基于多传感器信息检测和融合的中国手语识别研究

有效融合加速计、摄像头和表面肌电3种低成本传感器在手势动作信息捕获上的优势,是提高手语手势识别率和种类的霞要研究内容.提出一种基于多传感器信息检测和融合的中国手语识别方法:先利用表面肌电的幅值信息,对3类传感器信号进行手势分割,并实现单双手词的划分;然后借助视觉信号,完成有遮挡和无遮挡双手词的划分;最后利用Sugeno模糊积分,实现不同特征匹配结果的决策融合.结果表明,对4位受试者、201个高频手语词开展于势识别实验,其识别率均在99%以上,证明该基于多传感器信息检测和融合的手势识别方法在中国手语识别上的有效性.     

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。     

基于小波变换的肌肉疲劳表面肌电信号特征提取的研究

当前肌肉疲劳表面肌电信号(surface electromgography,sEMG)特征提取方法,忽略了非线性跳错信号的影响,且不能在非平稳状态下进行特征提取,存在特征提取准确度差的问题。提出基于小波变换的肌肉疲劳sEMG特征提取研究,采用小波变换对所采集的样本去噪,结合时域、频域特征分析法,融合傅里叶变换方法对肌电信号中的线性特征进行提取,根据带谱近似熵理论对非线性挑错信号进行特征回归分析,并利用拟态分解函数和希尔伯特变换法对肌电信号进行时频特征的整合提取,最终完成基于小波变换的肌肉疲劳sEMG特征提取研究。实验验证,所提方法具有可行性,且将1000个肌电信号样本分成5组,对其中的跳错信号进行特征提取,所提方法准确度较文献方法高出75%,在非平稳状态下将200个肌电信号样本分成5组进行特征提取,所提方法准确度较文献方法高出33%。由此得出,所提方法优于当前特征提取方法。     

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。     

一种基于加速度与表面肌电信息融合和统计语言模型的连续手语识别方法

加速计(ACC)和表面肌电(SEMG)传感器是两种有效轻便的手势捕获设备.本研究提出一种采用多级决策树融合ACC和SEMG信息识别手语词根,并引入统计语言模型进行词根接续判断和错误纠正的中国手语连续语句识别方法.对包含有120个词根的200组连续中国手语句子展开的识别实验结果表明,该方法可以有效的从连续信号中识别出词根序列,120个手语词根全局平均识别率接近95%,句子识别率接近90%,采用纠错模型的方法与未采用纠错模型相比,词根的平均识别率提高了4%左右,句子识别率提高了10%.这种结合模式识别和自然语言处理的手语识别方法在连续手语识别和人机交互领域有着广阔的应用前景.     

基于BP神经网络的手势动作表面肌电信号的模式识别

手势语言在日常生活中有着广泛的应用,本研究利用手势动作时从前臂4块肌肉上获取的4路表面肌电（SEMG）信号,经特征提取并采用BP神经网络,对8种手势动作模式进行了识别。鉴于BP网络具有较强的模式分类能力,而特征提取（幅度绝对值均值、AR模型系数、过零率）又利用了多路肌电信号的信息,实验结果取得了较高的识别正确率,表明所采用的方法是有效的。     

基于BP神经网络的手势动作表面肌电信号的模式识别

手势语言在日常生活中有着广泛的应用,本研究利用手势动作时从前臂4块肌肉上获取的4路表面肌电(SEMG)信号,经特征提取并采用BP神经网络,对8种手势动作模式进行了识别.鉴于BP网络具有较强的模式分类能力,而特征提取(幅度绝对值均值、AR模型系数、过零率)又利用了多路肌电信号的信息,实验结果取得了较高的识别正确率,表明所采用的方法是有效的.     

基于表面肌电信号的性别差异性手势识别

对于同一手势不同性别的表面肌电信号差异性较大。为了减小差异性,提出滑动平均能量与能量补偿相结合的方法。本实验共采集10种手势动作的表面肌电信号;利用滑动平均能量对活动段进行检测,并对女性的动作段进行能量补偿;小波包分解采用Db4、Bior3.2、Haar、Sys8、Dmey这5种小波函数提取特征;最后并通过粒子群优化支持向量机进行分类。结果分析表明,能量补偿增大了特征的辨识度,减小了性别差异性,提高了手势识别率。     

表面肌电信号的分析和特征提取

背景:表面肌电信号的检测与分析对临床诊断人体功能状况以及患者康复具有重要意义。目的:对表面肌电信号的采集、信号处理、特征分析和特征值提取方面进行分析。方法:在人体屈伸肘部的过程中,选取人体上肢4块肌肉(肱三头肌,肘肌,肱二头肌,肱桡肌)分别检测表面肌电信号,对表面肌电信号进行陷波和带通滤波等预处理(优化)。在此基础上分析表面肌电信号的特征,并应用不同的特征值提取方法对优化后的表面肌电信号进行了特征提取。结果与结论:时域方法最早应用于肌电信号分析,易提取、方法简单;频域方法提取的特征值较稳定,使得频域方法成为肌电信号处理技术的主流;以小波变换为代表的时-频分析方法因结合了时域、频域两方法的特性,在肌电信号分析方面颇有潜力。     

基于经验模态分解-小波包变换的表面肌电信号手势识别

为了提高表面肌电信号（sEMG）手部运动识别的正确率,比较常规的sEMG预处理和特征提取方法,提出一种基于经验模态分解（EMD）和小波包变换（WPT）的sEMG手势识别模型。首先,使用EMD方法将sEMG进行平稳化,得到一系列的固有模态函数。其次,求取各个固有模态函数与原始信号的相关性,选取相关性较高的前4个分量作为有效分量。然后,采用Db3小波函数进行WPT,提取小波包系数中的平均能量、平均绝对值、最大值、均方根和方差等特征。分别采用线性判别分析和支持向量机对12种手部运动进行模式识别。结果表明基于EMD和WPT的sEMG手势识别正确率比直接提取小波包系数中的特征识别正确率高。     

Intramuscular EMG signal decomposition

Information regarding motor unit potentials (MUPs) and motor unit fi ring patterns during muscle contractions is useful for physiological investigation and clinical examinations either for the understanding of motor control or for the diagnosis of neuromuscular disorders. In order to obtain such information, composite electromyographic (EMG) signals are decomposed (i.e., resolved into their constituent motor unit potential trains [MUPTs]). The goals of automatic decomposition techniques are to create a MUPT for each motor unit that contributed significant MUPs to the original composite signal. Diagnosis can then be facilitated by decomposing a needle-detected EMG signal, extracting features of MUPTs, and finally analyzing the extracted features (i.e., quantitative electromyography). Herein, the concepts of EMG signals and EMG signal decomposition techniques are explained. The steps involved with the decomposition of an EMG signal and the methods developed for each step, along with their strengths and limitations, are discussed and compared. Finally, methods developed to evaluate decomposition algorithms and assess the validity of the obtained MUPTs are reviewed and evaluated.     

基于脑肌电融合的混合脑机接口研究

动作模式识别是脑机接口技术的核心内容之一。针对目前脑机接口动作识别模式单一、识别率低等问题,基于混合脑机接口思想,提出一种脑电和肌电特征融合策略,可实现单侧肢体不同动作模式的有效分类,进而可用于脑机接口技术。同步采集9名健康受试者单侧手腕屈/伸两种动作模式下的脑电信号和表面肌电信号,分别提取脑电信号事件相关去同步化特征和表面肌电信号的积分肌电值特征,构建基于支持向量机和粒子群优化算法的脑肌电融合及运动模式识别模型,通过调整“特征融合系数”来实现动作模式最优分类,从而提高模式识别的准确率;进一步通过递降健康人的肌电信号幅值来模拟患者和运动疲劳状态下的肌电信号,验证所提出方法对动作模式识别的有效性。实验结果表明,基于脑肌电融合特征的动作模式识别率(98%)比单纯依靠脑电特征的识别率(73%)提高25%;在运动疲劳状态下,基于脑肌电融合特征的识别率稳定在80%以上,比单纯依靠肌电特征的识别率提高14%。可见,脑肌电融合策略能提高动作模式识别的准确性和鲁棒性,为混合脑机接口技术提供条件。     

基于经验公式的连续手势动作表面肌电信号识别方法

目的实现连续手势动作表面肌电信号（surface electromyography,sEMG）的简单有效识别。方法首先推导出测试信号属于手势动作模板的概率密度经验公式,通过数据处理实验确定公式参数,最后设计连续手势识别实验以测试该经验公式用于动作sEMG识别的效果。结果推导出的经验公式在连续手势识别中获得了较好的识别结果,验证了该经验公式用于连续手势动作sEMG信号识别的有效性。结论基于经验公式的方法为实现基于sEMG信号的连续手势识别提供了一种可行的解决方案。     

Wiener filtering of surface EMG with a priori SNR estimation toward myoelectric control for neurological injury patients

Voluntary surface electromyogram (EMG) signals from neurological injury patients are often corrupted by involuntary background interference or spikes, imposing difficulties for myoelectric control. We present a novel framework to suppress involuntary background spikes during voluntary surface EMG recordings. The framework applies a Wiener filter to restore voluntary surface EMG signals based on tracking a priori signal to noise ratio (SNR) by using the decision-directed method. Semi-synthetic surface EMG signals contaminated by different levels of involuntary background spikes were constructed from a database of surface EMG recordings in a group of spinal cord injury subjects. After the processing, the onset detection of voluntary muscle activity was significantly improved against involuntary background spikes. The magnitude of voluntary surface EMG signals can also be reliably estimated for myoelectric control purpose. Compared with the previous sample entropy analysis for suppressing involuntary background spikes, the proposed framework is characterized by quick and simple implementation, making it more suitable for application in a myoelectric control system toward neurological injury rehabilitation.     

基于改进小波阈值算法的ECG肌电信号去噪研究

为了解决传统软、硬阈值算法对肌电信号去噪后心电图（ECG）信号幅值降低和存在局部异常尖峰,导致去噪效果较差的问题。通过研究小波阈值算法的去噪原理和优化规则,基于双曲正切函数构造出一种具有连续性、结构简单、灵活性较高的可调阈值函数和改进的分层阈值,并分析得到小波分解含噪ECG信号的最佳小波基函数和分解层数,提出了一种改进的小波阈值算法。将软、硬阈值算法、相关文献中的阈值算法和本文所提改进阈值算法对含有真实肌电信号噪声的ECG信号进行去噪对比研究。实验结果表明：本文改进阈值算法能较好地去除ECG信号中的肌电信号噪声,并能更好地保持ECG信号波形特征,且Pearson相关系数值大于其他阈值算法。定性和定量结果表明,本文所提改进阈值算法对ECG肌电信号噪声具有较好的去噪效果。     

基于表面肌电信号和动作捕捉的上肢运动疲劳分析EI北大核心CSCD

目前,上肢运动的疲劳状态监测,一般单纯依赖表面肌电信号(sEMG)对疲劳进行识别和分类,导致结果不稳定,存在一定局限。为此,本文将sEMG信号识别与动作捕捉技术引入到疲劳状态监测过程中,提出了一种融合改进的肌电疲劳阈值算法与生物力学分析的疲劳分析方法。本研究通过右上肢负载屈肘试验,同步采集肱二头肌sEMG信号与上肢动作捕捉数据,并同时运用柏格(Borg)疲劳度主观自觉量表记录受试者疲劳感受。然后,将融合改进的肌电疲劳阈值算法和生物力学分析的疲劳分析方法与平均功率频率(MPF)、谱矩比(SMR)、模糊近似熵(fApEn)、Lempel-Ziv复杂度(LZC)四种单一评价指标疲劳评价方法的试验结果进行对比。试验结果表明,本文方法对总体疲劳状态识别率结果达到98.6%,对轻松、过渡、疲劳三种状态的识别率分别达到97%、100%、99%,较其他方法更有优势。本文研究结果证明,本文方法在上肢运动过程中能够有效预防过度训练引起的二次损伤,对于疲劳监护具有重要意义。     

大腿截肢患者的残肢肌电运动识别

目的研究利用大腿残肢肌电信号进行下肢运动模式识别的方法,探讨肌电信号控制下肢假肢的可能性。方法采集15名大腿截肢者残肢侧股直肌、股外侧肌、阔筋膜张肌、股二头肌、半腱肌、臀大肌6块肌肉的表面肌电信号,提取肌电信号的6种时域、频域特征,利用支持向量机对平地行走、上楼梯、下楼梯、坐下、起立5种下肢运动模式进行识别。结果利用残肢肌电信号可以实现5种下肢运动模式的在线识别,对同一受试者同次测试数据识别率为94%,同一受试者的多次混合数据识别率为85%,对不同受试者混合数据识别率为74%。通过特征优化,仅利用3块肌肉的2个特征,对同一受试者的同次测试数据识别率仍可达92%。对平地行走、上楼梯、下楼梯3种动作的识别,同一受试者同次测试数据识别率为100%,同一受试者的多次混合数据识别率为98.33%,对不同受试者混合数据识别率为93.33%。结论仅仅利用残肢肌电信号能够实现运动意图的在线识别,通过对同一患者使用前的多次数据训练,有望达到较高的识别率。研究结果为肌电运动识别用于下肢假肢控制奠定了基础。     

Spatio-spectral filters for low-density surface electromyographic signal classification

In this paper, we proposed to utilize a novel spatio-spectral filter, common spatio-spectral pattern (CSSP), to improve the classification accuracy in identifying intended motions based on low-density surface electromyography (EMG). Five able-bodied subjects and a transradial amputee participated in an experiment of eight-task wrist and hand motion recognition. Low-density (six channels) surface EMG signals were collected on forearms. Since surface EMG signals are contaminated by large amount of noises from various sources, the performance of the conventional time-domain feature extraction method is limited. The CSSP method is a classification-oriented optimal spatio-spectral filter, which is capable of separating discriminative information from noise and, thus, leads to better classification accuracy. The substantially improved classification accuracy of the CSSP method over the time-domain and other methods is observed in all five able-bodied subjects and verified via the cross-validation. The CSSP method can also achieve better classification accuracy in the amputee, which shows its potential use for functional prosthetic control.     

Chaotic analysis of electromyography signal at low back and lower limb muscles during forward bending posture

The present study aims to perform further investigation on muscular activity during forward bending posture by applying a nonlinear dynamic (chaotic) analysis method. The objective is to determine the characteristics of the low back and lower limb muscle electromyography (EMG) signal under chaotic analysis while maintaining a certain posture. Twelve subjects were asked to maintain postures of six stages in bending angles from 0 to 180 degrees, and the EMG signals of erector spinae (ES) at L1 and L5 levels, hamstrings, and gastrocnemius were recorded. Two important concepts to characterize deterministic chaos, Correlation Dimension (D2) and Lyapunov Exponents (lambda, LE), were applied to observe the chaotic characteristic of the EMG signals, and the results were also compared to the FFT based total power value. The EMG signals in all observed muscles during bending posture showed results of positive LE and high D2 at 5.5 to 7.5, which led us to classify EMG as a high dimension chaotic signal. The result obtained showed that the correlation dimension could be used as a reliable method to compare the EMG signal in various postures (or muscle contraction conditions). However, Lyapunov exponents did not show a significant difference of comparison result thus leading to the conclusion that LE could not be a reliable measure for high dimension chaotic system, such as an EMG signal. It was also shown that in both light and deep bending, the EMG signal of the low back muscles was of the same complexity level due to the D2 result. It was evident that somehow the low back muscle remained loaded in all bending stages which was contrary to the hypothesis that the low back muscle was less active during the deep bending, as was the case in most of the previous studies. The reason of such phenomenon was elucidated with use of the theory of muscular functional differentiation, including corticalization and spinalization.