinations of singular or paired kinematic of 10-class EMG motions. The simulation allows for multiple degree-of-freedom profiles as the classes can be activated independently, or in conjunction with others, allowing enhanced arm movement. Provisions for direct classified control inputs are built into the prototype for holistic system construction.     

Decomposition of multiunit electromyographic signals

We have developed a comprehensive technique to identify single motor unit (SMU) potentials and to decompose overlapped electromyographic (EMG) signals into their constituent SMU potentials. This technique is based on one-channel EMG recordings and is easily implemented for many clinical EMG tests. There are several distinct features of our technique: 1) it measures waveform similarity of SMU potentials in the wavelet domain, which gives this technique significant advantages over other techniques; 2) it classifies spikes based on the nearest neighboring algorithm, which is less sensitive to waveform variation; 3) it can effectively separate compound potentials based on a maximum signal energy deduction algorithm, which is fast and relatively reliable; and 4) it also utilizes the information on discharge regularities of SMU's to help correct possible decomposition errors. The performance of this technique has been evaluated by using simulated EMG signals composed of up to eight different discharging SMU's corrupted with white noise, and also by using real EMG signals recorded at levels up to 50% maximum voluntary contraction. We believe that it is a very useful technique to study SMU discharge patterns and recruitment of motor units in patients with neuromuscular disorders in clinical EMG laboratories.     

5-Link model based gait trajectory adaption control strategies of the gait rehabilitation exoskeleton for post-stroke patients

Many 4-DOF exoskeleton type robot devices have been widely developed for the gait rehabilitation of post-stroke patients. However, most systems run with purely position control not allowing voluntary active movements of the subject. The lack of intelligent control strategies for variable gait patterns has been a clinical concern of such kind exoskeleton man–machine systems. In this work, we establish a 5-link model for the usual 4-DOF gait rehabilitation exoskeleton type man–machine system and propose a gait trajectory adaption control strategy. A 4-DOF gait rehabilitation exoskeleton prototype is developed as a platform for the evaluation of design concepts and control strategies in the view of improved physical human–robot interaction. The experimental results with eight healthy volunteers and three stroke patients are encouraging.     

A Supervised Feature-Projection-Based Real-Time EMG Pattern Recognition for Multifunction Myoelectric Hand Control

Electromyographic (EMG) pattern recognition is essential for the control of a multifunction myoelectric hand. The main goal of this study was to develop an efficient feature- projection method for EMG pattern recognition. To this end, a linear supervised feature projection is proposed that utilizes a linear discriminant analysis (LDA). First, a wavelet packet transform (WPT) is performed to extract a feature vector from four-channel EMG signals. To dimensionally reduce and cluster the WPT features, an LDA, then, incorporates class information into the learning procedure, and identifies a linear matrix to maximize the class separability for the projected features. Finally, a multilayer perceptron classifies the LDA-reduced features into nine hand motions. To evaluate the performance of the LDA for WPT features, the LDA is compared with three other feature-projection methods. From a visualization and quantitative comparison, it is shown that the LDA produces a better performance for the class separability, plus the LDA-projected features improve the classification accuracy with a short processing time. A real-time pattern-recognition system is then implemented for a multifunction myoelectric hand. Experiments show that the proposed method achieves a 97.4% recognition accuracy, and all processes, including the generation of control commands for the myoelectric hand, are completed within 97 ms. Consequently, these results confirm that the proposed method is applicable to real-time EMG pattern recognition for multifunction myoelectric hand control.     

Event driven sliding mode control of a lower limb exoskeleton based on a continuous neural network electromyographic signal classifier

This study presents an event driven automatic controller to regulate the movement of a mobile lower limb active orthosis (LLAO) triggered with the information obtained from electromyographic (EMG) signals, which are captured from the user’s triceps and biceps muscles. The proposed controller has an output feedback realization including a velocity estimator algorithm based on a high order sliding mode observer. The output feedback controller implements a class of decentralized super-twisting algorithm. The controller must enforce the movement of the orthosis articulations following some defined reference trajectories. This strategy realizes a time-window dependent event driven controller for the active orthosis. The controller selects among four different routines to be executed by a patient. A differential neural network classifies the different patterns of muscle movements. This classifier succeeds in defining the correct EMG class in a 95% of the tested signals. This work senses the EMG signals from the biceps and triceps, considering a possible injury in the patient to be obtained from the quadriceps. Therefore, four upper limb routines are established to generate the corresponding classes and the four different main therapies for the LLAO. A fully instrumented and self-designed orthosis is constructed to evaluate the proposed controller including three rotational joints per leg and a mobile robot to execute translation movements.     

Characterization of EMG Patterns From Proximal Arm Muscles During Object- and Orientation-Specific Grasps

Reach-to-grasp tasks are composed of several actions that are more and more considered as simultaneously controlled by the central nervous system in a feedforward manner (at least for well-known activities). If this hypothesis is correct, during prehension tasks, the activity of proximal muscles (and not only of the distal ones used to control finger movements) is modulated according to the kind of object to be grasped and its position. This means that different objects could be identified by processing the electromyographic (EMG) signals recorded from proximal muscles. In this paper, specific experiments have been carried out to support this hypothesis in able-bodied subjects. The results achieved seem to confirm this possibility by showing that the activation of proximal muscles can be statistically different for different grip types. This finding supports the hypothesis that proximal and distal muscles are simultaneously controlled during reaching and grasping. Moreover, this kind of information could allow the development of an EMG-based control strategy based on the natural muscular activities selected by the central nervous system.     

Gait phase information provided by sensory nerve activity duringwalking: applicability as state controller feedback for FES

In this study, we extracted gait-phase information from natural sensory nerve signals of primarily cutaneous origin recorded in the forelimbs of cats during walking on a motorized treadmill. Nerve signals were recorded in seven cats using nerve cuff or patch electrodes chronically implanted on the median, ulnar, and/or radial nerves. Features in the electroneurograms that were related to paw contact and lift-off were extracted by threshold detection. For four cats, a state controller model used information from two nerves (either median and radial, or ulnar and radial) to predict the timing of palmaris longus activity during walking. When fixed thresholds were used across a variety of walking conditions, the model predicted the timing of EMG activity with a high degree of accuracy (average error = 7.8%, standard deviation = 3.0%, n = 14). When thresholds were optimized for each condition, predictions were further improved (average error = 5.5%, standard deviation = 2.3%, n = 14). The overall accuracy with which EMG timing information could be predicted using signals from two cutaneous nerves for two constant walking speeds and three treadmill inclinations for four cats suggests that natural sensory signals may be implemented as a reliable source of feedback for closed-loop control of functional electrical stimulation (FES).     

A Wearable Biomechatronic Interface for Controlling Robots with Voluntary Foot Movements

This paper presents an experimental investigation on a novel interface for high level control of mechatronic systems, by exploiting voluntary user's foot movements. Based on a biomechanical analysis of the foot anatomy and joint kinematics, a sensory system is designed for detecting pressure variations on selected areas of the insole, obtained from four different foot movements that can be purposively controlled by the person. A prototype is developed that integrates four sensitive areas, battery, and electronics into a wearable insole; electronics are used for data acquisition and wireless transmission, in order to have a stand-alone device. The prototype foot interface is experimentally tested in the control of a prosthetic hand, as a model of a typical device that can be effectively operated by foot movements. Experimental trials were conducted with ten able-bodied subjects and the results confirmed the usability and effectiveness of the foot interface in terms of correct and prompt transmission of the user's intention to the controlled device. Comparative experimental trials were performed with electromyography (EMG)-based control of the same prosthesis, which represents the most advanced interface currently available in clinical implants for amputees. The comparative results showed a significant decrease in required adaptation and learning from the user's side     

基于表面肌电信号的截肢者人手动作模式识别

基于表面肌电信号(sEMG)的手部动作模式识别技术已被广泛研究,它在健全的受试者中有良好的分类性能.但对于截肢者的日常使用,其性能还需进一步研究.本文对截肢者进行了10天的肌电信号采集,调查了截肢者对于不同动作的分类性能.模仿实际应用条件,取时域特征为支持向量机(SVM)的输入,对截肢者的双侧手臂进行手部动作识别,结果...     

Bayesian network modeling for discovering "dependent synergies" among muscles in reaching movements

The coordinated activities of muscles during reaching movements can be characterized by appropriate analysis of simultaneously-recorded surface electromyograms (sEMGs). Many recent sEMG studies have analyzed muscle synergies using statistical methods such as Independent Component Analysis, which commonly assume a small set of influences upstream of the muscles (e.g., originating from the motor cortex) produce the sEMG signals. Traditionally only the amplitude of the sEMG signal was investigated. Here, we present a fundamentally different approach and model sEMG signals after the effects of amplitude have been minimized. We develop the framework of Bayesian networks (BNs) for modeling muscle activities and for analyzing the overall muscle network structure. Instead of assuming that synergies may be independently activated, we assume that neuronal activity driving a given muscle may be conditionally dependent upon neurons driving other muscles. We call the resulting interactions between muscle activity patterns "dependent synergies". The learned BN networks were explored for the purpose of classification across subjects based on hand dominance or affliction by stroke. Network structure features were investigated as classification input features and it was determined that specific edge connection patterns of 3-node subnetworks were selectively recruited during reaching movements and were differentially recruited after stroke compared to normal control subjects. The resulting classification was robust to inter-subject and within-group variability and yielded excellent classification performance. The proposed framework extends muscle synergy analysis and provides a framework for thinking about muscle activity interactions in motor control.     

改进BP神经网络的EMG手指运动识别

在基于肌电信号(EMG)手指运动的模式识别中,稳定性和识别率是两个主要问题,为此提出了一种新的EMG模式识别算法。该算法采用现代信号处理理论中的AR模型和改进的BP神经网络相结合的算法,有效的解决了BP网络识别中落入局部极值问题。进行试验,将提取到的特征值输入MATLAB建立一个改进多层BP神经网络,识别三个不同类型的手指运动。实验表明,改进BP算法较传统BP算法获得了更高的识别精度,达到94%左右。     

Assessment of average muscle fiber conduction velocity from surface EMG signals during fatiguing dynamic contractions

In this paper, we propose techniques of surface electromyographic (EMG) signal detection and processing for the assessment of muscle fiber conduction velocity (CV) during dynamic contractions involving fast movements. The main objectives of the study are: 1) to present multielectrode EMG detection systems specifically designed for dynamic conditions (in particular, for CV estimation); 2) to propose a novel multichannel CV estimation method for application to short EMG signal bursts; and 3) to validate on experimental signals different choices of the processing parameters. Linear adhesive arrays of electrodes are presented for multichannel surface EMG detection during movement. A new multichannel CV estimation algorithm is proposed. The algorithm provides maximum likelihood estimation of CV from a set of surface EMG signals with a window limiting the time interval in which the mean square error (mse) between aligned signals is minimized. The minimization of the windowed mse function is performed in the frequency domain, without limitation in time resolution and with an iterative computationally efficient procedure. The method proposed is applied to signals detected from the vastus laterialis and vastus medialis muscles during cycling at 60 cycles/min. Ten subjects were investigated during a 4-min cycling task. The method provided reliable assessment of muscle fatigue for these subjects during dynamic contractions.     

On the intersubject generalization ability in extracting kinematic information from afferent nervous signals

In the recent past, many efforts have been carried out in order to evaluate the feasibility of implementing closed-loop controlled neuroprostheses based on the processing of sensory electroneurographic (ENG) signals. The success of these techniques mostly relies on the development of processing algorithms capable of extracting the necessary kinematic information from these signals. Soft-computing algorithms can be very useful when dealing with the complexity of the neuromuscular system because of their generalization ability and model-free structure. In this paper, these techniques were used to extract angular position information from the ENG signals recorded from muscle afferents in animal model using cuff electrodes. Specifically, a genetic algorithm-based dynamic nonsingleton fuzzy logic system (named GA-DNSFLS) was developed and tested on different types of angular trajectories (characterized by small or large angular excursions). In particular, two different Takagi-Sugeno-Kang (TSK)-like structures were used in the consequent part of the neuro-fuzzy model in order to verify which one could improve the generalization abilities (intrasubject and intersubject). The results showed that the GA-DNSFLS was able to reconstruct the trajectories giving interesting results in terms of correlation between the actual and the predicted trajectories for small excursion movements during intrasubject and intersubject tests. Particularly, one of the TSK models showed better results in terms of intersubject generalization. The simulations conducted with the large excursion movements led in some cases to interesting results but further experiments are necessary in order to analyze this point more in deep.     

Extracting Simultaneous and Proportional Neural Control Information for Multiple-DOF Prostheses From the Surface Electromyographic Signal

A novel signal processing algorithm for the surface electromyogram (EMG) is proposed to extract simultaneous and proportional control information for multiple DOFs. The algorithm is based on a generative model for the surface EMG. The model assumes that synergistic muscles share spinal neural drives, which correspond to the intended activations of different DOFs of natural movements and are embedded within the surface EMG. A DOF-wise nonnegative matrix factorization (NMF) is developed to estimate neural control information from the multichannel surface EMG. It is shown, both by simulation and experimental studies, that the proposed algorithm is able to extract the multidimensional control information simultaneously. A direct application of the proposed method would be providing simultaneous and proportional control of multifunction myoelectric prostheses.      

Biodegradable Shape-Memory Ionogels as Green and Adaptive Wearable Electronics Toward Physical Rehabilitation

Rehabilitation is necessary for the recovery of patients with paralysis caused by stroke and muscle atrophy. Wearable electronics can provide feedback on physical training and facilitate healthcare. However, most existing wearable electronics are difficult to maintain a conformal skin-device interface. Additionally, the use of non-degradable electronic materials is associated with environmental risks. Herein, ionogels with biodegradation and shape-memory properties as eco-friendly and geometry-adaptive wearable electronics for rehabilitation are proposed. The biodegradation is enabled by incorporating polycaprolactone segments into the ionogel matrix. Moreover, the ionogel-based wearable electronics can be conformal to certain joints by shape programming, and provide stable and reproducible real-time signals reflecting joint movements during long-term rehabilitation training assisted by a robotic glove, facilitating carers to assess rehabilitation efficacy and choose an appropriate scheme. This study demonstrates the potential of biodegradable shape-memory ionogels as green and adaptive wearable electronics for robot-assisted rehabilitation.     

EMG and EPP-integrated human-machine interface between the paralyzed and rehabilitation exoskeleton

Although a lower extremity exoskeleton shows great prospect in the rehabilitation of the lower limb, it has not yet been widely applied to the clinical rehabilitation of the paralyzed. This is partly caused by insufficient information interactions between the paralyzed and existing exoskeleton that cannot meet the requirements of harmonious control. In this research, a bidirectional human-machine interface including a neurofuzzy controller and an extended physiological proprioception (EPP) feedback system is developed by imitating the biological closed-loop control system of human body. The neurofuzzy controller is built to decode human motion in advance by the fusion of the fuzzy electromyographic signals reflecting human motion intention and the precise proprioception providing joint angular feedback information. It transmits control information from human to exoskeleton, while the EPP feedback system based on haptic stimuli transmits motion information of the exoskeleton back to the human. Joint angle and torque information are transmitted in the form of air pressure to the human body. The real-time bidirectional human-machine interface can help a patient with lower limb paralysis to control the exoskeleton with his/her healthy side and simultaneously perceive motion on the paralyzed side by EPP. The interface rebuilds a closed-loop motion control system for paralyzed patients and realizes harmonious control of the human-machine system.     

肌电生物反馈法康复治疗仪的设计

设计并研发一种通过肌电生物反馈法重建人体神经网络系统的医疗仪器,为神经肌肉系统类疾病患者的全面康复提供一种新的治疗平台.治疗仪由硬件电路和PC机控制软件两部分构成,下位机（MCU）包括体表肌电采集放大电路、神经肌肉电刺激电路两大部分;上位机（PC）的软件系统主要负责视觉信号反馈,治疗参数控制、病历登记、信息查询等功能.治疗仪达到了国家的医用康复治疗的各项指标,能够帮助患者逐步康复,且具有安全、无创、便捷、人机交互能力强等特点.