基于功率谱峰值及时变线性分类算法的运动意识分类

背景:脑电信号的特征提取是脑机接口系统中一个重要的环节,如何快速有效地提取反映大脑意识任务状态的脑电特征是进行分类、正确解读意识任务的关键。目前,提取脑电信号特征通常采用功率谱密度估计、自回归模型和小波变换等方法,这些特征都是以脑电信号的线性化为前提,上述方法不能很好地反映出大脑的非线性动力学性质。目的:分析脑电信号功率谱峰值在识别左右手想象运动中的作用。方法:采用脑机接口2003竞赛中Graz科技大学提供的脑电数据,用小波包分解获取8～24Hz脑电信号,计算C3,C4电极脑电信号的功率谱峰值作为脑电特征向量,运用时变线性分类算法对运动意识任务运行分类。结果与结论:对140次实验的测试样本进行数据分析,最大分类正确率可达89.29%,最大互信息和信噪比分别为0.6269bit和1.3848。C3,C4电极8～24Hz脑电信号功率谱峰值能很好地反映左右手运动想象脑电特征的变化,与事件相关去同步/事件相关同步现象变化一致,可在线识别左右手想象运动。     

基于离散小波变换提取脑机接口中脑电特征

在脑机接口中，针对脑电特征提取利用单一种类信息、使用数据量大、分类性能较差等缺点，提出一种新颖的基于离散小波变换的方法。分析了小波变换特征提取的特点和特征表示方式，用Daubechies类db4小波函数对脑电信号进行6层分解，抽取小波变换各子带关键的部分逼近系数、小波系数、小波子带系数均值组成特征向量。以分类正确率为指标检验了提取特征的性能。实验结果表明，这种方法能够利用少量数据提取脑电信号本质特征，具有较高的分类性能，为利用脑电识别人的不同意图提供了快速而有效的手段。     

基于小波包和共同空间模型的运动想象脑电信号特征提取算法

脑-机接口(brain-computer interface,BCI)为无法进行交流的人们提供了一种新的交流方式。传统的基于频率特征的脑电信号(electroencephalogram,EEG)特征提取方法只提取每个通道的能量特征,而忽略了不同通道之间的相关性信息。为了获得更好的特征提取结果,本研究采用了基于小波包和共同空间模型(common space pattern, CSP)的脑电信号特征提取方法。首先,在利用小波包对脑电信号分解前,对相关通道和频带进行辨别,提取运动想象脑电μ律和β节律,然后利用CSP算法进行空间滤波提取特征,选取相关节点计算小波包能量,最后通过支持向量机(support vector machine, SVM)将脑电信号分为左右手两种特征。为了验证本研究算法的可行性与有效性,在BCI竞赛数据集上进行了相应的实验,分类结果表明,所提出的特征提取算法能够有效提取运动想象特征,具有较高的分类精度。     

基于自回归小波包熵特征融合算法的情感识别研究

针对提高情感识别正确率这一国际开放问题,本文提出了一种基于小波包熵和自回归模型相结合的脑电信号特征提取算法。自回归过程能最大程度逼近脑电信号,用很少的自回归参数提供丰富的谱信息。小波包熵反映脑电信号在各个频带中的谱能量分布情况。将二者结合,能够更好地体现脑电信号的能量特征。本文基于核主成分分析方法,实现了脑电信号特征提取融合。课题组采用情感脑电国际标准数据集(DEAP),选取6类情感状态以本文算法进行情感识别。结果显示,本文算法情感识别正确率均在90%以上,最高情感识别正确率可达99.33%。本文的研究结果表明,该算法能够较好地提取脑电信号情感特征,是一种有效的情感特征提取算法。     

基于脑电样本熵和小波熵的麻醉深度监测

目的:通过研究全麻手术病人的脑电信号特征,从分类准确率、算法难易程度、计算时间等方面讨论样本熵和小波熵算法在麻醉深度监测中的应用。方法:基于脑电信号的非线性和不稳定性,采用两种非线性动力学分析方法(样本熵和小波熵)对30例全麻手术病人的脑电信号进行特征提取,并对每位病人清醒状态、轻度麻醉状态和中度麻醉状态下的脑电信号的样本熵和小波熵进行差异分析。结果:不同麻醉状态下的脑电信号的样本熵和小波熵均有明显差异。相同脑电信号的样本熵的变化阈值较小波熵的变化阈值大。结论:样本熵和小波熵算法均可以作为麻醉深度监测的有效指标。从分类准确率、算法难易程度和计算时间等方面考虑,使用样本熵算法的效果优于小波熵算法。     

基于核函数极限学习机和小波包变换的EEG分类方法

目的为实现运动功能障碍患者的运动意愿,基于脑-机接口(brain-computer interface,BCI)的康复训练技术是近年来的研究热点。脑-机接口的关键技术是快速准确地识别出与运动想象相关的脑电模式。针对脑电信号非平稳及个性化差异等特点,利用小波包理论和核函数极限学习机(extreme learning machine,ELM)方法,提出一种自适应的特征分类方法来提高脑电信号的分类识别率。方法由于小波包存在着频带交错的现象,所以首先利用距离准则将自适应提取的最优小波包的平均能量作为特征向量,并采用核函数ELM方法进行分类。最后利用BCI竞赛数据进行了脑电信号特征分类的仿真研究,并对不同算法的分类识别率进行仿真分析。结果自适应特征分类方法对用于实验的脑电数据的平均分类识别率达到97.6%,对比ELM、神经网络(back propagation,BP)和支持向量机(support vector machine,SVM)分类方法,核函数ELM方法在分类时间和识别精度上效果最佳。结论本文提出的脑电信号分类方法取得了较高的分类识别率,适用于脑电信号的分类应用。     

基于能量特征的脑电信号上肢运动意图智能识别

传统的对运动员上肢运动意图识别方法,没有对采集获得的大量脑电信号进行平滑滤波,存在较多毛刺干扰,导致识别准确率和识别率不高。我们提出一种基于能量特征的脑电信号上肢运动意图智能识别方法,采用快速傅里叶变换方法对采集获得的运动障碍患者脑电信号进行频率分析,获得患者脑电信号中的μ波和β波频率分布规律,找到脑电信号噪声所在频段;并采用Daubechies小波将患者脑电信号进行3阶分解,将患者脑电信号中低频部分的小波系数进行归零处理后,再进行脑电信号重构,即可消除低频脑电信号中的噪声干扰;在此基础上,采用小波包系数分析患者脑电能量,实现患者脑电信号能量特征提取;基于脑电信号能量特征,采用马氏距离判别方法对上肢运动意图进行智能识别。实验结果显示,所提方法能够去除原始脑电信号中的"毛刺"干扰,平均识别率结果为88. 6%,识别准确率和识别率较高。     

引入关联维的表面肌电信号的特征提取

考虑到表面肌电信号的非平稳特性,本研究在传统特征提取的基础上,又引入了非线性动力学中的关联维,通过小波系数的标准差和关联维重新构造特征向量,将其送入自组织映射网络对拇指弯曲、食指弯曲和无名指弯曲三种手势动作进行分类识别。结果表明:引入关联维的特征提取方法其识别正确率明显优于传统的小波变换的方法。可见,关联维作为一种新的特征参数,为肌电信号的特征提取提供了新的思路。     

基于空间频率与时间序列信息的多类运动想象脑电分类

结合共同空间模式（CSP）、离散小波变换（DWT）和长短期记忆网络（LSTM）方法,提出一种基于空间频率与时间序列信息的多类运动想象脑电特征提取方法。首先利用滑动矩形窗获得时间序列脑电信号,并采用DWT从每一段脑电信号提取运动想象脑电相关的子带小波系数,其次将小波系数通过一对多CSP进一步特征提取,得到的特征作为LSTM的输入,然后对LSTM的时间序列输出在时间步上进行平均,最后使用Softmax分类器进行分类。实验结果显示,新算法取得92.23%的准确率,相比CSP特征以及结合频率或时间序列信息的CSP特征有较大提升,表明空间、频率、时间序列信息的互补性和有效性。     

基于TQWT的癫痫脑电信号的识别

针对癫痫脑电(EEG)信号的识别问题,提出了一种基于可调品质因子小波变换(TQWT)的脑电特征提取方法。首先,利用TQWT将EEG信号进行分解,得到各个小波子波带;然后,根据癫痫异常波对应的频率范围,合理的选择小波子波带进行重构,提取有效值和峰峰值构成特征分量;最后,采用支持向量机进行分类。将所提出方法应用于癫痫脑电信号的识别中,以德国伯恩大学癫痫研究中心采集的典型脑电数据进行验证。实验分析结果表明,所提出的特征提取方法对正常和癫痫发作期EEG信号的分类准确率可达98%。     

Adaptive subject-based feature extraction in brain-computer interfaces using wavelet packet best basis decomposition

In this paper we discuss a subject-based feature extraction method using wavelet packet best basis decomposition (WPBBD) in brain-computer interfaces (BCIs). The idea is to employ the wavelet packet best basis algorithm to adapt to each subject separately. Firstly, original electroencephalogram (EEG) signals are decomposed to a given level by wavelet packet transform. Secondly, for each subject, the best basis algorithm is used to find the best-adapted basis for that particular subject. Finally, subband energies contained in the best basis are used as effective features. Adaptive and specific features of a subject are so obtained. Three different motor imagery tasks of six subjects are discriminated using the above features. Experiment results show that the subject-based adaptation method yields significantly higher classification performance than the non-subject-based adaptation and non-adaptive approaches.     

癫痫脑电特征波的综合检测分类方法研究

本文将小波变换、人工神经网络、专家规则判据等多种检测方法有机地结合起来 ,用于癫痫脑电特征波的检测与分类 ,以充分发挥不同方法的优势。这种综合检测分类方法是先将预处理的多导脑电时间序列经小波变换将脑电中癫痫特征波在不同尺度下分离出来 ,再对选出的癫痫嫌疑波进行特征参数提取 ,然后把特征参数送入已经训练好的人工神经网络进行分类识别 ,最后再由专家规则判断筛选并作出检测分类统计报告。研究表明 ,该方法具有很好的信号特征提取和屏蔽随机噪声能力 ,获得了较好的检出率 ;尤其适合于非平稳、非线性生物医学信号的检测分类 ,值得进一步深入研究     

基于小波包分解的不同状态下脑电信号分析

本文针对脑电信号的非平稳性,引入小波包分解理论处理临床脑电.根据脑电信号的不同节律特性,提出应用小波包分解构造不同频率特性的时变滤波器,提取脑电信号不同节律的动态特性,并由此构造各种节律的动态脑电地形图.为了研究不同脑功能状态下脑电信号各种节律的动态特性,文中对两组不同的临床脑电数据进行分析,比较两种状态下各种节律的动态特性.实验结果表明,利用小波包分解对脑电信号进行滤波,能够有效提取临床脑电不同节律的动态特性,为分析脑电信号提供一条新的途径.     

A Wavelet Packet-Based Algorithm for the Extraction of Neural Rhythms

Neural rhythms are associated with different brain functions and pathological conditions. These rhythms are often clinically relevant for purposes of diagnosis or treatment, though their complex, time-varying features make them difficult to isolate. The wavelet packet transform has proven itself to be versatile and effective with respect to resolving signal features in both time and frequency. We propose a signal analysis technique, called neural rhythm extraction (NRE) that incorporates wavelet packet analysis along with a threshold-based scheme for separating rhythmic neural features from non-rhythmic ones. We applied NRE to rat in vitro intracellular recordings and human scalp electroencephalogram (EEG) signals, and were able to isolate and classify individual neural rhythms in signals containing large amplitude spikes and other artifacts. NRE is capable of discriminating signal features sharing similar time or frequency localization, as well as extracting low-amplitude, low-power rhythms otherwise masked by spectrally dominant signal components. The algorithm allows for independent retention and reconstruction of rhythmic features, which may serve to enhance other analysis techniques such as independent component analysis (ICA), and aid in application-specific tasks such as detection, classification or tracking.     

基于CSSD和SVM的抑郁症脑电信号分类

从EEG脑电信号中提取与疾病相关的信息以实现对抑郁症的自动诊断。首先采用共空域子空间分解(CSSD)方法,对躁狂型抑郁症患者与健康人两组的16导联脑电信号进行特征提取,然后用支持向量机(SVM)分类器进行训练和分类测试。实验结果表明,相对于用小波变换提取的频率相关参数为分类特征的分类准确率为88%,采用CSSD方法提取特征参数进行分类可以取得更理想的效果为95%,后者的16导联脑电信号在空间模型上表现出较高的模式可分性。该研究成果对精神抑郁症的物理诊断和研究提供了新的视角。     

EEG signals classification of epileptic patients via feature selection and voting criteria in intelligent method

Epileptic disease can be diagnosed by using intelligent methods on the Electroencephalograph (EEG) signals. In this paper, wavelet packet transform (WPT) was used in each of the frequency bands and wavelet coefficients were obtained, then the energy and entropy function was done on the wavelet coefficients and used as initial feature vectors. In the next step, eight and 15 features from 30 initial energy and entropy features were selected as the final features because their receiver operating characteristic (ROC) curve areas were higher than others. There were seven classifier inputs. These seven classifiers consisted of four artificial neural networks (ANN) with different structures, support vector machines (SVM), K-nearest neighbours (KNN) and a hybrid network. Each classifier was trained by 0.5, 0.8 and 0.9 EEG signals. After the training process, a fusion network based on a voting criteria was used to make the algorithm robust against the possible changes in each classifier and increase the classification accuracy. Finally, the algorithm was tested by other EEG signals. As a result, normal and epileptic classes were detected with total classification accuracy of 99–100%.     

基于小波包变换的癫痫脑电棘波检测

为了能够较好地实现癫痫患者脑电的棘波检测,提出一种将棘波物理特征（幅度、频率）和小波包变换结合的算法,用于癫痫患者脑电信号的棘波检测。首先利用小波包变换对癫痫脑电信号进行小波包分解,将脑电波频率（0~30 Hz）划分为3层;其次根据脑电波的频率范围重构第三层节点频率S（3, 0）（0~10.85 Hz）、S（3, 1）（10.85~21.7 Hz）、S（3, 2）（21.7~32.55 Hz）的脑电信号;最后取棘波的幅度作为检测阈值分别提取癫痫患者健康期、癫痫发作间期及癫痫发作期的棘波。实验结果证明,当数据的采样频率为173.61 Hz、信号长度为23.6 s时,该算法能够提取不同癫痫患者在不同时期的棘波信号,该算法棘波的误检率为12.02%、漏检率为11.70%。因此,本文所采用的算法在癫痫棘波检测中具有良好的效果。     

Optimal feature selection for the assessment of vocal fold disorders

Unilateral vocal fold paralysis, vocal fold polyp, and vocal fold nodules are the most common types of neurogenic and organic vocal disorders. This article aims to distinguish these types of vocal diseases into four different classes for the purpose of automatic screening. Firstly, the reconstructed signal at each wavelet packet decomposition sub-band in five levels of decomposition with mother wavelet of (db10) is used to extract the nonlinear features of self-similarity and approximate entropy. Also, wavelet packet coefficients are used to measure energy and Shannon entropy features at different spectral sub-bands. Consequently, to find a discriminant feature vector, three different methods have been applied: Davies-Bouldin (DB) criteria, genetic algorithm (GA) with the fitness functions of support vector machine's (SVM) and k-nearest neighbor's (KNN) recognition rates. Finally, obtained feature vectors have been passed on to SVM and KNN classifiers. The results show that a feature vector of length 12 obtained by the optimization method of GA with the fitness function of SVM's recognition rate fed to SVM classifier achieves the highest classification accuracy of 91%. Furthermore, nonlinear features play an important role in pathological voice classification by participating rate of approximately 67% in the optimal feature vector.     

An effective feature extraction method by power spectral density of EEG signal for 2-class motor imagery-based BCI

EEG signals have weak intensity, low signal-to-noise ratio, non-stationary, non-linear, time-frequency-spatial characteristics. Therefore, it is important to extract adaptive and robust features that reflect time, frequency and spatial characteristics. This paper proposes an effective feature extraction method WDPSD (feature extraction from the Weighted Difference of Power Spectral Density in an optimal channel couple) that can reflect time, frequency and spatial characteristics for 2-class motor imagery-based BCI system. In the WDPSD method, firstly, Power Spectral Density (PSD) matrices of EEG signals are calculated in all channels, and an optimal channel couple is selected from all possible channel couples by checking non-stationary and class separability, and then a weight matrix which reflects non-stationary of PSD difference matrix in selected channel couple is calculated; finally, the robust and adaptive features are extracted from the PSD difference matrix weighted by the weight matrix. The proposed method is evaluated from EEG signals of BCI Competition IV Dataset 2a and Dataset 2b. The experimental results show a good classification accuracy in single session, session-to-session, and the different types of 2-class motor imagery for different subjects.