基于GA-RBF神经网络和sEMG的下肢动作识别方法研究

为了提高人体肌电信号对于下肢动作识别的准确率,提出一种基于遗传算法(GA)优化的径向基(RBF)神经网络分类模型.通过采集人体日常8种下肢动作的表面肌电信号并选择"sym6"系小波函数对肌电信号进行滤波预处理,使用主成分分析法(PCA)对时频域特征降维,把特征向量输入GA算法优化的RBF神经网络进行训练和识别.实验结果...     

基于小波包熵的与动作相关表面肌电信号的分类

目的:对与动作相关的表面肌电信号进行分类识别.材料与方法:与动作相关的表面肌电信号是从右手前臂肌群表面采集而来.用小波包变换将信号分解成16个等频带宽的的子空间.之后,计算每个子空间的相对小波包能量和每个信号的小波包熵.结果:正确识别率达到100%.结论:小波包熵能够作为与动作相关的表面肌电信号的特征值来识别不同的动作表面肌电模式.     

基于灰色系统理论的表面肌电分类

为提高假肢分类的准确率和速度 ,提出采用灰色系统理论中的灰关联法进行动作辨识。首先用小波变换方法对表面肌电信号进行分析 ,通过对小波系数奇异值分解提取信号特征 ,根据待分类动作与各标准动作模式间特征矢量的灰关联系数做出判断。从掌长肌和肱桡肌采集的两道表面肌电信号中识别四种运动模式 ,准确率达87.5 %。与神经网络等识别方法相比 ,此方法不需大量训练样本数量 ,运算量小 ,在识别率相近的情况下 ,辨识速度大大提高。     

基于最佳小波包的表面肌电信号分类方法

针对表面肌电信号的分类问题，采用最佳小波包分解构造最能体现分类能力的小波包基。用Fisher线性判别分析对肌电信号各个子空间的相对能量特征进行降维处理，然后利用BP神经网络进行分类识别。实验表明该方法能够有效地从伸肌和屈肌采集的两道肌电信号中识别前臂内旋、前臂外旋、握拳和展拳四种运动模式，是一种稳定、有效的特征提取方法，为非平稳生理信号的分析提供了新的手段。     

基于肌电信号的人手运动状态的辨识

研究的目的在于利用人体前臂的肌电信号进行人手动作模式的识别。根据采集的肌电信号，判断动作始末状态并对该肌电信号进行小波降噪预处理，利用小波变换的高频细节系数极值构造特征矢量，经过学习矢量量化（LVQ）神经网络训练，能够有效地识别握拳、展拳、手腕内旋和手腕外旋4种动作模式。和前馈型神经网络比较，LVQ神经网络具有更高的识别准确率和更稳定的再现性。     

小波变换在表面肌电信号分类中的应用

针对肌电信号的非平稳特性,采用小波变换方法对表面肌电信号进行分析。通过奇异值分解有效地提取信号特征进行模式识别,能够成功地从掌长肌和肱桡肌采集的两道表面肌电信号中识别展拳、握拳、前臂摧旋、前壁外旋四种运动模式。实验表明,基于小波变换的奇异值分解方法是一种稳定、有效的特征提取方法、为非平稳生理信号的分析提供了新的手段。     

一种基于表面肌电信号映射人体下肢运动意图的方法

智能膝关节假肢是截肢患者恢复日常运动的重要辅具。对人体下肢运动意图的识别是实现下肢假肢控制的关键。该文针对此问题,提出了一种通过表面肌电信号预测膝关节角度的方法。对表面肌电提取时域特征,通过 BP 神经网络模型建立平地行走过程中表面肌电信号和膝关节角度的映射关系,预测膝关节角度。     

采集表面肌电信号应用于动作识别的可行性

背景：文献表明上肢前臂运动时所产生的表面肌电信号具有非线性特征,而肢体运动时肌电信号又呈现出非平稳特性。 目的：设计一种简单的拾取电路采集表面肌电信号,拟应用于动作肌电信号的特征识别。 方法：根据表面肌电信号的特点,设计高共模抑制比的前端放大电路,抑制共模干扰;采用低通滤波电路,有源双T带阻滤波器对信号进行去噪处理;对采集得到的信号进行小波包变换,得到信号的特征量。 结果与结论：所设计的表面肌电信号检测电路具有较高共模抑制比,并能有效地滤除50 Hz工频信号,可以满足肌电信号采集电路的基本要求。肌电信号的处理结果表明采用子频段能量值的方法可以区分手部4种不同动作。     

引入关联维的表面肌电信号的特征提取

考虑到表面肌电信号的非平稳特性,本研究在传统特征提取的基础上,又引入了非线性动力学中的关联维,通过小波系数的标准差和关联维重新构造特征向量,将其送入自组织映射网络对拇指弯曲、食指弯曲和无名指弯曲三种手势动作进行分类识别。结果表明:引入关联维的特征提取方法其识别正确率明显优于传统的小波变换的方法。可见,关联维作为一种新的特征参数,为肌电信号的特征提取提供了新的思路。     

基于改进人工蜂群优化与组合特征提取的手部运动意图识别

为了解决表面肌电信号混迭导致的手部运动意图识别率较低的问题,提出了一种基于改进的人工蜂群优化盲源有序分离算法。本算法以表面肌电信号的规范四阶累积量作为代价函数,使用改进的人工蜂群优化算法代替传统的梯度算法对代价函数进行优化,并以代价函数绝对值的降序逐次提取出源信号;对于肌电信号的非平稳性及易受干扰的问题,采用一种基于小波包变换和样本熵的特征提取方法,并与表征肌电信号细节和强度的特征峰度、偏度、肌电积分值组合构建特征向量,训练二叉树支持向量机分类器。实验结果表明,采用表面肌电信号的盲源分离预处理与组合特征提取的方法识别六种手部运动意图,平均准确率达到93. 33%。     

小波变换和非线性分析在表面肌电信号中的应用及进展

表面肌电信号(surface EMG,sEMG)反映了神经和肌肉的功能和生理状态,分析研究sEMG对人类的生理健康有重要的意义.本文综述了小波变换和非线性分析方法近几年在sEMG研究中的应用情况,并且预测两种方法的有效结合在sEMG的应用前景.     

基于熵的动态收缩sEMG信号疲劳特征分析

频谱分析方法常被用来检测肌肉疲劳过程。本文将频率分析和非线性动力学方法结合起来，基于表面肌电（sEMG）信号在不同频率分布不均匀的特点将信号能量分解到不同频带。以此计算功率谱／小波包和熵相结合的功率谱熵／小波包熵来衡虽系统的复杂度，进而衡量肌肉的疲劳程度，为用EMG信号研究动态收缩过程中的肌肉疲劳程度提供了新的分析手段和方法。文中方法也适用于萁它生物医学信号的分析。     

基于小波系数熵的表面肌电信号识别

目的:对表面肌电信号进行分类识别。方法:30名健康的志愿者参加数据采集。每名志愿者用右手臂完成两个动作:前臂内旋和前臂外旋。在每个动作中,采集一组表面EMG信号。总共获得30组内旋和30组外旋的表面EMG信号。然后,运用小波包系数熵构成特征向量,用Bayes决策对两种模式信号进行分类识别。结果:当信号长度达350ms后,正确识别率达到100%。结论:采用小波包系数熵可以有效地提取表面EMG信号的特征信息,达到控制前臂假肢的目的。     

A Study on sEMG Simulation Modeling and Its Decomposition Methods

In this paper, we establish a surface electromyography(sEMG) signal model and study the signal decomposition method from noisy background. Firstly, single fiber action potential (SFAP), motor unit action potential (MUAP) and motor unit action potential train(MUAPT) are simulated based on the tripolar signal source model, and then the sEMG is obtained; secondly, the simulated sEMG signal is extracted from the mixed signals that consists of white noises, power frequency interference signal and electrocardio signal by independent component analysis (ICA) algorithms; lastly, the spikes corresponding to each motor unit action potential from the simulated sEMG signals were detected by applying the wavelet transform (WT) method. Simulation results showed that sEMG model could describe the physiological process of sEMG, ICA and WT methods could extract the sEMG signal and its features, which will lay a foundation for further classifying the MUAP.     

基于非线性尺度小波变换的表面肌电信号的分类

表面肌电信号（Surface EMG,sEMG）是一种复杂的非线性非平稳信号。我们介绍了一种非线性尺度小波变换（Wavelet transform with nonlinear scale，NWT）。由于NWT具有渐进缩短时间分辨率的特点．所以有利于从sEMG信号获得精确的时一频信息。首先，用NWT将sEMG信号（30组前臂内旋和30组外旋的sEMG信号）变换为强度分布（时频分布）．然后，用由主成分分析获得的强度分布特征值构成特征向量．最后，用BP神经网络对两种信号模式的特征向量进行分类识别。结果表明：与两种传统的时频分析方法相比，NWT能够获得较高的正确识别率．同时降低了神经网络计算的复杂度。     

The application of Hilbert�CHuang transform in the analysis of muscle fatigue during cyclic dynamic contractions

Surface electromyography (sEMG) is a common technique used in the assessment of local muscle fatigue. As opposed to static contraction situations, sEMG recordings during dynamic contractions are particularly characterised by non-stationary (and non-linear) features. Standard signal processing methods using Fourier and wavelet based procedures demonstrate well known restrictions on time-frequency resolution and the ability to process non-stationary and/or non-linear time-series, thus aggravating the spectral parameters estimation. The Hilbert-Huang transform (HHT), comprising of the empirical mode decomposition (EMD) and Hilbert spectral analysis (HSA), provides a new approach to overcome these issues. The time-dependent median frequency estimate is used as muscle fatigue indicator, and linear regression parameters are derived as fatigue quantifiers. The HHT method is utilised for the analysis of the sEMG signals recorded over quadriceps muscles during cyclic dynamic contractions. The results are compared with those obtained by the Fourier and wavelet based methods. It is shown that HHT procedure provides the most consistent and reliable assessment of spectral and derived linear regression parameters, given the time epoch width and sampling interval in the time domain. The suggested procedure successfully deals with non-stationary and non-linear properties of biomedical signals.     

Ant colony optimization-based feature selection method for surface electromyography signals classification

This paper presented a new ant colony optimization (ACO) feature selection method to classify hand motion surface electromyography (sEMG) signals. The multiple channels of sEMG recordings make the dimensionality of sEMG feature grow dramatically. It is known that the informative feature subset with small size is a precondition for the accurate and computationally efficient classification strategy. Therefore, this study proposed an ACO based feature selection scheme using the heuristic information measured by the minimum redundancy maximum relevance criterion (ACO-mRMR). The experiments were conducted on ten subjects with eight upper limb motions. Two feature sets, i.e., time domain features combined with autoregressive model coefficients (TDAR) and wavelet transform (WT) features, were extracted from the recorded sEMG signals. The average classification accuracies of using ACO reduced TDAR and WT features were 95.45±2.2% and 96.08±3.3%, respectively. The principal component analysis (PCA) was also conducted on the same data sets for comparison. The average classification accuracies of using PCA reduced TDAR and WT features were 91.51±4.9% and 89.87±4.4%, respectively. The results demonstrated that the proposed ACO-mRMR based feature selection method can achieve considerably high classification rates in sEMG motion classification task and be applicable to other biomedical signals pattern analysis.     

Evolved pseudo-wavelet function to optimally decompose sEMG for automated classification of localized muscle fatigue

The purpose of this study was to develop an algorithm for automated muscle fatigue detection in sports related scenarios. Surface electromyography (sEMG) of the biceps muscle was recorded from ten subjects performing semi-isometric (i.e., attempted isometric) contraction until fatigue. For training and testing purposes, the signals were labelled in two classes (Non-Fatigue and Fatigue), with the labelling being determined by a fuzzy classifier using elbow angle and its standard deviation as inputs. A genetic algorithm was used for evolving a pseudo-wavelet function for optimising the detection of muscle fatigue on any unseen sEMG signals. Tuning of the generalised evolved pseudo-wavelet function was based on the decomposition of twenty sEMG trials. After completing twenty independent pseudo-wavelet evolution runs, the best run was selected and then tested on ten previously unseen sEMG trials to measure the classification performance. Results show that an evolved pseudo-wavelet improved the classification of muscle fatigue between 7.31% and 13.15% when compared to other wavelet functions, giving an average correct classification of 88.41%.     

用于脑瘫儿下肢康复装置的表面肌电信号特征提取方法研究

采用时域、频域、时频域和熵的特征提取方法,找到适合脑瘫儿表面肌电信号的特征提取方法.通过在训练过程加一个阻力得到四个不同肌肉活性的训练阶段数据,对数据进行预处理和特征提取,然后用因子分析法对所提取的特征进行分析,实验结果显示本研究所提出的时域、时频域和熵特征部分适用于脑瘫儿,频域特征不适用于脑瘫儿.本研究结果对脑瘫儿的康复训练有很大的帮助.