基于sEMG的手指康复治疗的信号处理研究

手指功能在日常生活中特别重要,特别是在一些需要抓取和一些较为精细的动作中,对日常生活质量有着不可忽视的影响。而目前临床针对手指功能康复的治疗模式主要采用辅助设备康复,而这种模式又较为枯燥。提出了一种通过采集表面肌电信号(sEMG)的方式,使得手指功能受损的患者可以脱离现有比较枯燥的治疗方式,同时也更有利于患者其他功能例如神经系统功能的恢复。采用肌电信号公开数据集,对原始肌电信号做相关的预处理,同时采用matlab仿真的方式验证预处理的正确性;并通过临床实验采集患者肌电信号的方式验证使用目前的肌电传感器对运动意图分析的可行性。

Pattern recognition of surface electromyography signal based on wavelet coefficient entropy

This paper introduced a novel, simple and ef-fective method to extract the general feature of two surface EMG (electromyography) signal patterns: forearm supination (FS) surface EMG signal and forearm pronation (FP) surface EMG signal. After surface EMG (SEMG) signal was decomposed to the fourth resolution level with wavelet packet transform (WPT), its whole scaling space (with frequencies in the interval (0Hz, 500Hz]) was divided into16 frequency bands (FB). Then wavelet coefficient entropy (WCE) of every FB was calculated and corre-spondingly marked with WCE(n) (from the nth FB, n=1,2,…16). Lastly, some WCE(n) were chosen to form WCE feature vector, which was used to distinguish FS surface EMG signals from FP surface EMG signals. The result showed that the WCE feather vector consisted of WCE(7) (187.25Hz, 218.75Hz) and WCE(8) (218.75Hz, 250Hz) can more effectively recog-nize FS and FP patterns than other WCE feature vector or the WPT feature vector which was gained by the combination of WPT and principal components analysis.

Characterization of surface EMG signals using improved approximate entropy

An improved approximate entropy (ApEn) is presented and applied to characterize surface electromyography (sEMG) signals. In most previous experiments using nonlinear dynamic analysis, this certain processing was often confronted with the problem of insufficient data points and noisy circumstances, which led to unsatisfactory results. Compared with fractal dimension as well as the standard ApEn, the improved ApEn can extract information underlying sEMG signals more efficiently and accu- rately. The method introduced here can also be applied to other medium-sized and noisy physiological signals.

一种基于sEMG信号多重分形的肌肉疲劳特征分析方法

针对由表面肌电信号(sEMG)非平稳、非线性、自相似性等复杂特性导致的肌肉疲劳估计不准的问题,提出一种基于sEMG信号多重分形降趋移动平均法(MFDMA)的肌肉疲劳特征分析方法。首先,利用MFDMA方法对采集的sEMG信号、洗牌信号和高斯白噪声信号进行非线性动力学分析;其次,利用MFDMA方法计算sEMG信号的多重分形谱宽度、Hurst指数变化差值、概率测度值和峰值奇异指数4种多重分形特征;最后,利用t-检验法分析肌肉疲劳与非疲劳状态下的多重分形特征的显著差异性。结果表明,MFDMA方法能够描述sEMG信号的多重分形行为,谱宽等多重分形特征在肌肉疲劳与非疲劳状态下具有显著性差异。所提方法能够可靠表征运动性肌肉疲劳,可为肌肉疲劳识别模型建构、康复医学研究提供特征参考。

Feature Layer Fusion of Linear Features and Empirical Mode Decomposition of Human EMG Signal

To explore the influence of the fusion of different features on recognition,this paper took the electromyography(EMG)signals of rectus femoris under different motions(walk,step,ramp,squat,and sitting)as samples,linear features(time-domain features(variance(VAR)and root mean square(RMS)),frequency-domain features(mean frequency(MF)and mean power frequency(MPF)),and nonlinear features(empirical mode decomposition(EMD))of the samples were extracted.Two feature fusion algorithms,the series splicing method and complex vector method,were designed,which were verified by a double hidden layer(BP)error back propagation neural network.Results show that with the increase of the types and complexity of feature fusions,the recognition rate of the EMG signal to actions is gradually improved.When the EMG signal is used in the series splicing method,the recognition rate of time-domain+frequency-domain+empirical mode decomposition(TD+FD+EMD)splicing is the highest,and the average recognition rate is 92.32%.And this rate is raised to 96.1%by using the complex vector method,and the variance of the BP system is also reduced.

基于ISSA-VMD和二代小波的sEMG信号降噪研究

表面肌电(sEMG)信号是一种可以有效表征肌肉活动的弱生理信号,采集过程中易受到多种噪声干扰。为解决变分模态分解(VMD)参数经验设置的问题,并进一步消除sEMG信号中的噪声,提出了一种基于改进麻雀算法(ISSA)优化VMD和二代小波阈值法相结合的sEMG信号降噪法。首先,采用基于改进T混沌映射、自适应权重和麻雀数目动态变化的改进麻雀算法并将品质因子作为目标函数对VMD进行参数寻优,然后利用ISSA优化的VMD分解对预处理过的sEMG信号进行分解,通过谱相关分析区分信号分量和噪声分量,最后对信号分量进行二代小波阈值法降噪,得到降噪信号。结果表明:ISSA较SSA有效提高了VMD参数寻优能力;在不同噪声等级下,基于ISSA-VMD和二代小波硬阈值的降噪法的降噪性能优于二代小波和ISSA-VMD;基于ISSA-VMD与二代小波硬阈值降噪法处理实际sEMG信号,能有效去除噪声。

Control method for exoskeleton ankle with surface electromyography signals

This paper is concerned with a control method for an exoskeleton ankle with electromyography （EMG） signals. The EMG signals of human ankle and the exoskeleton ankle are introduced. Then a control method is proposed to control the exoskeleton ankle using the EMG signals. The feed-forward neural network model applied here is composed of four layers and uses the back-propagation training algorithm. The output signals from neural network are processed by the wavelet transform. Finally the control orders generated from the output signals are passed to the motor controller and drive the exoskeleton to move. Through experiments, the equality of neural network prediction of ankle movement is evaluated by giving the correlation coefficient. It is shown from the experimental results that the proposed method can accurately control the movement of ankle joint.

Robot driving and arm gesture remote control using surface EMG with accelerometer signals

This paper proposes a method of remotely controlling robots with arm gestures using surface electromyography(EMG)and accelerometer sensors attached to the operator's wrists.The EMG and accelerometer sensors receive signals from the arm gestures of the operator and infer the corresponding movement to execute the command to control the robot.The movements of the robot include moving forward and backward and turning left and right.The forearm of the robot can be rotated up,down,left and right,and the robot can clench its fists.The accuracy is over 99% and movements can be controlled in real time.

基于sEMG和变刚度控制的虚拟假手交互系统

为使虚拟假手在交互时具有柔顺性,实现了一种基于表面肌电(sEMG)信号和变刚度控制的虚拟假手交互系统。首先,采集人体前臂的sEMG信号并从中估计人手的刚度水平和关节扭矩;然后,通过变刚度阻抗控制模型估计虚拟假手的关节角度;最后,使用估计的关节角度控制虚拟假手与虚拟环境中的物体进行交互,交互过程中根据虚拟假手与物体的交互力对关节角度进行动态调节。实验结果表明:基于sEMG和变刚度控制的虚拟假手在进行抓握物体的交互任务时能在成功抓握物体的前提下产生较小的交互力,从而实现柔顺的交互。

Classification of uterine EMG signals using supervised classification method

Aim: The main purpose of this article is to detect any risk of preterm deliveries at an early gestation period using uterine electromyography signals. Detecting such uterine signals can yield a promising approach to determine and take actions to prevent this potential risk. Methods: The best position for the detection of different uterine signals is the median vertical axis of the abdomen. These signals differ from each other by their frequency content. Initially, simulation is done for the real detected EMG signals: preterm deliveries (PD) EMGs and deliveries at term (DT) EMGs. This is performed by applying autoregressive model (AR) of specific order to estimate AR coefficients of these real EMG signals. Finally, after calculation of the AR parameters of the two types of deliveries, we generate two types of simulated uterine contractions by using White Gaussian Noise (WGN). Frequency parameter extraction and classification are first applied on simulated signals to test the limits and performance of the used methods. The last remaining step is the classification of the contractions using supervised classification method. Results: Results show that uterine contractions may be classified using the Artificial Neural Networks (ANNs). The Simple Perceptron ANN is applied on the signals for their supervised classification into independent groups: preterm deliveries (PD) and deliveries at term (TD) according to their frequency content.

Hand Gestures Recognition Based on One-Channel Surface EMG Signal

This paper presents an experiment using OPENBCI to collect data of two hand gestures and decoding the signal to distinguish gestures. The signal was extracted with three electrodes on the subiect’s forearm and transferred in one channel. After utilizing a Butterworth bandpass filter, we chose a novel way to detect gesture action segment. Instead of using moving average algorithm, which is based on the calculation of energy, We developed an algorithm based on the Hilbert transform to find a dynamic threshold and identified the action segment. Four features have been extracted from each activity section, generating feature vectors for classification. During the process of classification, we made a comparison between K-nearest-neighbors (KNN) and support vector machine (SVM), based on a relatively small amount of samples. Most common experiments are based on a large quantity of data to pursue a highly fitted model. But there are certain circumstances where we cannot obtain enough training data, so it makes the exploration of best method to do classification under small sample data imperative. Though KNN is known for its simplicity and practicability, it is a relatively time-consuming method. On the other hand, SVM has a better performance in terms of time requirement and recognition accuracy, due to its application of different Risk Minimization Principle. Experimental results show an average recognition rate for the SVM algorithm that is 1.25% higher than for KNN while SVM is 2.031 s shorter than that KNN.

Classification of surface EMG signal with fractal dimension

Surface EMG (electromyography) signal is a complex nonlinear signal with low signal to noise ratio (SNR). This paper is aimed at identifying different patterns of surface EMG signals according to fractal dimension. Two patterns of surface EMG signals are respectively acquired from the right forearm flexor of 30 healthy volunteers during right forearm supination (FS) or forearm pronation (FP). After the high frequency noise is filtered from surface EMG signal by a low-pass filter, fractal di-mension is calculated from the filtered surface EMG signal. The results showed that the fractal dimensions of filtered FS surface EMG signals and those of filtered FP surface EMG signals distribute in two different regions, so the fractal dimensions can rep-resent different patterns of surface EMG signals.

Finger Flexion Motion Inference from sEMG Signals

This paper provides a method to infer finger flexing motions using a 4-channel surface Electromyogram(sEMG).Surface EMGs are harmless to the human body and easily done.However,they do not reflect the activity of specific nerves or muscles,unlike invasive EMGs.On the other hand,the non-invasive type is difficult to use for discriminating various motions while using only a small number of electrodes.Surface EMG data in this study were obtained from four electrodes placed around the forearm.The motions were the flexion of each 5 single fingers(thumb,index finger,middle finger,ring finger,and little fingers).One subject was trained with these motions and another left was untrained.The maximum likelihood estimation method was used to infer the finger motion.Experimental results have showed that this method could be useful for recognizing finger motions.The average accuracy was as high as 95%.

The Change of Spectral Energy Distribution of Surface EMG Signal During Forearm Action Process

Spectral energy distribution of surface EMG signal is often used but difficultly and effectively control artificial limb, because the spectral energy distribution changes in the process of limb actions. In this paper, the general characteristics of surface EMG signal patterns were firstly characterized by spectral energy change. 13 healthy subjects were instructed to execute forearm supination (FS) and forearm pronation (FP) with their right forearms when their forearm muscles were “fatigue” or “relaxed”. All surface EMG signals were recorded from their right forearm flexor during their right forearm actions. Two sets of surface EMG signals were segmented from every surface EMG signal appropriately at preparing stage and acting stage. Relative wavelet packet energy (symbolized by pnp and pna respectively at preparing stage and acting stage, n denotes the nth frequency band) of surface EMG signal firstly was calculated and then, the difference (Pn=pna-pnp) were gained. The results showed that Pn from some frequency bands can effectively characterize the general characteristics of surface EMG signal patterns. Compared with Pn in other frequency bands, P4, the spectral energy change from 93.75 to 125 Hz, was more appropriately regarded as the features.

肌电信号控制的智能小车实验平台设计

肌电信号是人体肌群在运动时产生的一种微弱信号,该信号蕴藏着与运动相关的控制信息源。提出了一种基于肌电信号的智能小车控制系统。该系统由肌电信号采集模块、无线传输模块、小车控制模块和显示模块等组成。整个系统分为主从两部分。主机采用STM32F103ZET6微处理器对肌电信号进行多通道采集,提取所采集信号的特征值。将特征值分为测试集和训练集,并对不同手势信号贴上对应的标签,使用K最近邻(KNN)算法对测试集进行准确度分析以实现对不同手势的识别。识别结果通过无线传输模块发送给从机小车,小车接收到主机发送的内容后进行相应的动作。测试结果表明,所提出的方法在不同时间段信号采集的平均准确率可达91.14%以上,系统具有很好的鲁棒性。

融合表面肌电和姿势信息的轮椅绩效评价方法

目的为客观评价轮椅的使用效益,使用表面肌电设备测试轮椅使用过程中的肌电信号,并融合姿势信号IMU来构建人机评价模型。方法分别对轮椅的折叠、刹车方式及行驶坡度进行试验来评估轮椅的使用绩效,通过对比用力肌群间的疲劳状况来判定较为舒适的轮椅折叠及刹车方式。实验要求被试者在执行轮椅任务时,分别使用两种折叠方式和三种刹车方式不同的轮椅进行实验,并在操作动作任务过程中采集sEMG和IMU信号,在实验任务结束后填写NASA-TLX量表。结果根据模型的评价指标对实验数据进行了比较与分析,横向收折式折叠和凹口式刹车(手刹位于前方)的轮椅疲劳度低,在3~4°坡度范围下轮椅使用者的受力最小,较为舒适,从而验证了模型在轮椅人机评价上的可行性,为优化轮椅设计提供参考。结论人机评价模型适用于评估产品绩效,同时提出的融合表面肌电和姿势信息的轮椅绩效评价方法具有较高的精度和准确性,能够有效地评估轮椅使用者的绩效水平。

基于多模态轻量化混合模型的情绪识别

实现更加准确的情绪识别是当前面临的一项富含挑战性且十分有意义的任务。由于情绪的复杂多样性,单一模态的脑电信号难以对情绪进行全面客观的度量。因此本文提出一种多模态轻量化混合模型PCA-MWReliefFGAPSO-SVM,该混合模型由PCA-MWReliefF特征通道选择器和GAPSO-SVM分类器构成。选用脑电信号(EEG)、肌电信号(EMG)、体温信号(TEM)三模态信号进行情绪识别。在DEAP公共数据集上进行多次实验验证,在效价维度、唤醒维度和四分类中分别取得了97.5000%、95.8333%、95.8333%的分类准确率。实验结果表明,提出的混合模型有助于提高情绪识别准确率且明显优于单模态情绪识别。与近期的类似工作相比,本文提出的混合模型具有较高准确率、计算量小且通道数少的优点,更易于实际应用。

一种基于循环时空深度神经网络的手势识别方法

针对表面肌电信号解码模型因缺乏时空信息等重要性表征,面临解码精度低、鲁棒性差等问题,提出了一种基于循环时空深度神经网络的手势识别模型,来提高挖掘表面肌电信号的表征能力。首先,设计多通道卷积神经网络,并融入双向循环神经网络来提取强判别力的时空特征信息。其次,采用通道注意力机制来捕捉时空特征中通道重要性信息,设计基于时空特征的注意力模块以进一步增强时空特征信息。同时,基于特征金字塔网络思想来设计多尺度特征融合模块,从多尺度、多角度获取多级特征信息,提高模型对肌电信号的解码能力。最后,将所提出的手势识别模型在大型手势识别数据库Ninapro上进行测试,结果表明所提方法能有效提高对表面肌电信号的表征挖掘能力,为人体手势动作识别的深度学习建模工作提供借鉴意义。

基于表面肌电信号及肌肉疲劳的上肢肌力预测

为解决目前肌肉力测量时用肢体末端力表示实际肌肉力大小,以及未将肌肉疲劳程度考虑在内的问题,本文提出了一种基于表面肌电信号和肌肉疲劳的上肢肌肉力预测方法。利用AnyBody软件建立上肢肌肉骨骼模型,并将上肢末端力经过仿真得到单块肌肉的肌力大小;采用肌肉等长收缩的时间来表征肌肉疲劳程度。10名健康男性受试者进行上肢等长收缩实验,提取实验过程中肱二头肌肌电信号的积分肌电值、均方根、中值频率、平均功率频率、最大小波系数及其对应频率六个特征值;将肌肉力与特征值、肌肉疲劳程度进行分析后发现三者之间高度相关。采用麻雀搜索算法优化BP神经网络的权值和阈值,构造并训练上肢肌力预测模型。经测试集检验结果表明,该方法的误差小于12%,可以对肌力进行较为准确的预测。

表面肌电与三轴信息融合的运动判断实验

为了提高基于表面肌电与三轴加速度信号的运动识别准确率,提出了一套多源信息融合处理的实验流程与方法。该方法利用5层离散小波变换对表面肌电信号进行分解,充分提取不同运动产生的肌电信号中各频域的特征信息;再将分解后的表面肌电信号与三轴加速度信号通过滑动窗口的方法进行特征融合,构造融合肌电与空间运动特征的特征图;最后用融合特征图对深度学习模型进行训练,并结合自动状态机进行最终运动状态的识别。实验结果表明,多源信息融合处理方法可以提高运动识别的准确性,总体识别精度分别达到了95.4%和89.2%。该方法在实时性与准确性上均有良好表现。