用核学习算法的意识任务特征提取与分类

介绍了核学习算法中核主分量分析(KPCA)和支持向量机(SVM)的基本原理,给出一种推广误差上界估计判据,实现了SVM核参数及惩罚因子的优化选取.根据多变量自回归模型理论对4个受试对象、三种不同意识任务的脑电信号进行特征提取,并利用KPCA方法进行降维预处理,对SVM进行训练和分类测试.结果表明,KPCA算法在高维特征空间具有较强的特征选择能力,优化核参数的SVM的分类正确率明显高于径向基函数网络,三种意识任务的平均分类正确率达78.6％.     

在线脑机接口中脑电信号的特征提取与分类方法

在脑机接口研究中,针对运动想象脑电信号的特征抽取,提出了一种基于离散小波变换和AR模型的方法.利用Daubechies类小波函数对脑电信号进行3层分解,抽取小波变换系数的统计特征;利用Burg算法提取脑电信号6阶AR模型系数.将这两类特征进行组合后使用神经网络、支持向量机、马氏距离线性判别进行分类并比较分析.采用BCI...     

色彩感知中的脑电信号多域特征选择算法研究

针对目前在不同色彩感知中的脑电信号识别方面的研究还不多见,本文提出采用随机森林算法对信号的时域特征和频域特征进行最优组合的方法对不同色彩感知中的脑电信号进行识别。首先采用小波变换,对脑电信号进行7层分解,提取脑电信号在delta、theta、alpha和beta节律频带上的小波能量,并结合脑电信号在时域上的统计量偏度和峰度组成特征向量。然后通过基于随机森林的特征选择算法提取最优的特征组合方案,删除冗余的特征量。使用自适应增强算法进行分类识别,识别的平均正确率可达到85.07%。该结果表明使用本文所提出的特征提取与选择方法用于不同色彩感知中的脑电信号识别上是可行的,并且能够取得较好的识别率。      

松脱件撞击波形检测算法

文中针对核反应设施松动件的检测，以碰撞波形检测为目标，提出了一种基于机器学习的松动件撞击波形检测方法。该方法以核反应设施中的传感器数据为输入基础，利用数据滤波、特征降维、机器学习等组合算法，实现松动件振动波形识别。实验结果表明，对数据进行滤波、降维后，利用GBDT算法，能有效识别不同类型的振动波形。此外，通过t-SNE算法对样本进行可视化后，发现经滤波和特征降维后的数据具有很好的聚类特征，有助于分类算法进一步完成分类识别。     

基于ISOMAP的高光谱遥感数据的降维与分类

为挖掘高光谱遥感数据内在的非线性结构特性,采用全局化流形学习算法等距特征映射（ISOMAP）对高光谱遥感数据进行非线性降维,并取得了优于常用的最小噪声分离（MNF）变换方法的结果,具有更好的数据压缩性能。将光谱角相似性度量方法用于ISOMAP 算法,取得良好的降维效果。通过把ISOMAP 降维算法和k-最邻近分类器相结合对降维后子空间特征进行分类,实验表明:ISOMAP 利用较少的特征维数获得比MNF 更高的分类精度,并达到较高稳定的分类精度,尤其对难以区分、光谱相似的两类别问题,ISOMAP 的特征维数能够有效的提高两类别的可分性。     

基于CNN-LSTM的运动想象脑电四分类研究

脑机接口通过对运动想象脑电信号的分类识别，帮助运动神经严重受损的患者实现与外部设备的直接交互。为了提高多分类运动想象脑电信号的分类准确率，提出一种基于卷积神经网络（Convolutional Neural Network,CNN）和长短时记忆（Long Short-Term Memory,LSTM）网络的脑电信号识别方法。首先，对原始脑电信号进行预处理，并利用快速傅里叶变换提取出相关频带的能量值；其次，对处理后的脑电信号采用一维卷积神经网络提取空间特征，再利用LSTM网络在序列上的建模能力，将空间特征组成特征序列输入到LSTM网络，提取时间特征；最后，将LSTM网络输出的特征输入到Softmax分类器，把结果分为左手、右手、舌头和脚四种类型。文中使用BCI Competition Ⅳ竞赛的数据集2a对所提的方法进行验证，实验结果表明，所提方法能够有效地提高多分类精度，分类结果的平均准确率达到90.38%。     

思维状态的EEG信号分类方法研究

脑电信号(EEG)是一种研究脑活动的重要信息来源,基于脑电信号的人与计算机的通信已成为一种新的人机接口方式.运用时域回归方法对2～5种不同思维脑电信号进行预处理,用AR模型提取信号分段前后特征,最后用BP算法进行分类.并对分段前后的分类结果进行比较,实验表明,该方法达到很好的分类效果.     

小波滤波与AR模型在脑电信号处理的应用

针对脑-计算机接口技术中的脑电信号处理、事件相关同步和事件相关去同步的特点,提出了一种基于离散小波滤波和AR模型来提取脑电信号特征向量的方法。利用Daubechies类小波函数对脑电信号进行4层分解,然后使用Burg算法提取脑电信号8阶AR模型系数,最后用BP神经网络进行分类和比较。得到最优的正确率为71.64%,小波滤波的效果要优于FIR滤波器。     

一种具有隐蔽色特征物体的图像分类方法研究

针对图像中某几类物体具有相似颜色特征而导致的分类困难问题,本文提出了一种具有隐蔽色特征物体的图像分类方法。该方法针对可见光图像中具有颜色隐蔽性物体而难以区分的问题,通过将二维图像的邻域像素空间特征与高光谱图像的谱段特征相结合并使用改进的局部线性嵌入降维算法实现了空谱联合的特征降维,最终利用主动学习胶囊网络训练高光谱数据分类器从而实现场景内目标的分类。通过改进的主动学习函数可以对更具代表性的样本进行标注,实现了利用小样本集对胶囊网络的训练,有效降低了样本的标注成本和模型的训练成本,提高了模型分类性能。实验表明,该算法运行在自建高光谱数据集上能够有效地分类隐蔽色特征物体和其他自然场景,针对隐蔽色目标的平均准确率达到了91%,针对所有类别物体的平均准确率达到了89.9%。     

基于蒙特卡罗特征降维算法的小样本高光谱图像分类

高光谱图像分类是高光谱数据分析的重要研究内容.相关向量机由于不受梅西定理的限制、不需要设置惩罚因子等优势受到广泛关注.由于高光谱数据具有较高的维数,当训练样本较少时,高光谱数据的分类精度受到严重的影响.通常解决这种现象的办法是对原数据进行特征降维处理,然而多数基于filter模型的特征选择算法无法直接给出最优特征选择个数.为此提出利用蒙特卡罗随机实验可以对特征参量进行统计估计的特性,计算高光谱图像的最优降维特征数,并与相关向量机结合,对降维后的数据进行分类.实验结果表明了使用蒙特卡罗算法求解降维波段数的可靠性.相比较原始末降维数据,降维后的高光谱图像分类精度有较大幅度的提高.     

A Modified Minimum Classification Error (MCE) Training Algorithm for Dimensionality Reduction

Dimensionality reduction is an important problem in pattern recognition. There is a tendency of using more and more features to improve the performance of classifiers. However, not all the newly added features are helpful to classification. Therefore it is necessary to reduce the dimensionality of feature space for effective and efficient pattern recognition. Two popular methods for dimensionality reduction are Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA). While these methods are effective, there exists an inconsistency between feature extraction and the classification objective. In this paper we use Minimum Classification Error (MCE) training algorithm for feature dimensionality reduction and classification on Daterding and GLASS databases. The results of MCE training algorithms are compared with those of LDA and PCA.     

基于线性和非线性算法的高效人脸识别系统

文中提出了一种基于外观的线性和非线性人脸识别方法,所用的线性算法有主成分分析(PCA)和线性判别分析(LDA)。两种非线性方法分别是核主成分分析(KPCA)及核费希尔分析(KFA),线性降维投影方法基于二阶相依性编码模式信息,非线性方法用于处理三个或更多像素之间的关系。首先通过Gabor对图片进行预处理,然后采用线性、非线性分析进行降维。通过马哈利诺比斯-余弦(Mahcos)度量用于定义两幅图像通过相应的降维技术后的相似性度量。实验表明,当与Gabor小波一同使用时,LDA和KFA的性能最高,分别为CMC和ROC结果的93.33%。通过对AT&T数据库400幅图像的综合分析,发现线性和非线性算法的性能受图像分类数目、图像预处理及识别测试集的人脸图像数目的影响。     

基于核主成分分析的二次雷达脉冲信号初始特征提取

针对二次雷达脉冲信号的特征选择与分类问题进行研究,提出了一种基于核主成分分析(KPCA)的初始特征提取方法.根据二次雷达脉冲信号的特点,首先经过数据整编、预处理,获取样本的初始特征参数;然后利用KPCA方法对特征参数进行主成分组合,以消除信号特征间的相关性和压缩特征向量的维数,最后利用聚类工具进行分类.数学分析和可视化实验结果都表明这种分析方法是有效的.试验还表明,KPCA在特征选取方面性能优于PCA.     

Kernel neighborhood preserving embedding for classification

The Neighborhood Preserving Embedding(NPE)algorithm is recently proposed as a new dimensionality reduction method.However,it is confined to linear transforms in the data space.For this,based on the NPE algorithm,a new nonlinear dimensionality reduction method is proposed,which can preserve the local structures of the data in the feature space.First,combined with the Mercer kernel,the solution to the weight matrix in the feature space is gotten and then the corresponding eigenvalue problem of the Kernel NPE (KNPE) method is deduced.Finally,the KNPE algorithm is resolved through a transformed optimization problem and QR decomposition.The experimental results on three real-world data sets show that the new method is better than NPE,Kernel PCA (KPCA) and Kernel LDA(KLDA)in performance.     

Gabor feature-based face recognition using supervised locality preserving projection

This paper introduces a novel Gabor-based supervised locality preserving projection (GSLPP) method for face recognition. Locality preserving projection (LPP) is a recently proposed method for unsupervised linear dimensionality reduction. LPP seeks to preserve the local structure which is usually more significant than the global structure preserved by principal component analysis (PCA) and linear discriminant analysis (LDA). In this paper, we investigate its extension, called supervised locality preserving projection (SLPP), using class labels of data points to enhance its discriminant power in their mapping into a low-dimensional space. The GSLPP method, which is robust to variations of illumination and facial expression, applies the SLPP to an augmented Gabor feature vector derived from the Gabor wavelet representation of face images. We performed comparative experiments of various face recognition schemes, including the proposed GSLPP method, PCA method, LDA method, LPP method, the combination of Gabor and PCA method (GPCA) and the combination of Gabor and LDA method (GLDA). Experimental results on AR database and CMU PIE database show superior of the novel GSLPP method.     

支持向量鉴别分析及在人脸表情识别中的应用

模式识别一般首先要对数据进行降维,PCA和LDA及其对应的核化算法是其中应用广泛的方法,但这些算法的应用前提是假设样本数据为高斯分布,在少样本训练时它们的推广性能有很大局限.本文提出了一种基于支持向量机的鉴别分析算法,该算法首先寻找有限样本情况下最优分类面,以其法线方向为投影轴对数据进行投影降维,在多类情况下提供了极其丰富的方案选择投影轴.该算法体现了支持向量机的内在优良推广性能,克服了PCA和LDA等算法的局限性.本文将所提算法应用于人脸表情特征提取,并与PCA、LDA、KPCA、GDA等算法进行了比较,结果表明该算法的有效性.     

Anomaly Detection for Hyperspectral Images Based on Robust Locally Linear Embedding

In this paper, anomaly detection in hyperspectral images is investigated using robust locally linear embedding (RLLE) for dimensionality reduction in conjunction with the RX anomaly detector. The new RX-RLLE method is implemented for large images by subdividing the original image and applying the RX-RLLE operations to each subset. Moreover, from the kernel view of LLE, it is demonstrated that the RX-RLLE is equivalent to introducing a locally linear embedding (LLE) kernel into the kernel RX (KRX) algorithm. Experimental results indicate that the RX-RLLE has good anomaly detection performance and that RLLE has superior performance to LLE and principal component analysis (PCA) for dimensionality reduction in the application of anomaly detection.     

乐山茶叶的近红外光谱分类识别

以乐山产正品竹叶青、劣质竹叶青和峨眉山毛峰为研究对象,提出了一种基于近红外光谱的不同茶叶品种分类识别算法.该算法采用多元散射校正(Multiplicative Scatter Correction,MSC)对3种茶叶的近红外光谱数据进行预处理,最大限度地扣除光谱数据中的随机变异;再采用主成分分析算法(Principal Component Analysis,PCA)对预处理后的光谱数据进行降维,去除冗余;接下来进行线性判别分析(Linear Discriminant Analysis,LDA),进一步提取特征;最后采用K_近邻算法(K_Nearest Neighbor,KNN)对LDA结果的前两个特征进行分类,从而达到对茶叶进行定性分类的目的.实验结果表明,该算法能有效地对3种茶叶进行分类,正确识别率达到100％.本研究为不同品种茶叶的分类识别提供了一种新思路.     

Decision Fusion With Confidence-Based Weight Assignment for Hyperspectral Target Recognition

Conventional hyperspectral image-based automatic target recognition (ATR) systems project high-dimensional reflectance signatures onto a lower dimensional subspace using techniques such as principal components analysis (PCA), Fisher's linear discriminant analysis (LDA), and stepwise LDA. Typically, these feature space projections are suboptimal. In a typical hyperspectral ATR setup, the number of training signatures (ground truth) is often less than the dimensionality of the signatures. Standard dimensionality reduction tools such as LDA and PCA cannot be applied in such situations. In this paper, we present a divide-and-conquer approach that addresses this problem for robust ATR. We partition the hyperspectral space into contiguous subspaces based on the optimization of a performance metric. We then make local classification decisions in every subspace using a multiclassifier system and employ a decision fusion system for making the final decision on the class label. In this work, we propose a metric that incorporates higher order statistical information for accurate partitioning of the hyperspectral space. We also propose an adaptive weight assignment method in the decision fusion process based on the strengths (as measured by the training accuracies) of individual classifiers that made the local decisions. The proposed methods are tested using hyperspectral data with known ground truth, such that the efficacy can be quantitatively measured in terms of target recognition accuracies. The proposed system was found to significantly outperform conventional approaches. For example, under moderate pixel mixing, the proposed approach resulted in classification accuracies around 90%, where traditional feature fusion resulted in accuracies around 65%.