基于TRCSP和L2范数的脑电通道选择方法

脑-机接口（BCI）系统常用高密度电极通道来获取较高空间分辨率的脑电（EEG）信号，但同时也会引入过多的噪声通道，影响脑电的解码性能。为了消除无关的噪声通道，提出了一种基于Tikhonov正则化共空间模式（TRCSP）和L2范数的运动想象脑电通道选择方法。首先基于TRCSP和分类器得到最优的空间滤波器，接着基于L2范数对空间滤波器得到的各通道的权重值进行排序。选择前K个通道的数据进行CSP特征提取，根据分类器的分类准确率确定最优K值，进而得到最优的通道数和通道组合。在实验中，使用6种分类器分别在BCI竞赛III（2005）数据集IVa和实验室自采集数据上验证所提出的通道选择方法的有效性。所提出的方法在两个数据集上的平均分类准确率分别达到了87.57%和74.32%，优于其它现有的方法。     

基于改进GSA-SVM算法的电能质量扰动分类方法

针对不同类型电能质量扰动信号分类准确率不高的问题,通过MATLAB/simulink搭建常见的9种不同的电能质量扰动信号的模型进行仿真分析,提出一种改进的万有引力搜索算法(improved gravitational search algorithm, IGSA)对支持向量机(support vector machine, SVM)的惩罚因子和核函数参数进行寻优的方法,通过优化SVM的惩罚因子和核函数参数,构建IGSA-SVM分类器,再把提取到的特征向量进行归一化之后输入到所构造好IGSA-SVM分类器中进行训练与分类。仿真结果表明,IGSA-SVM分类器的分类准确率比SVM和GSA-SVM这2种分类器都要好,可以实现对9种不同的电能质量扰动信号的快速准确分类,有利于解决实际的工程问题。     

应用贝叶斯框架的LS-SVM概率输出诊断电力变压器故障

针对传统最小二乘支持向量机（LS-SVM）分类器的参数选择具有随意性和不确定性等不足,采用贝叶斯推断方法、通过3级分层推断优化来确定最小二乘支持向量机的各参数,有效提高了最小二乘支持向量机的建模效率。结合最小二乘支持向量机的后验概率输出,可将其运用到变压器故障诊断中。仿真结果表明：该方法能有效地诊断电力变压器故障,且诊断精度和建模效率均优于传统的最小二乘支持向量机方法。     

An enhanced time-frequency-spatial approach for motor imagery classification.

Human motor imagery (MI) tasks evoke electroencephalogram (EEG) signal changes. The features of these changes appear as subject-specific temporal traces of EEG rhythmic components at specific channels located over the scalp. Accurate classification of MI tasks based upon EEG may lead to a noninvasive brain-computer interface (BCI) to decode and convey intention of human subjects. We have previously proposed two novel methods on time-frequency feature extraction, expression and classification for high-density EEG recordings (Wang and He 2004; Wang, Deng, and He, 2004). In the present study, we refined the above time-frequency-spatial approach and applied it to a one-dimensional "cursor control" BCI experiment with online feedback. Through offline analysis of the collected data, we evaluated the capability of the present refined method in comparison with the original time-frequency-spatial methods. The enhanced performance in terms of classification accuracy was found for the proposed approach, with a mean accuracy rate of 91.1% for two subjects studied.     

Wavelet-based feature extraction and selection for classification of power system disturbances using support vector machines

This paper presents a new approach for the classification of the power system disturbances using support vector machines (SVMs). The proposed approach is carried out at three serial stages. Firstly, the features to be form the SVM classifier are obtained by using the wavelet transform and a few different feature extraction techniques. Secondly, the features exposing the best classification accuracy of these features are selected by a feature selection technique called as sequential forward selection. Thirdly, the best appropriate input vector for SVM classifier is rummaged. The input vector is started with the first best feature and incrementally added the chosen features. After the addition of each feature, the performance of the SVM is evaluated. The kernel and penalty parameters of the SVM are determined by cross-validation. The parameter set that gives the smallest misclassification error is retained. Finally, both the noisy and noiseless signals are applied to the classifier given above stages. Experimental results indicate that the proposed classifier is robust and has more high classification accuracy with regard to the other approaches in the literature for this problem.     

Application of tripolar concentric electrodes and prefeature selection algorithm for brain-computer interface.

For persons with severe disabilities, a brain-computer interface (BCI) may be a viable means of communication. Lapalacian electroencephalogram (EEG) has been shown to improve classification in EEG recognition. In this work, the effectiveness of signals from tripolar concentric electrodes and disc electrodes were compared for use as a BCI. Two sets of left/right hand motor imagery EEG signals were acquired. An autoregressive (AR) model was developed for feature extraction with a Mahalanobis distance based linear classifier for classification. An exhaust selection algorithm was employed to analyze three factors before feature extraction. The factors analyzed were 1) length of data in each trial to be used, 2) start position of data, and 3) the order of the AR model. The results showed that tripolar concentric electrodes generated significantly higher classification accuracy than disc electrodes.     

Application of Tripolar Concentric Electrodes and Prefeature Selection Algorithm for Brain–Computer Interface

For persons with severe disabilities, a brain-computer interface (BCI) may be a viable means of communication. Lapalacian electroencephalogram (EEG) has been shown to improve classification in EEG recognition. In this work, the effectiveness of signals from tripolar concentric electrodes and disc electrodes were compared for use as a BCI. Two sets of left/right hand motor imagery EEG signals were acquired. An autoregressive (AR) model was developed for feature extraction with a Mahalanobis distance based linear classifier for classification. An exhaust selection algorithm was employed to analyze three factors before feature extraction. The factors analyzed were 1) length of data in each trial to be used, 2) start position of data, and 3) the order of the AR model. The results showed that tripolar concentric electrodes generated significantly higher classification accuracy than disc electrodes.     

A geometry‐based two‐step method for nonlinear classification using quasi‐linear support vector machine

This paper proposes a two‐step method to construct a nonlinear classifier consisting of multiple local linear classifiers interpolated with a basis function. In the first step, a geometry‐based approach is first introduced to detect local linear partitions and build local linear classifiers. A coarse nonlinear classifier can then be constructed by interpolating the local linear classifiers. In the second step, a support vector machine (SVM) formulation is used to further implicitly optimize the linear parameters of the nonlinear classifier. In this way, the nonlinear classifier is constructed in exactly the same way as a standard SVM, using a special data‐dependent quasi‐linear kernel composed of the information of the local linear partitions. Numerical experiments on several real‐world datasets demonstrate the effectiveness of the proposed classifier and show that, in cases where traditional nonlinear SVMs run into overfitting problems, the proposed classifier is effective in improving the classification performance. © 2017 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

Particle swarm optimization-least squares support vector regression based forecasting model on dissolved gases in oil-filled power transformers

This paper presents a forecasting model based upon least squares support vector machine (LS-SVM) regression and particle swarm optimization (PSO) algorithm on dissolved gases in oil-filled power transformers. First, the LS-SVM regression model, with radial basis function (RBF) kernel, is established to facilitate the forecasting model. Then a global optimizer, PSO is employed to optimize the hyper-parameters needed in LS-SVM regression. Afterward, a procedure is put forward to serve as an effective tool for forecasting of gas contents in transformer oil. The application of the proposed model on actual transformer gas data has given promising results. Moreover, four other forecasting models, derived from back propagation neural network (BPNN), radial basis function neural network (RBFNN), generalized regression neural network (GRNN) and support vector regression (SVR), are selected for comparisons. The experimental results further demonstrate that the proposed model achieves better forecasting performance than its counterparts under the circumstances of limited samples.     

Brain-computer interfaces for 1-D and 2-D cursor control: designs using volitional control of the EEG spectrum or steady-state visual evoked potentials.

We have developed and tested two electroencephalogram (EEG)-based brain-computer interfaces (BCI) for users to control a cursor on a computer display. Our system uses an adaptive algorithm, based on kernel partial least squares classification (KPLS), to associate patterns in multichannel EEG frequency spectra with cursor controls. Our first BCI, Target Practice, is a system for one-dimensional device control, in which participants use biofeedback to learn voluntary control of their EEG spectra. Target Practice uses a KPLS classifier to map power spectra of 62-electrode EEG signals to rightward or leftward position of a moving cursor on a computer display. Three subjects learned to control motion of a cursor on a video display in multiple blocks of 60 trials over periods of up to six weeks. The best subject's average skill in correct selection of the cursor direction grew from 58% to 88% after 13 training sessions. Target Practice also implements online control of two artifact sources: 1) removal of ocular artifact by linear subtraction of wavelet-smoothed vertical and horizontal electrooculograms (EOG) signals, 2) control of muscle artifact by inhibition of BCI training during periods of relatively high power in the 40-64 Hz band. The second BCI, Think Pointer, is a system for two-dimensional cursor control. Steady-state visual evoked potentials (SSVEP) are triggered by four flickering checkerboard stimuli located in narrow strips at each edge of the display. The user attends to one of the four beacons to initiate motion in the desired direction. The SSVEP signals are recorded from 12 electrodes located over the occipital region. A KPLS classifier is individually calibrated to map multichannel frequency bands of the SSVEP signals to right-left or up-down motion of a cursor on a computer display. The display stops moving when the user attends to a central fixation point. As for Target Practice, Think Pointer also implements wavelet-based online removal of ocular artifact; however, in Think Pointer muscle artifact is controlled via adaptive normalization of the SSVEP. Training of the classifier requires about 3 min. We have tested our system in real-time operation in three human subjects. Across subjects and sessions, control accuracy ranged from 80% to 100% correct with lags of 1-5 s for movement initiation and turning. We have also developed a realistic demonstration of our system for control of a moving map display (http://ti.arc.nasa.gov/).     

基于小波分形和核判别分析的模拟电路故障诊断

提出了采用小波分形分析和核判别分析作为预处理器来实行特征提取的神经网络模拟电路故障诊断方法。这个诊断方法采用小波分形分析方法首先获取了故障响应信号的小波分形维特征,然后采用核判别分析进一步实施特征提取,最后将所获得的最优特征模式作为神经网络分类器的输入以进行故障诊断。仿真结果表明,本文提出的预处理方法能很好地获取故障响应信号的本质特征,并表现出了比其他特征提取方法更好的性能。并且,由此所构建的神经网络不但具有小的网络结构,而且能取得高的故障诊断正确率。     

基于蚁群优化算法的电力系统暂态稳定评估特征选择

暂态稳定评估的特征选择是一个典型的组合优化问题。针对该问题解的离散性特点,提出基于蚁群优化算法的特征选择方法。该方法以最小二乘支持向量机作为暂态稳定评估分类器,以分类错误率最低和特征选择比率最小为优化目标,通过二进制编码形式的蚁群优化算法实现特征的选择。这样能选择出计及分类器特性的最优特征子集,减少了特征维数,提高了分类正确率。通过对综合程序EPRI-36节点系统的仿真计算,验证了该方法的有效性。     

基于最小二乘支持向量机的改进型GIS局部放电识别方法

利用最小二乘支持向量机（1east square-support vector machine,LS．SVM）的方法识别气体绝缘组合电器局部放电的类型。在信号的快速分类后利用相位分布的局部放电特征谱图的特征参数作为LS．SVM识别放电类型的依据;信号快速分类处理部分主要包括信号时间一频率特性提取部分和模糊C-均值聚类2...     

Cognitive tasks for driving a brain-computer interfacing system: a pilot study

Different cognitive tasks were investigated for use with a brain-computer interface (BCI). The main aim was to evaluate which two of several candidate tasks lead to patterns of electroencephalographic (EEG) activity that could be differentiated most reliably and, therefore, produce the highest communication rate. An optimal signal processing method was also sought to enhance differentiation of EEG profiles across tasks. In ten normal subjects (five male), aged 29-54 years, EEG activity was recorded from four channels during cognitive tasks grouped in pairs, and performed alternately. Four imagery tasks were: spatial navigation around a familiar environment; auditory imagery of a familiar tune; and right and left motor imagery of opening and closing the hand. Signal processing methodology included autoregressive (AR) modeling and classification based on logistic regression and a nonlinear generative classifier. The highest communication rate was found using the navigation and auditory imagery tasks. In terms of classification performance and, hence, possible communication rate, these results were significantly better (p < 0.05) than those obtained with the classical pairing of motor tasks involving imaginary movements of the left and right hands. In terms of EEG data analysis, a nonlinear classification model provided more robust results than a linear model (p < 0.01), and a lower AR model order than those used in previous work was found to be effective. These findings have implications for establishing appropriate methods to operate BCI systems, particularly for disabled people who may experience difficulty with motor tasks, even motor imagery.     

特征可分性显式建模的跨数据库脑电解码方法

目前,在运动想象解码领域,研究主要集中在被试依赖和被试独立解码两种方法上。然而,这两种解码方式在脑机接口（BCI）系统的实际使用中存在较大局限性。被试依赖和被试独立解码都依赖于同一中心数据集,当解码模型应用于其他中心的数据集时,性能将显著下降,无法满足BCI系统跨中心使用的需求。为提升运动想象脑电跨数据库解码性能,基于领域泛化的方法框架,提出了一种基于Fisher准则正则化的稀疏选择模型。在最小绝对值收缩和选择算子（LASSO）模型的基础上,引入Fisher准则正则项,以在特征选择过程中显式建模特征的可分性。这有助于提高领域泛化的表示学习能力,从而增强分类模型在不同数据集上的泛化性能。采用两个公开的运动想象脑电数据集,并使用滤波器组共空间模式（FBCSP）和多时频共空间模式（MTFCSP）两种特征提取方法,验证了所提方法的有效性, 进一步使用自采集的数据也证实了该方法在实际应用中同样有效。与现有的方法相比,所提方法取得了最高平均分类准确率,达到67.26%。实验结果表明,所提方法在运动想象跨数据库解码中具有更好的泛化能力、更高的特征可分性、更好的鲁棒性。所提方法有望促进BCI系统跨中心使用,提高通用性。     

集成学习在脑机接口分类算法中的研究

提出了一种基于独立分量分析的支持向量机集成学习算法,用于脑机接口中P300字符识别.首先由P300信号分解出独立分量,基于Bagging算法送入支持向量机基分类器进行集成学习,通过平均的方法获得对应类别概率进行分类决策.数据来源于P300字符拼写实验,不同导联和不同序列的分类结果表明,该分类算法学习效率和分类精度高,全...     

Frequency component selection for an EEG-based brain to computer interface.

A new communication channel for severely handicapped people could be opened with a direct brain to computer interface (BCI). Such a system classifies electrical brain signals online. In a series of training sessions, where electroencephalograph (EEG) signals are recorded on the intact scalp, a classifier is trained to discriminate a limited number of different brain states. In a subsequent series of feedback sessions, where the subject is confronted with the classification results, the subject tries to reduce the number of misclassifications. In this study the relevance of different spectral components is analyzed: 1) on the training sessions to select optimal frequency bands for the feedback sessions and 2) on the feedback sessions to monitor changes.     

基于迁移学习多层级融合的运动想象 EEG 辨识算法

为了准确获取运动想象脑电信号的全局特征和个体间的共性特征,进而提高其分类准确率和模型鲁棒性,提出一种参 数共享迁移学习的融合卷积神经网络算法。 首先把源域上训练完成的网络逐层迁移至目标网络以获取最佳迁移层。 其次,在 迁移层后分别连接不同数量的卷积-池化块构成 4 个不同深度的卷积网络,并将其并行融合后连接分类器得到分类结果。 利用 BCI 竞赛 IV Datasets 2a 对提出方法进行实验分析。 结果显示,使用 100%和 50%样本时所有受试者的平均辨识率分别为 80. 85%和 78. 9%,验证了提出方法在全局特征提取上的有效性小样本问题上的优势。     

基于 KPCA-SVM 的表面肌电信号疲劳分类研究

为了提高手臂疲劳模型识别的准确率,本研究在常用时域、频域特征的基础上,引入了时频域、非线性和参数模型特征,提取3通道的表面肌电信号,构成特征集合.特征降维一般分为特征提取以及特征选择,分别采用特征提取中的主成分分析(PCA),核主成分分析(KPCA)方法以及特征选择中的互信息(MI)度量方法进行特征降维,采用支持向量机(SVM)和K近邻(KNN)作为分类器,通过3种降维方法分与SVM和KNN的不同组合构成疲劳分类模型.结果 表明,KPCA与SVM的组合模型对于疲劳的正确识别率最高达到99％,高于其他组合算法.