Recognition of Electromyographic Signals Using Cascaded Kernel Learning Machine

Electromyographic (EMG) signals recognition is a complex pattern recognition problem due to its property of large variations in signals and features. This paper proposes a novel EMG classifier called cascaded kernel learning machine (CKLM) to achieve the goal of high-accuracy EMG recognition. First, the EMG signals are acquired by three surface electrodes placed on three different muscles. Second, EMG features are extracted by autoregressive model (ARM) and EMG histogram. After the feature extraction, the CKLM is performed to classify the features. CKLM is composed of two different kinds of kernel learning machines: generalized discriminant analysis (GDA) algorithm and support vector machine (SVM). By using GDA, both the goals of the dimensionality reduction of input features and the selection of discriminating features, named kernel FisherEMG, can be reached. Then, SVM combined with one-against-one strategy is executed to classify the kernel FisherEMG. By cascading SVM with GDA, the input features will be nonlinearly mapped twice by radial-basis function (RBF). As a result, a linear optimal separating hyperplane can be found with the largest margin of separation between each pair of postures' classes in the implicit dot product feature space. In addition, we develop a digital signal processor (DSP)-based EMG classification system for the control of a multi-degrees-of-freedom prosthetic hand for the practical implementation. Based on the clinical experiments, the results show that the proposed CKLM is superior to other frequently used methods, such as k-nearest neighbor algorithm, multilayer neural network, and SVM. The best EMG recognition rate 93.54% is obtained by CKLM.     

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。     

Evaluation of a Multifunctional Hand Prosthesis System Using EMG Controlled Animation

In this communication, we present an on-line real-time simulation system used to evaluate a new method of controlling a multifunctional hand prosthesis. The system employs two computers. Acquisition, analysis, and classification of EMG signals are performed by a minicomputer, and the animation model of the hand prosthesis which is displayed on a monitor TV is controlled by a microcomputer. From three EMG signals picked up from the most suitable muscles of the forearm, three amplitude and three frequency components are derived. Six voluntary movements are then classified by the use of a pattern recognition technique based on the linear discriminant analysis method. Besides the six basic motions, the model can also make eight combined motions using the method of selecting control signals. The experimental results tested on healthy adults indicated that recognition rate was above 90 percent, and nearly 100 percent in some of the better cases. Then the subjects could easily operate the model on the TV screen.     

EMG-based speech recognition using hidden markov models with global control variables

It is well known that a strong relationship exists between human voices and the movement of articulatory facial muscles. In this paper, we utilize this knowledge to implement an automatic speech recognition scheme which uses solely surface electromyogram (EMG) signals. The sequence of EMG signals for each word is modelled by a hidden Markov model (HMM) framework. The main objective of the work involves building a model for state observation density when multichannel observation sequences are given. The proposed model reflects the dependencies between each of the EMG signals, which are described by introducing a global control variable. We also develop an efficient model training method, based on a maximum likelihood criterion. In a preliminary study, 60 isolated words were used as recognition variables. EMG signals were acquired from three articulatory facial muscles. The findings indicate that such a system may have the capacity to recognize speech signals with an accuracy of up to 87.07%, which is superior to the independent probabilistic model.     

Blind separation of linear instantaneous mixtures of nonstationary surface myoelectric signals

Electromyographic (EMG) recordings detected over the skin may be mixtures of signals generated by different active muscles due to the phenomena related to volume conduction. Separation of the sources is necessary when single muscle activity has to be detected. Signals generated by different muscles may be considered uncorrelated but in general overlap in time and frequency. Under certain assumptions, mixtures of surface EMG signals can be considered as linear instantaneous but no a priori information about the mixing matrix is available when different muscles are active. In this study, we applied blind source separation (BSS) methods to separate the signals generated by two active muscles during a force-varying task. As the signals are non stationary, an algorithm based on spatial time-frequency distributions was applied on simulated and experimental EMG signals. The experimental signals were collected from the flexor carpi radialis and the pronator teres muscles which could be activated selectively for wrist flexion and rotation, respectively. From the simulations, correlation coefficients between the reference and reconstructed sources were higher than 0.85 for signals largely overlapping both in time and frequency and for signal-to-noise ratios as low as 5 dB. The Choi-Williams and Bessel kernels, in this case, performed better than the Wigner-Ville one. Moreover, the selection of time-frequency points for the procedure of joint diagonalization used in the BSS algorithm significantly influenced the results. For the experimental signals, the interference of the other source in each reconstructed source was significantly attenuated by the application of the BSS method. The ratio between root-mean-square values of the signals from the two sources detected over one of the muscles increased from (mean +/- standard deviation) 2.33 +/- 1.04 to 4.51 +/- 1.37 and from 1.55 +/- 0.46 to 2.72 +/- 0.65 for wrist flexion and rotation, respectively. This increment was statistically significant. It was concluded that the BSS approach applied is promising for the separation of surface EMG signals, with applications ranging from muscle assessment to detection of muscle activation intervals, and to the control of myoelectric prostheses.     

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.     

基于粒子群优化-支持向量机方法的下肢肌电信号步态识别

为提高下肢表面肌电信号步态识别的准确性和实时性,该文提出一种基于粒子群优化(PSO)算法优化支持向量机(SVM)的模式识别方法。首先对消噪后的肌电信号提取积分肌电值和方差作为特征样本,然后利用PSO算法优化SVM的惩罚参数和核函数参数,最后利用步态动作的肌电信号样本数据对构造的SVM分类器进行训练、测试。实验结果表明PSO-SVM分类器对下肢正常行走5个步态的识别率,明显高于未经参数优化的SVM分类器,优化后平均识别率达到97.8%,并兼顾了分类的准确性和自适应性。     

Physiologically based simulation of clinical EMG signals

An algorithm that generates electromyographic (EMG) signals consistent with those acquired in a clinical setting is described. Signals are generated using a model constructed to closely resemble the physiology and morphology of skeletal muscle, combined with line source models of commonly used needle electrodes positioned in a way consistent with clinical studies. The validity of the simulation routines is demonstrated by comparing values of statistics calculated from simulated signals with those from clinical EMG studies of normal subjects. The simulated EMG signals may be used to explore the relationships between muscle structure and activation and clinically acquired EMG signals. The effects of motor unit (MU) morphology, activation, and neuromuscular junction activity on acquired signals can be analyzed at the fiber, MU and muscle level. Relationships between quantitative features of EMG signals and muscle structure and activation are discussed.     

A real-time EMG pattern recognition system based on linear-nonlinear feature projection for a multifunction myoelectric hand

This paper proposes a novel real-time electromyogram (EMG) pattern recognition for the control of a multifunction myoelectric hand from four channel EMG signals. To extract a feature vector from the EMG signal, we use a wavelet packet transform that is a generalized version of wavelet transform. For dimensionality reduction and nonlinear mapping of the features, we also propose a linear-nonlinear feature projection composed of principal components analysis (PCA) and a self-organizing feature map (SOFM). The dimensionality reduction by PCA simplifies the structure of the classifier and reduces processing time for the pattern recognition. The nonlinear mapping by SOFM transforms the PCA-reduced features into a new feature space with high class separability. Finally, a multilayer perceptron (MLP) is used as the classifier. Using an analysis of class separability by feature projections, we show that the recognition accuracy depends more on the class separability of the projected features than on the MLP's class separation ability. Consequently, the proposed linear-nonlinear projection method improves class separability and recognition accuracy. We implement a real-time control system for a multifunction virtual hand. Our experimental results show that all processes, including virtual hand control, are completed within 125 ms, and the proposed method is applicable to real-time myoelectric hand control without an operational time delay.     

Estimation of motor unit conduction velocity from surface EMG recordings by signal-based selection of the spatial filters

Muscle fiber conduction velocity (CV) can be estimated by the application of a pair of spatial filters to surface electromagnetic (EMG) signals and compensation of the spatial filter transfer function with equivalent temporal filters. This method integrates the selection of the spatial filters for signal detection to the estimation of CV. Using this approach, in this paper, we propose a novel technique for signal-based selection of the spatial filter pair that minimizes the effect of nonpropagating signal components (end-of-fiber effects) on CV estimates (optimal filters). The technique is applicable to signals with one propagating and one nonpropagating component, such as single motor unit action potentials. It is shown that the determination of the optimal filters also allows the identification of the propagating and nonpropagating signal components. The new method was applied to simulated and experimental EMG signals. Simulated signals were generated by a cylindrical, layered volume conductor model. Experimental signals were recorded from the abductor pollicis brevis with a linear array of 16 electrodes. In the simulations, the proposed approach provided CV estimates with lower bias due to nonpropagating signal components than previously proposed methods based on the entire signal waveform. In the experimental signals, the technique separated propagating and nonpropagating signal components with an average reconstruction error of 2.9 +/- 0.9% of the signal energy. The technique may find application in single motor unit studies for decreasing the variability and bias of CV estimates due to the presence and different weights of the nonpropagating components.     

Singularity characteristics of needle EMG IP signals

Clinical electromyography (EMG) interference pattern (IP) signals can reveal more diagnostic information than their constituents, the motor unit action potentials (MUAPs). Singularities and irregular structures typically characterize the mathematically defined content of information in signals. In this paper, a wavelet transform method is used to detect and quantify the singularity characteristics of EMG IP signals using the Lipschitz exponent (LE) and measures derived from it. The performance of the method is assessed in terms of its ability to discriminate healthy, myopathic and neuropathic subjects and how it compares with traditionally used Turns Analysis (TA) methods and a method recently developed by the authors, interscale wavelet maximum (ISWM). Highly significant intergroup differences were found using the LE method. Most of the singularity measures have a performance similar to that of ISWM and considerably better than that of TA. Some measures such as the ratio of the mean LE value to the number of singular points in the signal have considerably superior performance to both methods. These findings add weight to the view that wavelet analysis methods offer an effective way forward in the quantitative analysis of EMG IP signal to assist the clinician in the diagnosis of neuromuscular disorders.     

脑电信号预处理方法研究综述

脑电信号是一种复杂且重要的生物信号,被广泛应用于类脑智能技术和脑机接口领域的研究。文中介绍了干扰正常脑电信号的常见非生理性伪迹和生理性伪迹的类型及特点,并对生理性伪迹的产生原因进行了详细分析。通过对各种脑电信号去除伪迹方法的回顾以及应用现状的分析,比较并总结了传统去除伪迹方法和新型去除伪迹方法的研究进展,并进一步分析去除伪迹方法的优缺点。部分方法已经成功应用于处理脑电信号中的眼电、心电和肌电等伪迹中。文中还针对目前脑电信号去除伪迹的需求及所面临的问题给出了应对策略,并对未来的研究方向进行了分析和展望。     

A novel approach for estimating muscle fiber conduction velocity by spatial and temporal filtering of surface EMG signals

We describe a new method for the estimation of muscle fiber conduction velocity (CV) from surface electromyography (EMG) signals. The method is based on the detection of two surface EMG signals with different spatial filters and on the compensation of the spatial filtering operations by two temporal filters (with CV as unknown parameter) applied to the signals. The transfer functions of the two spatial filters may have different magnitudes and phases, thus the detected signals have not necessarily the same shape. The two signals are first spatially and then temporally filtered and are ideally equal when the CV value selected as a parameter in the temporal filters corresponds to the velocity of propagation of the detected action potentials. This approach is the generalization of the classic spectral matching technique. A theoretical derivation of the method is provided together with its fast implementation by an iterative method based on the Newton's method. Moreover, the lowest CV estimate among those obtained by a number of filter pairs is selected to reduce the CV bias due to nonpropagating signal components. Simulation results indicate that the method described is less sensitive than the classic spectral matching approach to the presence of nonpropagating signals and that the two methods have similar standard deviation of estimation in the presence of additive, white, Gaussian noise. Finally, experimental signals have been collected from the biceps brachii muscle of ten healthy male subjects with an adhesive linear array of eight electrodes. The CV estimates depended on the electrode location with positive bias for the estimates from electrodes close to the innervation or tendon regions, as expected. The proposed method led to significantly lower bias than the spectral matching method in the experimental conditions, confirming the simulation results.     

Interscale wavelet maximum-a fine to coarse algorithm for wavelet analysis of the EMG interference pattern

A method has been developed, interscale wavelet maximum (ISWM), for characterising the electromyogram (EMG) interference pattern to assist in the diagnosis of neuromuscular disease. EMG signals are decomposed with the redundant dyadic wavelet transform and wavelet maxima (WM) are found. Thresholding methods are applied to remove WM due to noise and background activity. An efficient fine-to-coarse algorithm identifies the WM tree structure for the motor unit action potential rising edges. The WM for each tree are summed at each scale; the largest value is the ISWM. Highly significant differences in ISWM values have been found between healthy, myopathic, and neuropathic subjects that could make the technique a useful diagnostic tool.     

Pattern recognition of multiple EMG signals applied to the description of human gait

The application of pattern recognition to the classification of normal and four pathological gaits is described. The classification is based on construction of a pattern feature vector whose elements are obtained by processing EMG signals obtained from 6 muscles responsible for movement of the foot at the ankle. The paper describes the basic actions of these muscles and the resulting gait patterns. Data were obtained from 30 patients at Rancho Los Amigos Hospital. 11 sets of data were used as training patterns for the synthesis of linear dicriminant functions needed in the classification algorithm. The resulting algorithm was used to proces 19 patient records. The correct gait was identified in 15 of these 19 sets. Potential clinical applications of the results are discussed.     

Spatial Filtering of Noninvasive Multielectrode EMG: Part II?Filter Performance in Theory and Modeling

Spatial filtering, particularly common in the field of engineering, is adapted in theory and practice to the filtering of propagating spatial EMG signals. This technique offers a new flexibility in the design of selective EMG measurement configurations. Longitudinal as well as two-dimensional spatial filters can be used. The conditions for the design of suitable spatial filters are deduced by signal theory. The performances of different selected configurations are compared by means of a given simple model of an excited motor unit. The modeling results compare well to the previously described experimental signals.     

基于DS证据理论的机载火控雷达空空工作模式判定

针对机载火控雷达典型空空工作模式的判定问题,提出一种基于DS证据理论的判定体系。首先,从侦收到的敌方雷达信号中提取特征参数并构建雷达信号特征库,通过预判断流程快速实现单平台下的模式分组;然后,对分组后的多维空间模式识别结果运用DS证据理论,采用分布式结构进行单平台多周期时域融合和多平台空域信息融合,实现雷达工作模式判定。仿真结果表明:该体系能在单平台下识别速度搜索模式和单目标跟踪模式,在多平台下对边搜索边测距模式和边扫描边跟踪模式的判定信度达83.3%,实时性和准确率较好,具有实际应用价值。     

Investigation of optimum electrode locations by using an automatized surface electromyography analysis technique.

Identification of the innervation zone is widely used to optimize the accuracy and precision of noninvasive surface electromyography (EMG) signals because the EMG signal is strongly influenced by innervation zones. However, simply structured fusiform muscle, such as biceps brachii muscle, has been employed mainly due to the simplicity with which the propagation from raw EMG signals can be observed. In this study, the optimum electrode location (OEL), free from innervational influence, was investigated by the propagation pattern of action potentials for brachii muscles and more complicated deltoid muscle structures using an automatized signal analysis technique. The technique employed newly developed computer software with additional clinical uses and minimized subjective differences. EMG signals were recorded using surface array electrodes during voluntary isometric contractions obtained from 12 healthy male subjects. Peaks in EMG signals were detected and averaged for each muscle. The propagation patterns and OEL were examined from biceps brachii muscles for all subjects and from deltoid muscles for seven subjects. The estimated locations were partially confirmed by comparing the root mean squares of the EMG signals. These results show that propagation patterns and OEL could be estimated simply and automatically even from the surface EMG signals of deltoid muscles.     

Unsupervised pattern recognition for the classification of EMGsignals

The shapes and firing rates of motor unit action potentials (MUAPs) in an electromyographic (EMG) signal provide an important source of information for the diagnosis of neuromuscular disorders. In order to extract this information from EMG signals recorded at low to moderate force levels, it is required: i) to identify the MUAPs composing the EMG signal, ii) to classify MUAPs with similar shape, and iii) to decompose the superimposed MUAP waveforms into their constituent MUAPs. For the classification of MUAPs two different pattern recognition techniques are presented: i) an artificial neural network (ANN) technique based on unsupervised learning, using a modified version of the self-organizing feature maps (SOFM) algorithm and learning vector quantization (LVQ) and ii) a statistical pattern recognition technique based on the Euclidean distance. A total of 1213 MUAPs obtained from 12 normal subjects, 13 subjects suffering from myopathy, and 15 subjects suffering from motor neuron disease were analyzed. The success rate for the ANN technique was 97.6% and for the statistical technique 95.3%. For the decomposition of the superimposed waveforms, a technique using crosscorrelation for MUAP's alignment, and a combination of Euclidean distance and area measures in order to classify the decomposed waveforms is presented. The success rate for the decomposition procedure was 90%