加权解码在解决纠错输出编码Consistent-Diverse平衡问题的应用

 纠错输出编码作为解决多类分类问题的通用集成框架,能有效的把多类问题分解为二类问题从而使问题得以简化.然而在生成基分类器的过程中,经常面临提高基分类器之间的差异性和增加各基分类器与集成分类器学习的一致性的矛盾,称之为consistent-diverse平衡问题.在保证差异性的前提下减小由学习不一致性引起的分类错误率是解决该平衡问题的一个出发点,在此利用加权解码,通过对加权系数矩阵的再学习进而减弱和消除由基分类器学习不一致性产生的误差.实验利用人工数据集和UCI数据集分别加以验证,结果表明以集成分类器的分类错误率为适应度函数的遗传算法搜索出的最优加权系数矩阵相比其它方法产生的系数矩阵在解决consistent-diverse平衡问题更具有优越性.     

一种基于集成学习和特征融合的遥感影像分类新方法

针对多源遥感数据分类的需要,提出了一种基于全极化SAR影像、极化相干矩阵特征、光学遥感影像光谱和纹理的多种特征融合和多分类器集成的遥感影像分类新方法.对全极化PALSAR数据进行预处理和极化相干矩阵特征提取,利用灰度共生矩阵计算光学和SAR影像的对比度、逆差距、二阶距、差异性等纹理特征参数,并与光谱特征结合,形成6种组合策略.利用集成学习方法对随机森林分类器、子空间分类器、最小距离分类器、支持向量机分类器、反向传播神经网络分类器等分类器进行组合,对不同组合策略的遥感影像特征集进行分类.结果表明提出的基于多种特征和多分类器集成的新方法很好地利用了主被动遥感数据在不同地表景观类型提取上的潜力,综合了多种算法的优势,能够有效地提高总体精度和各类别的分类精度.     

基于集成学习的光纤光栅传感网络入侵行为检测

针对光纤光栅传感网络结构复杂，入侵行为检测难度较高的问题，研究基于集成学习的光纤光栅传感网络入侵行为检测方法。选取支持向量机作为集成学习算法的基分类器，计算各基分类器分类光纤光栅传感网络入侵行为样本的误差率，依据基分类器的误差率确定基分类器的重要程度。利用AdaBoost集成学习算法，依据各基分类器的重要程度集成各基分类器，构建最终的集成分类器，利用所构建集成分类器，输出光纤光栅传感网络入侵行为检测结果。实验结果表明，该方法可以精准检测光纤光栅传感网络的远程入侵、拒绝服务入侵等入侵行为，数据丢弃量较低，提升了光纤光栅传感网络的通信性能。     

基于优化Adaboost迭代过程的SVM集成算法

为提高Adaboost算法迭代过程中生成基分类器的分类精度以及简化整个集成学习系统的复杂度,文章提出了一种优化Adaboost迭代过程的SVM集成算法。该算法提出了一种在其迭代过程中加入样本选择和特征选择的集成方法。通过均值近邻算法对样本进行选择,并利用相对熵法进行特征选择,最后利用优化得到的特征样本子集对基分类器SVM进行训练,并用加权投票法融合各个SVM基分类器的决策结果进行最终判决。通过对UCI数据集的仿真结果表明,本算法与支持向量机集成算法相比,能够在更少的样本以及特征的基础上,实现较高的识别正确率。     

认知无线网络中的智能协作频谱感知机制研究

作为智能体,认知无线电应具有智能学习和智能判决的能力。为充分发掘认知用户的智能体特性,本文提出一种基于支持向量机和模糊积分的智能协作频谱感知机制。该机制将协作频谱感知模型转化成基于模糊积分的多分类器融合模型,其中每个认知用户均被看作一个独立的支持向量机分类器,单个感知周期内得到的采样数据作为分类器的输入,分类器的概率输出将被发送至融合中心,融合中心采用模糊积分算法将各分类器得到的结果进行融合并判决。该机制充分挖掘了认知用户在频谱感知阶段的“智能学习”能力和信息融合阶段的“智能判决”能力,仿真结果进一步表明,与单一的分类模型相比,本文提出的智能协作频谱感知机制具有更高的检测概率和更低的虚警概率。      

基于MapReduce技术的并行集成分类算法

由于计算机内存资源限制,分类器组合的有效性及最优性选择是机器学习领域的主要研究内容。经典的集成分类算法在处理小数据集时,拥有较高的分类准确性,但面对大量数据时,由于多基分类器学习、分类共用1台计算机资源,导致运算效率较低,这显然不适合处理当今的海量数据。针对已有集成分类算法只适合作用于小规模数据集的缺点,剖析了集成分类器的特性,采用基于聚合方式的集成分类器和云计算的MapReduce技术设计了并行集成分类算法(EMapReduce),达到并行处理大规模数据的目的。并在Amazon计算集群上模拟实验,实验结果表明该算法具有一定的高效性和可行性。     

基于动态功能连接的握力运动参数脑电识别

为了研究握力运动过程中脑功能网络(Brain Functional Network,BFN)的动态变化特征及对握力运动参数任务识别的影响,提出一种加权相位滞后指数法构建动态脑功能网络.通过对预处理的EEG时间序列按照一定的非重叠窗口截断成等长的子时间序列,按时间顺序,利用相位同步特性对所有子序列进行筛选;筛选出的有效数据段用加权相位滞后指数法估计功能连接大小,构建相应节点的脑功能网络;提取4种不同网络特征参数,对其进行串行融合获得特征向量;最后以支持向量机作为分类器进行分类.与静息态和不均匀子时段划分方法相比,所提方法的平均识别率提高到了74％.     

基于小波变换的运动想象脑电信号分类

在脑-机接口的研究中,针对运动想象的两种思维任务的脑电信号的特征提取,提出了一种基于小波包变换的特征提取方法。该方法利用想象运动中,脑电信号Mu/Beta节律事件相关同步化/去同步化特性,采用BCI2003竞赛数据,输入Matlab的Classify分类函数进行分类,正确率达到88.57%。     

基于脑电熵值特征和功能连接的不同线型道路下驾驶状态检测

基于脑电信号完成对不同驾驶过程的解码分析，并就驾驶意图做出预测，是基于脑机接口的人机协同智能驾驶控制中的核心问题.为了实现对直线、左弯道和右弯道驾驶过程的识别，本文提出了基于脑电功能性脑网络和熵值特征的驾驶行为特征检测方法，并结合支持向量机和高斯混合模型等算法完成对不同线型驾驶过程的分类识别.模拟驾驶实验结果表明，本文提出的方法可有效实现对不同线型驾驶过程的识别，针对16名被试对直线和弯道驾驶过程的识别准确率均高于82%，最高达到86.66%，对左弯道和右弯道驾驶过程的识别准确率均高于75%，最高达到77.95%.对主要脑区间相互依赖关系的分析结果表明，弯道驾驶过程表现出明显的大脑对侧性特征，且左弯道驾驶相比右弯道需要更多的脑区间交互活动，而直线驾驶过程中左脑区的活动稍强于右脑区.本文研究结果对理解弯道驾驶过程中驾驶员脑认知特性，以及开展不同线型道路下驾驶行为检测和驾驶状态研究，具有一定的参考价值.     

一种集成式Beta过程最大间隔一类分类方法

一类分类是一种将目标类样本和其他所有的非目标类样本区分开的分类方法.传统的一类分类方法针对所有训练样本建立一个分类器,忽视了数据的内在结构,在样本分布复杂时,其分类性能会严重下降.为了提升复杂分布情况下的分类性能,该文提出一种集成式Beta过程最大间隔一类方法.该方法利用Dirichlet过程混合模型(DPM)对训练样本聚类,同时在每一个聚类学习一个Beta过程最大间隔一类分类器.通过多个分类器的集成,可以构造出一个描述能力更强的分类器,提升复杂分布下的分类效果.DPM聚类模型和Beta过程最大间隔一类分类器在同一个贝叶斯框架下联合优化,保证了每一个聚类样本的可分性.此外,在Beta过程最大间隔一类分类器中,加入了服从Beta过程先验分布的特征选择因子,从而可以降低特征冗余度以及提升分类效果.基于仿真数据、公共数据集和实测SAR图像数据的实验结果证明了所提方法的有效性.     

xDAWN Algorithm to Enhance Evoked Potentials: Application to Brain–Computer Interface

A brain-computer interface (BCI) is a communication system that allows to control a computer or any other device thanks to the brain activity. The BCI described in this paper is based on the P300 speller BCI paradigm introduced by Farwell and Donchin. An unsupervised algorithm is proposed to enhance P300 evoked potentials by estimating spatial filters; the raw EEG signals are then projected into the estimated signal subspace. Data recorded on three subjects were used to evaluate the proposed method. The results, which are presented using a Bayesian linear discriminant analysis classifier, show that the proposed method is efficient and accurate.     

Toward unsupervised adaptation of LDA for brain-computer interfaces

There is a step of significant difficulty experienced by brain-computer interface (BCI) users when going from the calibration recording to the feedback application. This effect has been previously studied and a supervised adaptation solution has been proposed. In this paper, we suggest a simple unsupervised adaptation method of the linear discriminant analysis (LDA) classifier that effectively solves this problem by counteracting the harmful effect of nonclass-related nonstationarities in electroencephalography (EEG) during BCI sessions performed with motor imagery tasks. For this, we first introduce three types of adaptation procedures and investigate them in an offline study with 19 datasets. Then, we select one of the proposed methods and analyze it further. The chosen classifier is offline tested in data from 80 healthy users and four high spinal cord injury patients. Finally, for the first time in BCI literature, we apply this unsupervised classifier in online experiments. Additionally, we show that its performance is significantly better than the state-of-the-art supervised approach.     

Transfer Learning of BCI Using CUR Algorithm

The brain computer interface (BCI) are used in many applications including medical, environment, education, economy, and social fields. In order to have a high performing BCI classification, the training set must contain variations of high quality subjects which are discriminative. Variations will also drive transferability of training data for generalization purposes. However, if the test subject is unique from the training set variations, BCI performance may suffer. Previously, this problem was solved by introducing transfer learning in the context of spatial filtering on small training set by creating high quality variations within training subjects. In this study however, it was discovered that transfer learning can also be used to compress the training data into an optimal compact size while improving training data performance. The transfer learning framework proposed was on motor imagery BCI-EEG using CUR matrix decomposition algorithm which decomposes data into two components; C and UR which is each subject’s EEG signal and common matrix derived from historical EEG data, respectively. The method is considered transfer learning process because it utilizes historical data as common matrix for the classification purposes. This framework is implemented in the BCI system along with Common Spatial Pattern (CSP) as features extractor and Extreme Learning Machine (ELM) as classifier and this combination exhibits an increase of accuracy to up to 26% with 83% training database compression.

     

Adaptive BCI based on variational Bayesian Kalman filtering: an empirical evaluation

This paper proposes the use of variational Kalman filtering as an inference technique for adaptive classification in a brain computer interface (BCI). The proposed algorithm translates electroencephalogram segments adaptively into probabilities of cognitive states. It, thus, allows for nonstationarities in the joint process over cognitive state and generated EEG which may occur during a consecutive number of trials. Nonstationarities may have technical reasons (e.g., changes in impedance between scalp and electrodes) or be caused by learning effects in subjects. We compare the performance of the proposed method against an equivalent static classifier by estimating the generalization accuracy and the bit rate of the BCI. Using data from two studies with healthy subjects, we conclude that adaptive classification significantly improves BCI performance. Averaging over all subjects that participated in the respective study, we obtain, depending on the cognitive task pairing, an increase both in generalization accuracy and bit rate of up to 8%. We may, thus, conclude that adaptive inference can play a significant contribution in the quest of increasing bit rates and robustness of current BCI technology. This is especially true since the proposed algorithm can be applied in real time.     

An Algorithm for Idle-State Detection and Continuous Classifier Design in Motor-Imagery-Based BCI

Abstract-The development of asynchronous brain-computer interface （BCI） based on motor imagery （M1） poses the research in algorithms for detecting the nontask states （i.e., idle state） and the design of continuous classifiers that classify continuously incoming electroencephalogram （EEG） samples. An algorithm is proposed in this paper which integrates two two-class classifiers to detect idle state and utilizes a sliding window to achieve continuous outputs. The common spatial pattern （CSP） algorithm is used to extract features of EEG signals and the linear support vector machine （SVM） is utilized to serve as classifier. The algorithm is applied on dataset IVb of BCI competition Ⅲ, with a resulting mean square error of 0.66. The result indicates that the proposed algorithm is feasible in the first step of the development of asynchronous systems.     

Common Spatial Pattern Ensemble Classifier and Its Application in Brain-Computer Interface

Common spatial pattern (CSP) algorithm is a successful tool in feature estimate of brain-computer interface (BCI). However, CSP is sensitive to outlier and may result in poor outcomes since it is based on pooling the covariance matrices of trials. In this paper, we propose a simple yet effective approach, named common spatial pattern ensemble (CSPE) classifier, to improve CSP performance. Through division of recording channels, multiple CSP filters are constructed. By projection, log-operation, and subtraction on the original signal, an ensemble classifier, majority voting, is achieved and outlier contaminations are alleviated. Experiment results demonstrate that the proposed CSPE classifier is robust to various artifacts and can achieve an average accuracy of 83.02%.     

An Algorithm for Idle-State Detection and Continuous Classifier Design in Motor-Imagery-Based BCI

The development of asynchronous braincomputer interface (BCI) based on motor imagery (MI) poses the research in algorithms for detecting the nontask states (i.e., idle state) and the design of continuous classifiers that classify continuously incoming electroencephalogram (EEG) samples. An algorithm is proposed in this paper which integrates two two-class classifiers to detect idle state and utilizes a sliding window to achieve continuous outputs. The common spatial pattern (CSP) algorithm is used to extract features of EEG signals and the linear support vector machine (SVM) is utilized to serve as classifier. The algorithm is applied on dataset IVb of BCI competition III, with a resulting mean square error of 0.66. The result indicates that the proposed algorithm is feasible in the first step of the development of asynchronous systems.     

Common Spatial Pattern Ensemble Classifier and Its Application in Brain-Computer Interface

Abstract-Common spatial pattern （CSP） algorithm is a successful tool in feature estimate of brain-computer interface （BCI）. However, CSP is sensitive to outlier and may result in poor outcomes since it is based on pooling the covariance matrices of trials. In this paper, we propose a simple yet effective approach, named common spatial pattern ensemble （CSPE） classifier, to improve CSP performance. Through division of recording channels, multiple CSP filters are constructed. By projection, log-operation, and subtraction on the original signal, an ensemble classifier, majority voting, is achieved and outlier contaminations are alleviated. Experiment results demonstrate that the proposed CSPE classifier is robust to various artifacts and can achieve an average accuracy of 83.02%.     

A high-performance sensorless indirect stator flux orientation control of induction motor drive

A new method for the implementation of a sensorless indirect stator-flux-oriented control (ISFOC) of induction motor drives with stator resistance tuning is proposed in this paper. The proposed method for the estimation of speed and stator resistance is based only on measurement of stator currents. The error of the measured q-axis current from its reference value feeds the proportional plus integral (PI) controller, the output of which is the estimated slip frequency. It is subtracted from the synchronous angular frequency, which is obtained from the output integral plus proportional (IP) rotor speed controller, to have the estimated rotor speed. For current regulation, this paper proposes a conventional PI controller with feedforward compensation terms in the synchronous frame. Owing to its advantages, an IP controller is used for rotor speed regulation. Stator resistance updating is based on the measured and reference d-axis stator current of an induction motor on d-q frame synchronously rotating with the stator flux vector. Experimental results for a 3-kW induction motor are presented and analyzed by using a dSpace system with DS1102 controller board based on the digital signal processor (DSP) TMS320C31. Digital simulation and experimental results are presented to show the improvement in performance of the proposed method.     

A fully on-line adaptive BCI

A viable fully on-line adaptive brain computer interface (BCI) is introduced. On-line experiments with nine naive and able-bodied subjects were carried out using a continuously adaptive BCI system. The data were analyzed and the viability of the system was studied. The BCI was based on motor imagery, the feature extraction was performed with an adaptive autoregressive model and the classifier used was an adaptive quadratic discriminant analysis. The classifier was on-line updated by an adaptive estimation of the information matrix (ADIM). The system was also able to provide continuous feedback to the subject. The success of the feedback was studied analyzing the error rate and mutual information of each session and this analysis showed a clear improvement of the subject's control of the BCI from session to session.