应用小波变换和ICA方法的肌电信号分解

基于单通道、短时真实肌电（EMG）记录和模拟EMG信号，提出一种改进的肌电信号分解方法。首先应用小波滤波、硬阈值估计等方法去除背景噪声和白噪声，并将独立成分分析（ICA）方法和小波滤波方法相结合去除工频干扰信号，然后再进行幅度滤波，从而提高了系统的速度和强健性。在运动单元动作电位（MUAP）聚类以及从原始信号中去除已识别的MUAP波形等方面也进行了改进。与已有的EMG分解方法相比，本文方法更快速、稳定。     

Semi-supervised change detection using modified self-organizing feature map neural network

In the present article, semi-supervised learning is integrated with an unsupervised context-sensitive change detection technique based on modified self-organizing feature map (MSOFM) network. In the proposed methodology, training of the MSOFM network is initially performed using only a few labeled patterns. Thereafter, the membership values, in both the classes, for each unlabeled pattern are determined using the concept of fuzzy set theory. The soft class label for each of the unlabeled patterns is then estimated using the membership values of its K nearest neighbors. Here, training of the network using the unlabeled patterns along with a few labeled patterns is carried out iteratively. A heuristic method has been suggested to select some patterns from the unlabeled ones for training. To check the effectiveness of the proposed methodology, experiments are conducted on three multi-temporal and multi-spectral data sets. Performance of the proposed work is compared with that of two unsupervised techniques, a supervised technique and two semi-supervised techniques. Results are also statistically validated using paired t-test. The proposed method produced promising results.     

下肢表面肌电信号的降维和映射分析

肌电信号的采集和分析是外骨骼式康复机器人关节预测控制的重要基础之一.肌电信号数据量大并且复杂,相关性较高,信号处理通用性和高效性低,分析和预测人体运动信息误差大.采用最大自主等长收缩标准化处理算法,大大提高了表面肌电信号的通用性和泛化能力,并基于主成分分析方法,对肌电信号降维处理,利用神经网络实现与下肢的映射分析.实验结果表明,通过对比分析不同的降维处理方式,主成分降维后处理的肌电信号平均相关性达0.93,利用神经网络预测人体正常行走的下肢三关节运动角度,具有良好的可重复性和较高的精度,可以实现人体下肢肌电信号和各关节的映射控制.     

Dynamic muscle fatigue detection using self-organizing maps

Wavelets are used for the processing of signals that are non-stationary and time varying. The electromyogram (EMG) contains transient signals related to muscle activity. Wavelet coefficients are proposed as features for identifying muscle fatigue. By observing the approximation coefficients it is shown that their amplitude follows closely the muscle fatigue development. The proposed method for detecting fatigue is automated by using neural networks. The self-organizing map (SOM) has been used to visualize the variation of the approximation wavelet coefficients and aid the detection of muscle fatigue. The results show that a 2D SOM separates EMG signatures from fresh and fatigued muscles, thus providing a visualization of the onset of fatigue over time. The map is able to detect if muscles have recovered temporarily. The system is adaptable to different subjects and conditions since the techniques used are not subject or workload regime specific.     

Real-time gait subphase detection using an EMG signal graph matching (ESGM) algorithm based on EMG signals

This study presents a gait subphase recognition method using an electromyogram (EMG) with a signal graph matching (ESGM) algorithm. Existing pattern recognition and machine learning using EMG signals has several innate problems in gait subphase detection. With respect to time domain features, their feature values may be analogous because two different gait steps may have similar muscle activation. In addition, the current gait subphase might not be recognized until the next gait subphase passes because the window size needed for feature extraction is larger than the period of the gait subphase. The ESGM algorithm is a new approach that compares reference EMG signals and input EMG signals according to time variance to solve these problems and considers variations of physiological muscle activity. We also determined all the elements of the ESGM algorithm using kinematic gait analysis and optimized the algorithm using experiments. Therefore, the ESGM algorithm reflects better timing characteristics of EMG signals than the time domain feature extraction algorithm. In addition, it can provide real-time and user-adaptive recognition of the gait subphase by using only EMG signals. Experimental results show that the average accuracy of the proposed method is 13% better than existing methods and the average detection latency of the proposed method was 5.5 times lower than existing methods.     

EMG pattern classification using SOFMs for hand signal recognition

 We propose a method of pattern classification of electromyographic (EMG) signals using a set of self- organizing feature maps (SOFMs). The proposed method is simple to apply in that the EMG signals are directly input to the SOFMs without preprocessing. Experimental results are presented that show the effectiveness of the SOFM based classifier for the recognition of the hand signal version of the Korean alphabet from EMG signal patterns.     

The Development of a Virtual Myoelectric Prosthesis Controlled by an EMG Pattern Recognition System Based on Neural Networks

One of the major difficulties faced by those who are fitted with prosthetic devices is the great mental effort needed during the first stages of training. When working with myoelectric prosthesis, that effort increases dramatically. In this sense, the authors decided to devise a mechanism to help patients during the learning stages, without actually having to wear the prosthesis. The system is based on a real hardware and software for detecting and processing electromyografic (EMG) signals. The association of autoregressive (AR) models and a neural network is used for EMG pattern discrimination. The outputs of the neural network are then used to control the movements of a virtual prosthesis that mimics what the real limb should be doing. This strategy resulted in rates of success of 100% when discriminating EMG signals collected from the upper arm muscle groups. The results show a very easy-to-use system that can greatly reduce the duration of the training stages.     

Classification of EMG signals using combined features and soft computing techniques

The motor unit action potentials (MUPs) in an electromyographic (EMG) signal provide a significant source of information for the assessment of neuromuscular disorders. Since recently there were different types of developments in computer-aided EMG equipment, different methodologies in the time domain and frequency domain has been followed for quantitative analysis of EMG signals. In this study, the usefulness of the different feature extraction methods for describing MUP morphology is investigated. Besides, soft computing techniques were presented for the classification of intramuscular EMG signals. The proposed method automatically classifies the EMG signals into normal, neurogenic or myopathic. Also, multilayer perceptron neural networks (MLPNN), dynamic fuzzy neural network (DFNN) and adaptive neuro-fuzzy inference system (ANFIS) based classifiers were compared in relation to their accuracy in the classification of EMG signals. Concerning the impacts of features on the EMG signal classification, different results were obtained through analysis of the soft computing techniques. The comparative analysis suggests that the ANFIS modelling is superior to the DFNN and MLPNN in at least three points: slightly higher recognition rate; insensitivity to overtraining; and consistent outputs demonstrating higher reliability.     

An application of a muscle model to study electromyographic signals

A simulation program for research and teaching electromyography (EMG) has been developed. It has a great number of parameters that may be optionally changed in simulations of normal and diseased muscle. The simulator is user-friendly and fast and can actually be run without much help from the manual. It is easy to introduce new motor units (MU), to change MU and individual muscle fibre parameters, to insert an EMG electrode and to change its position. The model allows simulation of the most common pathological situations. The resulting signals are displayed in a conventional form. The generated EMG signals obtained with the three electrodes that have been used so far are reasonably similar to the signals obtained in real recordings. A few shortcomings in simulating, e.g. end plate zone and abnormal volume conduction characteristics do not seem to influence the principal results. The simulator can, therefore, be used in teaching and even for research.     

Head motion anticipation for virtual-environment applications using kinematics and EMG energy

Real-time human-computer interaction plays an important role in virtual-environment (VE) applications. Such interaction can be improved by detecting and reacting to the user's head motion. Today's VE systems use head-mounted inertial sensors to update and spatially stabilize the image displayed to a user through a head-mounted display. Since motion can only be detected after it has already occurred, latencies in the stabilization scheme can only be reduced but never eliminated. Such latencies slow down manual control, cause inaccuracies in matching real and virtual objects through a half-transparent display, and reduce the sense of presence. This paper presents novel methods for reducing VE latencies by anticipating future head motion based on electromyographic (EMG) signals originating from the major neck muscles and head kinematics; it also reports results for anticipation of 17.5 and 35 ms. Features extracted from the EMG signals are used to train a neural network in mapping EMG data, given present head kinematics, into future head motion. The trained network is then used in real time for head-motion anticipation, which gives the VE system the time advantage necessary to compensate for the inherent latencies. The main contribution of this work is the use of EMG energy and bounded head acceleration as the key input/output information, which results in improved performance compared to the previous work.     

Depth map inpainting via sparse distortion model

The depth map captured from a real scene by the Kinect motion sensor is always influenced by noise and other environmental factors. As a result, some depth information is missing from the map. This distortion of the depth map directly deteriorates the quality of the virtual viewpoints rendered in 3D video systems. We propose a depth map inpainting algorithm based on a sparse distortion model. First, we train the sparse distortion model using the distortion and real depth maps to obtain two learning dictionaries: one for distortion and one for real depth maps. Second, the sparse coefficients of the distortion and the real depth maps are calculated by orthogonal matching pursuit. We obtain the approximate features of the distortion from the relationship between the learning dictionary and the sparse coefficients of the distortion map. The noisy images are filtered by the joint space structure filter, and the extraction factor is obtained from the resulting image by the extraction factor judgment method. Finally, we combine the learning dictionary and sparse coefficients from the real depth map with the extraction factor to repair the distortion in the depth map. A quality evaluation method is proposed for the original real depth maps with missing pixels. The proposed method achieves better results than comparable methods in terms of depth inpainting and the subjective quality of the rendered virtual viewpoints.     

无线传感器网络中声震信号的特征提取算法

面向无线传感器网络在地面目标声震信号识别方面的应用需求,提出基于局域判别基(Local Discriminant Bases,LDB)算法的特征提取方法.并且,针对现有的基于时频能量图的可分性测度的缺点,提出新的基于概率密度估计的相对微分熵的可分性测度.基于实地采集到的信号的仿真实验表明,该方法在一定程度上提高了目标的正确识别率,降低了特征维数,具有实际的应用价值.     

基于统计聚类方法的儿童下肢肌电信号周期识别

为运用肌电信号分析髋脱位儿童和正常儿童的差异,提出一种基于统计的聚类方法,识别步态中下肢肌电信号的周期起始时刻。使用非参数贝叶斯模型将肌电信号序列聚类为状态序列,并通过k均值聚类算法将该状态序列标记为肌肉活跃和不活跃两种状态,将肌肉活跃状态的起始时刻作为肌电信号周期的起始位置,并且利用窗函数方法提高预测准确性。实验结果表明,该方法对于预测正常儿童周期起始位置的识别误差较小,平均值为2.15%,并且在5%的置信度水平下与SampEN、SNEO和IP等检测算法相比具有较高的预测准确率。     

Filter design for cancellation of baseline-fluctuation in needle EMG recordings

Appropriate cancellation of the baseline fluctuation (BLF) is an important issue when recording EMG signals as it may degrade signal quality and distort qualitative and quantitative analysis. We present a novel filter-design approach for automatic cancellation of the BLF based on several signal processing techniques used sequentially. The methodology is to estimate the spectral content of the BLF, and then to use this estimation to design a high-pass FIR filter that cancel the BLF present in the signal. Two merit figures are devised for measuring the degree of BLF present in an EMG record. These figures are used to compare our method with the conventional approach, which naively considers the baseline course to be of constant (without any fluctuation) potential shift. Applications of the technique on real and simulated EMG signals show the superior performance of our approach in terms of both visual inspection and the merit figures.     

Cross-fuzzy entropy: A new method to test pattern synchrony of bivariate time series

A new method, namely cross-fuzzy entropy (C-FuzzyEn) analysis, that can enable the measurement of the synchrony or similarity of patterns between two distinct signals, is presented in this study. With the inclusion of fuzzy sets, the similarity of vectors is fuzzily defined in C-FuzzyEn based on the exponential function and their shapes, rather than on the Heaviside function used in the conventional cross sample entropy (C-SampEn). Tests on simulated data sets and real EEG signals showed that C-FuzzyEn was superior to C-SampEn in several aspects, including giving the entropy definition in the case of small parameters, better relative consistency, and less dependence on record length. The proposed C-FuzzyEn was then applied for the analysis of simultaneously recorded electromyography (EMG) and mechanomyography (MMG) signals during sustained isometric contraction for monitoring local muscle fatigue. The results showed that the C-FuzzyEn of EMG-MMG signals decreased significantly during the development of muscle fatigue. The C-FuzzyEn showed a similar trend with the mean frequency (MNF) of EMG, the commonly used muscle fatigue indicator. However, C-FuzzyEn of EMG-MMG demonstrated a better robustness to the length of the analysis window in comparison with the MNF of EMG. The results suggested that the proposed C-FuzzyEn of EMG-MMG may potentially become a new reliable method for muscle fatigue assessment. It can also be applied to other bivariate signals extracted from complex systems with short data lengths in noisy backgrounds.     

基于MEMD-rTVgPDC的皮层肌肉耦合分析

本文将多元经验模态分解(MEMD)与鲁棒时变广义偏定向相干性(rTV-gPDC)引入皮层肌肉耦合分析中,探索脑肌电之间线性和非线性耦合关系。首先同步采集8名健康志愿者在静态握力(5 kg、10 kg、20 kg)下的三通道脑电(EEG)和肌电(EMG)信号,接着采用MEMD对信号进行时-频尺度化,最后同时计算不同耦合方向(EEG→EMG和EMG→EEG)上的rTV-gPDC线性和非线性值。实验结果表明静态握力输出时,皮层肌肉耦合主要反映在beta和gamma频段,其中EEG→EMG方向的耦合强度略高于EMG→EEG方向的耦合强度,且随着左右手握力增加,EEG→EMG和EMG→EEG方向的耦合强度同时增加。此外脑肌电耦合中同时存在线性和非线性因果关系。本文方法能够定量刻画不同握力下三个脑肌电通道之间的线性和非线性交互影响,可为研究运动功能障碍及康复评价提供有效的生理参数指标。     

基于典型相关分析与低通滤波的肌电伪迹去除

提出了一种基于典型相关分析(CCA)和低通滤波的盲源分离方法去除脑电信号(EEG)中的肌电伪迹.该方法首先将混入了肌电伪迹的EEG信号分解为不相关的CCA分量,然后对与伪迹源相关的分量进行低通滤波处理,去除这些分量中的高频伪迹成分,最后利用与EEG相关的CCA分量和滤波处理后的新分量重构信号,消除肌电伪迹的影响.实验结果表明,采用CCA能够有效地分离出肌电伪迹,而结合低通滤波技术能够更有效地保留EEG信息.该方法取得了较好的去除肌电伪迹的效果.     

Feature extraction of the first difference of EMG time series for EMG pattern recognition

This paper demonstrates the utility of a differencing technique to transform surface EMG signals measured during both static and dynamic contractions such that they become more stationary. The technique was evaluated by three stationarity tests consisting of the variation of two statistical properties, i.e., mean and standard deviation, and the reverse arrangements test. As a result of the proposed technique, the first difference of EMG time series became more stationary compared to the original measured signal. Based on this finding, the performance of time-domain features extracted from raw and transformed EMG was investigated via an EMG classification problem (i.e., eight dynamic motions and four EMG channels) on data from 18 subjects. The results show that the classification accuracies of all features extracted from the transformed signals were higher than features extracted from the original signals for six different classifiers including quadratic discriminant analysis. On average, the proposed differencing technique improved classification accuracies by 2–8%.     

基于模糊聚类技术的肌电信号完全分解算法

肌电(EMG)信号分解是EMG信号产生的逆过程。通过EMG分解获取完整的运动单元(MU)的波形和发放信息,需完成复杂的叠加波形分解过程。首先,基于小波滤波和小波阈值估计技术去除EMG信号中的噪声;接着,利用幅度-斜率双阈值法检测出MUAP波形;然后,采用分类功能强的模糊K均值聚类技术对波形进行聚类,再利用最近邻法将未分配波形分类;最后,采用基于伪相关相似性度量的剥落法,进行叠加电位波形分解,实现肌电信号的完全分解,获取完整的MUAP波形和发放模式。利用对来自正常人的真实EMG信号和模拟EMG信号进行实验,系统平均正确率可达87%以上。     

基于虚拟现实和动态加权决策融合的恐高情绪识别

目前恐高情绪分类中的生理信号主要涉及脑电、心电、皮电等, 考虑到脑电在采集和处理上的局限性以及多模态信号间的融合问题, 提出一种基于6种外周生理信号的动态加权决策融合算法. 首先, 通过虚拟现实技术诱发被试不同程度的恐高情绪, 同步记录心电、脉搏、肌电、皮电、皮温和呼吸这6种外周生理信号; 其次, 提取信号的统计特征和事件相关特征构建恐高情感数据集; 再次, 根据分类性能、模态和跨模态信息提出一种动态加权决策融合算法, 从而对多模态信号进行有效整合以提高识别精度. 最后, 将实验结果与先前相关研究进行对比, 同时在开源的WESAD情感数据集进行验证. 结论表明, 多模态外周生理信号有助于恐高情绪分类性能的提升, 提出的动态加权决策融合算法显著提升了分类性能和模型鲁棒性.