基于集合经验模态分解的脑电信号高阶张量特征提取

为了实现脑机接口系统需要有效的特征提取算法。针对二维主成分分析(2DPCA)的特征提取方法忽略脑电信号(EEG)频域特征的缺点和基于小波分解构建EEG高阶张量时小波参数难以确定的局限性,提出了基于集合经验模态分解(EEMD)构建高阶张量结合多线性主成分分析(MPCA)降维的特征提取方法。设计了3种不同特征提取方法的对照实验,并结合Fisher线性判别分析分类方法取得分类准确率。结果表明:新提出的方法相比基于小波分解构建高阶张量结合MPCA进行降维和2DPCA的特征提取方法,平均识别准确率分别提高4.75%和2.6%,且识别准确率的方差分别减小72.69%和23.86%。该方法在提高单次运动想象脑电信号识别准确率的同时还具有更好的适用性,为实现运动想象脑电信号解码奠定了基础。     

基于共空间模式和均匀流形投影的运动想象脑电信号识别方法

运动想象脑电信号的识别与分类问题一直是脑机领域研究的热点问题。针对此问题,使用区别传统线性降维方法的流形学习方法,将共空间模式算法与均匀流形投影算法相结合,充分利用了脑电信号中的非线性特征,对运动想象脑电信号进行了特征提取和数据降维,并使用KNN分类器进行了分类,对分类效果做出了评价;将降维前后的数据分类结果进行对比,说明了数据降维的优点和必要性;进一步讨论了降维结果在数据可视化方面的表现。发现经过数据降维的特征数据的可视化效果明显优于未经过降维的数据,进一步提出了一种基于共空间模式和均匀流形投影的新型脑电信号识别方法,对进行脑电信号深度剖析。挖掘脑电信号非线性特征提供了参考价值,同时也在数据流形分布以及数据可视化的角度为运动想象脑电信号识别提供了新思路。     

改进的多尺度熵算法及其情感脑电特征提取性能分析

进行了用多尺度熵提取情感脑电特征的研究,针对传统的基于多尺度熵的特征提取算法在粗粒化过程中存在重要信息丢失以及尺度选择过小造成特征不显著、尺度过大造成计算过度复杂的问题,提出了一种改进的多尺度熵算法。该改进算法通过自适应多尺度熵中本征模态函数的个数确定尺度,而且为突出脑电信号的微小变化,对脑电信号进行自适应二值化处理,充分挖掘特征并降低算法复杂性。利用Deap国际标准情感分析数据库并基于优化支持向量机分类器实现了情感脑电特征识别,进行了改进算法与传统多尺度熵算法的性能比较。结果表明,改进算法的分类准确率较传统多尺度熵算法提高了12.33%,较自适应多尺度熵算法提高了7.27%,表明改进算法是一种有效的脑电特征提取算法。     

基于GST-ECNN的运动想象脑电信号识别方法

在对脑电信号的解码研究中,存在着现有时频分析方法对高频信号处理能力有限,多通道信号信息冗余,常用卷积神经网络分类器ReLU激活函数受学习速率的影响较大,对不同层采用相同的正则化很难获得满意结果等问题。为此,提出了一种基于广义S变换特征提取和增强卷积神经网络分类相结合的方法,同时提出一种结合Relief算法和向前选择搜索策略的包裹式方法进行通道选择。结果表明,提出的方法利用较少的信号通道,具有更强的特征提取和分类的能力,在第Ⅳ届BCI的数据集I上取得最高98.44±1.5%的分类准确率,高于其他现有算法。该方法良好的分类性能不仅减少了计算消耗,也有效提高了分类准确率,对脑电信号特征提取和分类具有一定的参考意义。     

基于支持向量特征筛选方法的想象动作识别

引入了支持向量特征筛选方法,以克服基于想象动作诱发脑电特征的脑-机接口识别中,由于特征维度较高而训练数据有限、不易获得理想识别效果的问题.支持向量特征筛选方法采用扰动支持向量机代价函数的方法测量特征的分类贡献度,进而建立特征序贯指数,以递归方法进行特征排序和优化筛选.对14例受试者的左右上肢想象动作诱发脑电信号进行分析,提取6类246维特征,采用支持向量递归筛选方法进行特征优选,利用支持向量机对优选特征进行识别,结果显示,支持向量递归筛选得到的优选特征可显著提高识别正确率.研究表明,支持向量特征筛选可以降低无效特征干扰,提高分类器效率,适用于特征维度较高的脑-机接口任务识别.     

基于集成分类器的泡罩包装药品缺陷识别

目的 针对药品生产包装过程中常出现缺陷泡罩包装药品的问题,研究一种基于多特征构建与集成分类器的泡罩包装药品缺陷识别方法.方法 该方法通过集成2个不同的分类器算法分别对药品图像类别进行预测,并采用联合判定函数对2个预测输出值进行联合决策,得到最终分类结果.第1个分类器模型通过将图像转化到HSV颜色空间,分割出泡罩区域和药片区域,进行特征设计,并在提取多项特征参数后构建BP神经网络分类算法给定药品类别预测.第2个分类器模型应用多层卷积神经网络取代传统算法对图像特征进行提取,并输出药品图像类别的预测值.根据2个分类器的性能进行算法集成,构成最终集成分类器.结果 实验结果表明,该集成分类模型对数据集中泡罩包装药品图像进行分类识别测试,准确率达97％以上.结论 集成分类模型不仅提高了单一分类器的识别准确率,也具有更佳的稳定性.该方法取得了卓越的分类效果,具有较高应用性.     

支持向量机集成和特征选择联合算法

提出了两种基于支持向量机集成和特征选择联合算法。联合算法的核心思想是在构建基础分类器的同时选择有效特征。通过对实测舰船数据和公共数据的识别实验,证明了两种算法都可以用于舰船目标识别。算法一更适用于冗余特征较多的情况。算法二在对舰船目标识别时,选择的特征数目降低为原来特征数目的30%,正确分类率比单个支持向量机高近10%。     

仿射变换下的分类识别

特征提取和分类识别是统计模式识别中两大关键步骤。显然,不同的特征提取方法与不同的分类器相结合,识别性能往往是不同的。从微分几何的角度出发,可将特征系数的获得看成线性几何变换,即仿射变换,据此在黎曼空间提出一种基于黎曼度量的分类识别方法。通过对经典最近邻分类器的线性加权,达到更有效地分类识别。不但在理论上将特征系数提取与分类识别合理的结合起来,而且由人脸识别实验表明该方法的有效性,该方法比传统方法的识别率有约 3%的提高。     

基于残差图卷积网络的运动想象任务分类

为了提高运动想象脑机接口任务分类的准确性,需要增强运动想象脑电信号的解码精度。利用脑电的空间分布及多导联信息关联,构建图神经网络,提出了一种基于残差图卷积的运动想象任务分类模型。将残差学习嵌入深度图卷积神经网络,改善网络退化;并将分层图池化方法加入模型,充分提取运动想象脑电特征信息,提高分类准确率。该模型在两个脑机接口竞赛数据集上分别取得93.84%和96.39%的平均分类准确率以及0.917 1和0.953 5的平均Kappa系数。仿真结果表明,模型能有效提高运动想象脑机接口任务分类精度,且具有较好的泛化能力。     

基于排列熵与多重分形指数结合的特征提取算法在情感识别中的应用

通过对脑电信号的熵分析,进行了情感识别研究,并根据脑电信号的非线性特性以及多重分形特性的特点,提出了一种排列熵与多重分形指数相结合的情感脑电特征提取算法。该算法采用排列熵、Hurst指数、质量指数和奇异谱宽度相结合,实现情感脑电的特征提取,采用支持向量机(SVM))实现情感识别。结果显示,该算法两两情感识别,测试集最高正确率达到92.8%,除去激动对可怕外,正确率均在80%以上;与单独使用排列熵和分形指数特征的方法相比,最高正确率分别提高41.9%和31.2%。进一步分析了对积极和消极两类情感状态的识别效果,测试集平均正确率为78.3%,比排列熵与多重分形特征,测试集正确率分别提高了26.7%和1.6%。结果表明,基于排列熵与多重分形指数相结合的特征提取算法,能够充分挖掘脑电信号的非线性特性与多重分形特征信息,是一种有效的情感脑电特征提取算法。     

Classification of Electroencephalogram Signals Using LSTM and SVM Based on Fast Walsh-Hadamard Transform

Classification of electroencephalogram (EEG) signals for humans can be achieved via artificial intelligence (AI) techniques. Especially, the EEG signals associated with seizure epilepsy can be detected to distinguish between epileptic and non-epileptic regions. From this perspective, an automated AI technique with a digital processing method can be used to improve these signals. This paper proposes two classifiers: long short-term memory (LSTM) and support vector machine (SVM) for the classification of seizure and non-seizure EEG signals. These classifiers are applied to a public dataset, namely the University of Bonn, which consists of 2 classes –seizure and non-seizure. In addition, a fast Walsh-Hadamard Transform (FWHT) technique is implemented to analyze the EEG signals within the recurrence space of the brain. Thus, Hadamard coefficients of the EEG signals are obtained via the FWHT. Moreover, the FWHT is contributed to generate an efficient derivation of seizure EEG recordings from non-seizure EEG recordings. Also, a k-fold cross-validation technique is applied to validate the performance of the proposed classifiers. The LSTM classifier provides the best performance, with a testing accuracy of 99.00%. The training and testing loss rates for the LSTM are 0.0029 and 0.0602, respectively, while the weighted average precision, recall, and F1-score for the LSTM are 99.00%. The results of the SVM classifier in terms of accuracy, sensitivity, and specificity reached 91%, 93.52%, and 91.3%, respectively. The computational time consumed for the training of the LSTM and SVM is 2000 and 2500 s, respectively. The results show that the LSTM classifier provides better performance than SVM in the classification of EEG signals. Eventually, the proposed classifiers provide high classification accuracy compared to previously published classifiers.     

Human Emotions Classification Using EEG via Audiovisual Stimuli and AI

Electroencephalogram (EEG) is a medical imaging technology that can measure the electrical activity of the scalp produced by the brain, measured and recorded chronologically the surface of the scalp from the brain. The recorded signals from the brain are rich with useful information. The inference of this useful information is a challenging task. This paper aims to process the EEG signals for the recognition of human emotions specifically happiness, anger, fear, sadness, and surprise in response to audiovisual stimuli. The EEG signals are recorded by placing neurosky mindwave headset on the subject’s scalp, in response to audiovisual stimuli for the mentioned emotions. Using a bandpass filter with a bandwidth of 1–100 Hz, recorded raw EEG signals are preprocessed. The preprocessed signals then further analyzed and twelve selected features in different domains are extracted. The Random forest (RF) and multilayer perceptron (MLP) algorithms are then used for the classification of the emotions through extracted features. The proposed audiovisual stimuli based EEG emotion classification system shows an average classification accuracy of 80% and 88% using MLP and RF classifiers respectively on hybrid features for experimental signals of different subjects. The proposed model outperforms in terms of cost and accuracy.     

Classification of focal and nonfocal EEG signals using ANFIS classifier for epilepsy detection

The electroencephalogram (EEG) is the frequently used signal to detect epileptic seizures in the brain. For a successful epilepsy surgery, it is very essential to localize epileptogenic area in the brain. The signals from the epileptogenic area are focal signals and signals from other area of the brain region nonfocal signals. Hence, the classification of focal and nonfocal signals is important for locating the epileptogenic area for epilepsy surgery. In this article, we present a computer aided automatic detection and classification method for focal and nonfocal EEG signal. The EEG signal is decomposed by Dual Tree Complex Wavelet Transform (DT‐CWT) and the features are computed from the decomposed coefficients. These features are trained and classified using Adaptive Neuro Fuzzy Inference System (ANFIS) classifier. The proposed system achieves 98% sensitivity, 100% specificity, and 99% accuracy for EEG signal classification. The experimental results are presented to show the effectiveness of the proposed classification method to classify the focal and nonfocal EEG signals. © 2016 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 26, 277–283, 2016     

Brainwave Classification for Character-Writing Application Using EMD-Based GMM and KELM Approaches

A brainwave classification, which does not involve any limb movement and stimulus for character-writing applications, benefits impaired people, in terms of practical communication, because it allows users to command a device/computer directly via electroencephalogram signals. In this paper, we propose a new framework based on Empirical Mode Decomposition (EMD) features along with the Gaussian Mixture Model (GMM) and Kernel Extreme Learning Machine (KELM)-based classifiers. For this purpose, firstly, we introduce EMD to decompose EEG signals into Intrinsic Mode Functions (IMFs), which actually are used as the input features of the brainwave classification for the character-writing application. We hypothesize that EMD along with the appropriate IMF is quite powerful for the brainwave classification, in terms of character applications, because of the wavelet-like decomposition without any down sampling process. Secondly, by getting motivated with shallow learning classifiers, we can provide promising performance for the classification of binary classes, GMM and KELM, which are applied for the learning of features along with the brainwave classification. Lastly, we propose a new method by combining GMM and KELM to fuse the merits of different classifiers. Moreover, the proposed methods are validated by using the volunteer-independent 5-fold cross-validation and accuracy as a standard measurement. The experimental results showed that EMD with the proper IMF achieved better results than the conventional discrete wavelet transform (DWT) feature. Moreover, we found that the EMD feature along with the GMM/KELM-based classifier provides the average accuracy of 77.40% and 80.10%, respectively, which could perform better than the conventional methods where we use DWT along with the artificial neural network classifier in order to get the average accuracy of 80.60%. Furthermore, we obtained the improved performance by combining GMM and KELM, i.e., average accuracy of 80.60%. These outcomes exhibit the usefulness of the EMD feature combining with GMM and KELM based classifiers for the brainwave classification in terms of the Character-Writing application, which do not require any limb movement and stimulus.     

An automatic channel selection method based on the standard deviation of wavelet coefficients for motor imagery based brain–computer interfacing

The redundant data in multichannel electroencephalogram (EEG) signals significantly reduces the performance of brain–computer interface (BCI) systems. By removing redundant channels, a channel selection strategy increases the classification accuracy of BCI systems. In this work, a novel channel selection method (stdWC) based on the standard deviation of wavelet coefficients across channels is proposed to identify Motor Imagery (MI) based EEG signals. The wavelet coefficients are calculated by employing a Continuous Wavelet Transform (CWT) filter bank to decompose each trial from the EEG channel. The wavelet coefficient's standard deviation values are obtained across the channels, and these values are then sorted to determine the EEG channels with the highest standard deviation values. The channels with the largest wavelet coefficient divergence are chosen. MI trials are then spatially filtered with the Common Spatial Pattern (CSP), and CWT filter bank-based 2D images are generated from the spatially filtered trials. These images are then classified using a unique nine-layered convolutional neural network (CNN) model that combines two feature maps acquired with differing filter sizes. The proposed framework (stdWC-CSP-CNN) is evaluated using kappa score and classification accuracy on two publically accessible datasets (BCI Competition III dataset IVa and BCI Competition IV dataset 2a). The suggested framework achieved a mean test classification accuracy of 88.8% for dataset IVa from BCI Competition III and 75.03% for dataset 2a from BCI Competition IV, according to the results. The proposed channel selection method outperforms the other channel selection methods examined, according to the results. By rejecting redundant channels, the whole framework can improve the performance of MI-based BCIs.     

Random forest and rotation forest ensemble methods for classification of epileptic EEG signals based on improved 1D‐LBP feature extraction

In this study, an efficient method for extracting and selecting features of unrefined Electroencephalogram (EEG) signals according to the one‐dimensional local binary pattern (1D‐LBP) is presented. Considering that taking a correct decision on various issues particularly in the field of diagnosing diseases, such as epilepsy, is of paramount importance, a functional approach is designed to extract the optimal features of EEG signals. The proposed method is comprised of two main steps: First, extraction and selection of features is performed based on a novel improved 1D‐LBP model followed by data normalization through principal component analysis (PCA); as combining 1D‐LBP neighboring models and PCA (1D‐LBP^c2p) method. The second step includes classification using two of the best ensemble classification algorithms, that is, random forest and rotation forest. A comparative evaluation is performed between the proposed methods and 13 distinct reported approaches including uniform and non‐uniform 1D‐LBP. The results are demonstrating that the combining method presented in our approaches has superiority along with efficiency by providing higher accuracy compared to the other models and classifiers. The proposed method in this paper can be considered as a new method for feature extraction and selection of other kinds of EEG signals and data sets.     

三种鱼类发声信号频带能量特征提取与分类研究

海洋渔业资源的开发和利用对经济鱼类的分类识别提出了迫切的技术需求。根据鱼类的不同发声特征,文章采用有监督机器学习方法实现了三个不同鱼种发声信号的分类。基于小波包分解技术提取了黄花鱼、大米鱼和黄姑鱼三种鱼类发声信号的频带能量特征,并利用不同的分类器进行分类。结果表明：三种鱼的发声信号频率主要集中在300～800 Hz之间,基于小波包分解的频带能量特征可实现3种鱼的有效分类。其中,线性判别分类器和随机子空间判别分类器的分类效果较好。该方法可为海洋渔业资源的开发和利用提供服务。     

Picture-Induced EEG Signal Classification Based on CVC Emotion Recognition System

Emotion recognition systems are helpful in human–machine interactions and Intelligence Medical applications. Electroencephalogram (EEG) is closely related to the central nervous system activity of the brain. Compared with other signals, EEG is more closely associated with the emotional activity. It is essential to study emotion recognition based on EEG information. In the research of emotion recognition based on EEG, it is a common problem that the results of individual emotion classification vary greatly under the same scheme of emotion recognition, which affects the engineering application of emotion recognition. In order to improve the overall emotion recognition rate of the emotion classification system, we propose the CSP_VAR_CNN (CVC) emotion recognition system, which is based on the convolutional neural network (CNN) algorithm to classify emotions of EEG signals. Firstly, the emotion recognition system using common spatial patterns (CSP) to reduce the EEG data, then the standardized variance (VAR) is selected as the parameter to form the emotion feature vectors. Lastly, a 5-layer CNN model is built to classify the EEG signal. The classification results show that this emotion recognition system can better the overall emotion recognition rate: the variance has been reduced to 0.0067, which is a decrease of 64% compared to that of the CSP_VAR_SVM (CVS) system. On the other hand, the average accuracy reaches 69.84%, which is 0.79% higher than that of the CVS system. It shows that the overall emotion recognition rate of the proposed emotion recognition system is more stable, and its emotion recognition rate is higher.     

基于融合特征的短语音汉语声调自动识别方法

提出一种基于韵律特征(基频、时长)和梅尔倒谱系数(Mel-Frequency Cepstral Coefficient,MFCC)特征的融合特征进行短语音汉语声调识别的方法,旨在利用两种特征的优势提高短语音汉语声调识别率。该融合特征包括7个根据不同模型得到的韵律特征和统计参数以及4个从每个音段的梅尔倒谱系数计算得来的对数化后验概率,使用高斯混合模型表示4个声调的倒谱特征的分布。实验分两步:第一步,将基于韵律特征和倒谱特征的分类器在决策阶段混合起来进行声调分类,分别赋予两个分类器权重,计算倒谱特征和韵律特征在声调分类任务中的权重;第二步,将基于字的韵律特征和基于帧的倒谱特征结合起来生成融合特征的超向量,使用融合特征进行汉语声调识别,根据准确率、未加权平均召回率(Unweigted Average Recall,UAR)和科恩卡帕(Cohen’s Kappa)系数3个指标,比较并评估5种分类器(两种设置的高斯混合模型,后向传播神经网络,支持向量机和卷积神经网络(Convolutional Neural Network,CNN))在不平衡数据集上的分类效果。实验结果表明:(1)倒谱特征方法能够提高汉语声调的识别率,该特征在总体分类任务中的权重为0.11;(2)基于融合特征的深度学习(CNN)方法对声调的识别率最高,为87.6%,与高斯混合模型的基线系统相比,提高了5.87%。该研究证明了倒谱特征法能够提供与韵律特征法互补的信息,从而提高短语音汉语声调识别率;同时,该方法可以运用到韵律检测和副语言信息检测等相关研究中。