基于蚁群算法的表面肌电信号特征选择

目的为提高假肢系统对动作信号的识别速度,设计了基于优化蚁群算法（ant colonyoptimization,ACO）的特征选择法,对表面肌电信号（surface electromyography,sEMG）高维特征向量降维以减少计算负担。方法以特征与目标类型之间互信息关系作为启发函数,通过蚁群算法选出最佳特征子集,最后用已训练好的人工神经网络检验其分类性能。结果对10名健康受试者进行了手腕部动作的肌电信号模式分类实验。与传统主成分分析法（principle component analysis,PCA）相比,该算法选出的特征子集提高了识别准确率,并显著降低了原始特征集的特征维数,进而简化分类器的结构,减少计算开销。结论本方法在实时性要求高的肌电控制假肢等系统中具有良好的应用前景。     

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...     

Supervised mutual-information based feature selection for motor unit action potential classification

A new supervised mutual information-based feature selection method is presented. Using real motor unit action potential (MUAP) data from 10 EMG signals, the performances of 32 time-sample feature sets, feature subsets selected using first- and second-order mutual information and features obtained using linear discriminant analysis (LDA) and principal component analysis (PCA) were evaluated using a minimum Euclidean distance (MED) classifier. The evaluation showed that by using only 20 first-order features or only 15 second-order features mean error rates and error rate variations equivalent to using all 32 samples or LDA or PCA could be obtained. The computational cost of first-order feature selection was considerably less than LDA, PCA and second-order feature selection. The performance of first-order features was further evaluated using a more robust classifier. Unlike the MED classifier, the robust classifier only assigned a candidate MUAP if the assignment was sufficiently certain. For the robust classifier the average error rates using 20 features were similar to using the full feature set, yet higher assignment rates were obtained. Results from both evaluations suggest that the sets of first-order features were an efficient representation of lower dimension, which provided high accuracy classification with reduced computational requirements.     

Joint application of rough set-based feature reduction and Fuzzy LS-SVM classifier in motion classification

This paper presents an effective classification scheme consisting of the rough set theory (RST)-based feature selection and the fuzzy least squares support vector machine (LS-SVM) classifier for the surface electromyographic (sEMG)-based motion classification. The wavelet packet transform (WPT) is exploited to decompose the four-class motion EMG signals to the non-overlapped sub-bands and the energy characteristic of each sub-band is adopted to form the original feature set. In order to reduce the computation complexity, the RST is utilized to get the reduction feature set without compromising classification accuracy. In the feature reduction phase, cluster separation index (CSI) is introduced to evaluate the performance of the proposed algorithm. In the sequel, the Fuzzy LS-SVM is constructed for the multi-class classification task. The RST-based feature selection is independent of the classifier design. Consequently the classification performance will vary with different classifiers. We make the comparison between the proposed classification scheme and the commonly used classification scheme, such as the combination of the principal component analysis (PCA)-based feature selection and the neural network (NN) classifier. The results of comparative experiments show that the diverse motions can be identified with high accuracy by the proposed scheme. Compared with other feature extraction and selection algorithms and classifiers, superior performance of the proposed classification scheme illustrates the potential of the SVM techniques combined with WPT and RST in EMG motion classification.     

Feature dimensionality reduction for myoelectric pattern recognition: A comparison study of feature selection and feature projection methods

This study investigates the effect of the feature dimensionality reduction strategies on the classification of surface electromyography (EMG) signals toward developing a practical myoelectric control system. Two dimensionality reduction strategies, feature selection and feature projection, were tested on both EMG feature sets, respectively. A feature selection based myoelectric pattern recognition system was introduced to select the features by eliminating the redundant features of EMG recordings instead of directly choosing a subset of EMG channels. The Markov random field (MRF) method and a forward orthogonal search algorithm were employed to evaluate the contribution of each individual feature to the classification, respectively. Our results from 15 healthy subjects indicate that, with a feature selection analysis, independent of the type of feature set, across all subjects high overall accuracies can be achieved in classification of seven different forearm motions with a small number of top ranked original EMG features obtained from the forearm muscles (average overall classification accuracy >95% with 12 selected EMG features). Compared to various feature dimensionality reduction techniques in myoelectric pattern recognition, the proposed filter-based feature selection approach is independent of the type of classification algorithms and features, which can effectively reduce the redundant information not only across different channels, but also cross different features in the same channel. This may enable robust EMG feature dimensionality reduction without needing to change ongoing, practical use of classification algorithms, an important step toward clinical utility.     

A discriminant bispectrum feature for surface electromyogram signal classification

This paper presents a discriminant bispectrum (DBS) feature extraction approach to surface electromyogram (sEMG) signal classification for prosthetic control. The proposed feature extraction method involves two steps: (1) the bispectrum matrix integration, and (2) the Fisher linear discriminant (FLD) projection. We compare DBS with other conventional features, such as autoregressive coefficients, root mean square, power spectral distribution and time domain statistics. First, the separability of the features is investigated by the visualization of feature distribution in the FLD subspace and quantitative measurement (Davies–Boulder clustering index). Then four linear and non-linear classifiers are used to evaluate the discriminative powers of the features in terms of classification accuracy (CA). The experimental results show that DBS has better performance than other features for identifying the motion patterns of sEMG signals, and the best CA result of DBS is 99.4%.     

基于表面肌电信号的手势识别与分析

目的 研究利用前臂及手部表面肌电( surface electromyography,sEMG)信号进行手势识别的方法,以及不同 手势下拇指、食指的关节角度,探讨 sEMG 信号控制外骨骼手的可行性。 方法 采集 20 名健康右利手受试者右侧 前臂及手部 6 块肌肉 sEMG 信号。 提取 sEMG 信号的时域特征值,对比人工神经网络( artificial neural network, ANN)、K-近邻(K-nearest neighbor, KNN)、决策树(decision tree, DT)、随机森林( random forest, RF)和支持向量机(support vector machine, SVM)等多种分类器对 6 种日常手势进行识别。 同时,采用 Vicon 摄像机跟踪系统捕捉右手拇指、食指运动轨迹,计算拇指、食指关节角度。 结果 利用前臂及手部 sEMG 信号可以实现 6 种手势的模式识别,其中 ANN 分类器的分类预测效果最好,测试集预测精度可达 97. 9% ,Kappa 系数可达 0. 975。 同时,计算得到不同手势下拇指、食指的关节角度,并进行不同手势下关节角度相关性分析。 结论 利用前臂及手部 sEMG 信号进 行手势识别,能够实现具有几乎完全一致的分类预测结果。 研究结果证明了 sEMG 信号手势识别应用于外骨骼手 控制的可行性。     

An automated feature extraction and emboli detection system based on the PCA and fuzzy sets

The Doppler ultrasound technique is commonly used to detect emboli in the cerebral circulation. Here an automated feature extraction and emboli detection system is proposed based on the principal components analysis (PCA) and fuzzy sets. In the system, two features, R(ry) and k, are extracted by the PCA method. Meanwhile, MMR and sigma(f min) are obtained with the traditional temporal processing and spectrogram analysis, respectively. Normal blood flow signals are firstly distinguished from abnormal signals by MMR. Then signals containing emboli and disturbance noises are further differentiated by other features based on fuzzy sets. From experiments with computer-simulated and clinical Doppler ultrasound signals, it is shown that features extracted from the PCA method achieve better classification performance than those of traditional methods. The fuzzy-based detection system not only obtains high classification accuracy but is more applicable in clinical diagnosis.     

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。     

An affective computing approach to physiological emotion specificity: toward subject-independent and stimulus-independent classification of film-induced emotions

The hypothesis of physiological emotion specificity has been tested using pattern classification analysis (PCA). To address limitations of prior research using PCA, we studied effects of feature selection (sequential forward selection, sequential backward selection), classifier type (linear and quadratic discriminant analysis, neural networks, k-nearest neighbors method), and cross-validation method (subject- and stimulus-(in)dependence). Analyses were run on a data set of 34 participants watching two sets of three 10-min film clips (fearful, sad, neutral) while autonomic, respiratory, and facial muscle activity were assessed. Results demonstrate that the three states can be classified with high accuracy by most classifiers, with the sparsest model having only five features, even for the most difficult task of identifying the emotion of an unknown subject in an unknown situation (77.5%). Implications for choosing PCA parameters are discussed.     

Feature extraction from Doppler ultrasound signals for automated diagnostic systems

This paper presented the assessment of feature extraction methods used in automated diagnosis of arterial diseases. Since classification is more accurate when the pattern is simplified through representation by important features, feature extraction and selection play an important role in classifying systems such as neural networks. Different feature extraction methods were used to obtain feature vectors from ophthalmic and internal carotid arterial Doppler signals. In addition to this, the problem of selecting relevant features among the features available for the purpose of classification of Doppler signals was dealt with. Multilayer perceptron neural networks (MLPNNs) with different inputs (feature vectors) were used for diagnosis of ophthalmic and internal carotid arterial diseases. The assessment of feature extraction methods was performed by taking into consideration of performances of the MLPNNs. The performances of the MLPNNs were evaluated by the convergence rates (number of training epochs) and the total classification accuracies. Finally, some conclusions were drawn concerning the efficiency of discrete wavelet transform as a feature extraction method used for the diagnosis of ophthalmic and internal carotid arterial diseases.     

Comparison of feature evaluation criteria for speech recognition based on electromyography

In this paper, we present a performance comparison of 14 feature evaluation criteria and 4 classifiers for isolated Thai word classification based on electromyography signals (EMG) to find a near-optimal criterion and classifier. Ten subjects spoke 11 Thai number words in both audible and silent modes while the EMG signal from five positions of the facial and neck muscles were captured. After signal collection and preprocessing, 22 EMG features widely used in the EMG recognition field were computed and were then evaluated based on 14 evaluation criteria including both independent criteria (IC) and dependent criteria (DC) for feature evaluation and selection. Subsequently, the top nine features were selected for each criterion, and were used as inputs to classifiers. Four types of classifier were employed with 10-fold cross-validation to estimate classification performance. The results showed that features selected with a DC on a Fisher’s least square linear discriminant classifier (D_FLDA) used with a linear Bayes normal classifier (LBN) gave the best average accuracies, of 93.25 and 80.12% in the audible and the silent modes, respectively.     

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.     

基于多通道线性描述符的脑-机接口分类算法的研究

脑电信号的特征提取是脑—机接口(BCI)中的一个关键部分,对提高分类正确率和信息传输率起着决定性的作用。本研究利用多通道线性描述符提取脑电信号的分类特征信息,将三个描述符单独和联合地施加于三个感兴趣的电极子集,导出12个特征矢量。五个受试参加了一个在线反馈BCI实验。实验期间他们被要求想象左手或右手运动,记录的脑电图数据用于离线分析。对来自7导和11导两个电极子集的8个特征矢量,五个受试平均的分类精度在89%和93.5%之间,而最好的分类精度在85%与99.9%之间。比较基于描述符的特征与基于自回归(AR)模型的特征分类性能,结果表明多通道线性描述符是一种有效的特征提取方法。使用该方法提取特征时,理想的电极数应在7与11之间。     

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。     

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%.     

基于双线性模型的动作肌电信号用户无关识别研究

动作肌电信号具有个体差异性且不同动作的肌电信号是不同的,通过挖掘双线性模型的因素分解能力,将训练样本的特征矢量分解为用户相关和动作相关两大因素,通过确定因素的维度重构具有共性的训练样本特征。在测试样本特征重构阶段引入适应融合机制,更新模型参数重构测试样本特征。以11名受试者的4类动作为例,分别采用线性判别、K近邻分类算法和支持向量机,对比3种实验方案(多用户单天、单用户多天和基于双线性模型的多用户单天)的识别结果。实验表明,双线性模型的平均识别率最低为85%以上,相比于单纯的多用户单天识别结果(平均识别率不高于75%)有显著提高(P <0.001),且相比于单用户多天的识别结果(平均识别率90%以上)差异性不显著(P >0.24)。双线性模型为基于动作识别技术的非特定人肌电控制系统提供了交互方案,且该模型具备将多用户单天的数据看成单用户多天数据的能力,提供了用户训练负担降低的可行性。     

Feature Extraction for Systolic Heart Murmur Classification

Heart murmurs are often the first signs of pathological changes of the heart valves, and they are usually found during auscultation in the primary health care. Distinguishing a pathological murmur from a physiological murmur is however difficult, why an “intelligent stethoscope” with decision support abilities would be of great value. Phonocardiographic signals were acquired from 36 patients with aortic valve stenosis, mitral insufficiency or physiological murmurs, and the data were analyzed with the aim to find a suitable feature subset for automatic classification of heart murmurs. Techniques such as Shannon energy, wavelets, fractal dimensions and recurrence quantification analysis were used to extract 207 features. 157 of these features have not previously been used in heart murmur classification. A multi-domain subset consisting of 14, both old and new, features was derived using Pudil’s sequential floating forward selection (SFFS) method. This subset was compared with several single domain feature sets. Using neural network classification, the selected multi-domain subset gave the best results; 86% correct classifications compared to 68% for the first runner-up. In conclusion, the derived feature set was superior to the comparative sets, and seems rather robust to noisy data.     

Analysis of EEG signals by combining eigenvector methods and multiclass support vector machines

A new approach based on the implementation of multiclass support vector machine (SVM) with the error correcting output codes (ECOC) is presented for classification of electroencephalogram (EEG) signals. In practical applications of pattern recognition, there are often diverse features extracted from raw data which needs recognizing. Decision making was performed in two stages: feature extraction by eigenvector methods and classification using the classifiers trained on the extracted features. The aim of the study is classification of the EEG signals by the combination of eigenvector methods and multiclass SVM. The purpose is to determine an optimum classification scheme for this problem and also to infer clues about the extracted features. The present research demonstrated that the eigenvector methods are the features which well represent the EEG signals and the multiclass SVM trained on these features achieved high classification accuracies.     

Computerized three-class classification of MRI-based prognostic markers for breast cancer

The purpose of this study is to investigate whether computerized analysis using three-class Bayesian artificial neural network (BANN) feature selection and classification can characterize tumor grades (grade 1, grade 2 and grade 3) of breast lesions for prognostic classification on DCE-MRI. A database of 26 IDC grade 1 lesions, 86 IDC grade 2 lesions and 58 IDC grade 3 lesions was collected. The computer automatically segmented the lesions, and kinetic and morphological lesion features were automatically extracted. The discrimination tasks-grade 1 versus grade 3, grade 2 versus grade 3, and grade 1 versus grade 2 lesions-were investigated. Step-wise feature selection was conducted by three-class BANNs. Classification was performed with three-class BANNs using leave-one-lesion-out cross-validation to yield computer-estimated probabilities of being grade 3 lesion, grade 2 lesion and grade 1 lesion. Two-class ROC analysis was used to evaluate the performances. We achieved AUC values of 0.80?±?0.05, 0.78?±?0.05 and 0.62?±?0.05 for grade 1 versus grade 3, grade 1 versus grade 2, and grade 2 versus grade 3, respectively. This study shows the potential for (1) applying three-class BANN feature selection and classification to CADx and (2) expanding the role of DCE-MRI CADx from diagnostic to prognostic classification in distinguishing tumor grades.