Semi-supervised feature extraction for EEG classification

Two semi-supervised feature extraction methods are proposed for electroencephalogram (EEG) classification. They aim to alleviate two important limitations in brain–computer interfaces (BCIs). One is on the requirement of small training sets owing to the need of short calibration sessions. The second is the time-varying property of signals, e.g., EEG signals recorded in the training and test sessions often exhibit different discriminant features. These limitations are common in current practical applications of BCI systems and often degrade the performance of traditional feature extraction algorithms. In this paper, we propose two strategies to obtain semi-supervised feature extractors by improving a previous feature extraction method extreme energy ratio (EER). The two methods are termed semi-supervised temporally smooth EER and semi-supervised importance weighted EER, respectively. The former constructs a regularization term on the preservation of the temporal manifold of test samples and adds this as a constraint to the learning of spatial filters. The latter defines two kinds of weights by exploiting the distribution information of test samples and assigns the weights to training data points and trials to improve the estimation of covariance matrices. Both of these two methods regularize the spatial filters to make them more robust and adaptive to the test sessions. Experimental results on data sets from nine subjects with comparisons to the previous EER demonstrate their better capability for classification.     

Robust Sequential Data Modeling Using an Outlier Tolerant Hidden Markov Model

Hidden Markov (chain) models using finite Gaussian mixture models as their hidden state distributions have been successfully applied in sequential data modeling and classification applications. Nevertheless, Gaussian mixture models are well known to be highly intolerant to the presence of untypical data within the fitting data sets used for their estimation. Finite Student's t-mixture models have recently emerged as a heavier-tailed, robust alternative to Gaussian mixture models, overcoming these hurdles. To exploit these merits of Student's t-mixture models in the context of a sequential data modeling setting, we introduce, in this paper, a novel hidden Markov model where the hidden state distributions are considered to be finite mixtures of multivariate Student's t-densities. We derive an algorithm for the model parameters estimation under a maximum likelihood framework, assuming full, diagonal, and factor-analyzed covariance matrices. The advantages of the proposed model over conventional approaches are experimentally demonstrated through a series of sequential data modeling applications.     

基于双通道变分自编码器的高光谱图像分类

针对现有高光谱图像变分自编码器（variational autoencoder,VAE）分类算法存在空间和光谱特征利用效率低的问题,提出一种基于双通道变分自编码器的高光谱图像深度学习分类算法。通过构建一维条件变分自编码器（conditional variational autoencoder,CVAE）特征提取框架和二维循环通道条件变分自编码（channel-recurrent conditional variational autoencoders,CRCVAE）特征提取框架分别提取高光谱图像的光谱特征和空间特征,将光谱特征向量和空间特征向量叠加形成空谱联合特征向量,将联合特征送入Softmax分类器中进行分类。在Indian pines和Pavia University两种高光谱数据集上进行了分析验证,实验结果显示,与其他算法相比,提出的算法在总分类精度、平均分类精度和Kappa系数等评价指标上至少提高了3.40、2.75和3.57个百分点,结果显示提出的算法得到了最高的分类精度和更好的可视化效果。     

Classification of large data sets with mixture models via sufficient EM

For the classification of very large data sets with a mixture model approach a two-step strategy for the estimation of the mixture is proposed. In the first step data are scaled down using compression techniques. Data compression consists of clustering the single observations into a medium number of groups and the representation of each group by a prototype, i.e. a triple of sufficient statistics (mean vector, covariance matrix, number of observations compressed). In the second step the mixture is estimated by applying an adapted EM algorithm (called sufficient EM) to the sufficient statistics of the compressed data. The estimated mixture allows the classification of observations according to their maximum posterior probability of component membership. The performance of sufficient EM in clustering a real data set from a web-usage mining application is compared to standard EM and the TwoStep clustering algorithm as implemented in SPSS. It turns out that the algorithmic efficiency of the sufficient EM algorithm is much more higher than for standard EM. While the TwoStep algorithm is even faster the results show a lack of stability.     

基于增强空谱特征网络的空间感知协同表示算法

高光谱图像具有高维度、带间相关性较高、样本数量较少等诸多问题,直接利用表示学习算法对高光谱图像进行分类会导致严重的维数灾难.对于高光谱图像,不是所有的光谱带都可用于特定的分类任务.因此,文中提出基于增强空谱特征网络的空间感知协同表示算法.依据高光谱图像内在的低维流形构建基于空谱特征的分层网络.利用训练的网络对高维数据进行特征提取,并利用空间感知协同表示算法进行分类.在两个高光谱数据集Indian Pines和Pavia University上的实验表明文中算法的有效性.     

基于主动深度学习的高光谱影像分类

针对当前高光谱遥感影像分类人工标注样本费时费力,大量未标注样本未得到有效利用以及主要利用光谱信息而忽视空间信息等问题,提出了一种空-谱信息与主动深度学习相结合的高光谱影像分类方法。首先利用主成分分析对原始影像进行降维,在此基础上提取像素的一正方形小邻域作为该像素的空间信息并结合其原始光谱信息得到空谱特征。然后,通过稀疏自编码器得到原始数据的稀疏特征表达,并通过逐层无监督学习稀疏自编码器构建深度神经网络,输出原始数据的深度特征,将其连接到softmax分类器,利用少量标记样本以监督学习的方式完成模型的精调。最后,利用主动学习算法选择最不确定性样本对其进行标注,并加入至训练样本以提高分类器的分类效果。分别对PaviaU影像和PaviaC影像进行分类实验的结果表明,该方法在少量标记样本情况下,相对于传统方法能有效地提高分类精度。     

MLiT: mixtures of Gaussians under linear transformations

The curse of dimensionality hinders the effectiveness of density estimation in high dimensional spaces. Many techniques have been proposed in the past to discover embedded, locally linear manifolds of lower dimensionality, including the mixture of principal component analyzers, the mixture of probabilistic principal component analyzers and the mixture of factor analyzers. In this paper, we propose a novel mixture model for reducing dimensionality based on a linear transformation which is not restricted to be orthogonal nor aligned along the principal directions. For experimental validation, we have used the proposed model for classification of five “hard” data sets and compared its accuracy with that of other popular classifiers. The performance of the proposed method has outperformed that of the mixture of probabilistic principal component analyzers on four out of the five compared data sets with improvements ranging from 0.5 to 3.2%. Moreover, on all data sets, the accuracy achieved by the proposed method outperformed that of the Gaussian mixture model with improvements ranging from 0.2 to 3.4%.     

高光谱图像分类的自适应决策融合方法

目的 目前高光谱图像决策融合方法主要采用以多数票决（majority vote，MV）为代表的硬决策融合和以对数意见池（logarithmic opinion pool，LOGP）为代表的软决策融合策略。由于这些方法均使用统一的权重系数进行决策融合，没有对子分类器各自的分类性能进行评估而优化分配权重系数，势必会影响最终的分类精度。针对该问题，本文对多数票决和对数意见池融合策略进行了改进，提出了面向高光谱图像分类的自适应决策融合方法。方法 根据相关系数矩阵对高光谱图像进行波段分组，对每组波段进行空谱联合特征提取；利用高斯混合模型（Gaussian mixture model，GMM）或支持向量机（support vector machine，SVM）分类器对各组空谱联合特征进行分类；最后，采用本文研究的两种基于权重系数优化分配的自适应融合策略对子分类器的分类结果进行决策融合，使得分类精度低的波段组和异常值对最终分类结果的影响达到最小。结果 对两个公开的高光谱数据集分别采用多种特征和两种分类器组合进行实验验证。实验结果表明，在相同特征和分类器条件下，本文提出的自适应多数票决策融合策略（adjust majority vote，adjustMV）、自适应对数意见池决策融合策略（adjust logarithmic opinion pool，adjustLOGP）比传统的MV决策融合策略、LOGP决策融合策略对两个数据集的分类精度均有大幅度提高。Indian Pines数据集上，adjustMV算法的分类精度比相应的MV算法平均提高了1.2%，adjustLOGP算法的分类精度比相应的LOGP算法平均提高了7.38%；Pavia University数据集上，adjustMV算法的分类精度比相应的MV算法平均提高了2.1%，adjustLOGP算法的分类精度比相应的LOGP算法平均提高了4.5%。结论 本文提出的自适应权重决策融合策略为性能较优的子分类器（即对应于分类精度高的波段组）赋予较大的权重，降低了性能较差的子分类器与噪声波段对决策融合结果的影响，从而大幅度提高分类精度。所研究的决策融合策略的复杂度和计算成本均较低，在噪声环境中具有更强的鲁棒性，同时在一定程度上解决了高光谱图像分类应用中普遍存在的小样本问题。     

On combining multiscale deep learning features for the classification of hyperspectral remote sensing imagery

In recent years, satellite imagery has greatly improved in both spatial and spectral resolution. One of the major unsolved problems in highly developed remote sensing imagery is the manual selection and combination of appropriate features according to spectral and spatial properties. Deep learning framework can learn global and robust features from the training data set automatically, and it has achieved state-of-the-art classification accuracies over different image classification tasks. In this study, a technique is proposed which attempts to classify hyperspectral imagery by incorporating deep learning features. Firstly, deep learning features are extracted by multiscale convolutional auto-encoder. Then, based on the learned deep learning features, a logistic regression classifier is trained for classification. Finally, parameters of deep learning framework are analysed and the potential development is introduced. Experiments are conducted on the well-known Pavia data set which is acquired by the reflective optics system imaging spectrometer sensor. It is found that the deep learning-based method provides a more accurate classification result than the traditional ones.     

Multivariate mixed normal conditional heteroskedasticity

A new multivariate volatility model where the conditional distribution of a vector time series is given by a mixture of multivariate normal distributions is proposed. Each of these distributions is allowed to have a time-varying covariance matrix. The process can be globally covariance stationary even though some components are not covariance stationary. Some theoretical properties of the model such as the unconditional covariance matrix and autocorrelations of squared returns are derived. The complexity of the model requires a powerful estimation algorithm. A simulation study compares estimation by maximum likelihood with the EM algorithm. Finally, the model is applied to daily US stock returns.     

Improving hyperspectral image classification by combining spectral,texture, and shape features

Several studies have already demonstrated the efficiency of utilizing spatial information in representation and interpretation of hyperspectral (HS) images. Texture and shape features are known as two important categories of spatial information in various applications of image processing. This study tries to utilize texture and shape features extracted from HS images, as well as spectral information, in order to reduce overall classification errors. These features include morphological profiles (MPs), global Gabor features, and features extracted from conventional and segmentation-based grey-level co-occurrence matrices (GLCMs). Various combinations of these spatial features along with spectral information are fed into a support vector machine (SVM) classifier, and the best combinations for different situations are determined. Experiments on the widely used Indian Pines, Pavia University, and Salinas HS data sets demonstrate the efficiency of the proposed framework in comparison with some recent spectral–spatial classification methods.     

CNN和三维Gabor滤波器的高光谱图像分类

卷积神经网络(CNN)具有强大的特征提取能力,能够有效地提高高光谱图像的分类精度.然而CNN模型训练需要大量的训练样本参与,以防止过拟合,Gabor滤波器以非监督的方式提取图像的边缘和纹理等空间信息,能够减轻CNN模型对训练样本的依赖度及特征提取的压力.为了充分利用CNN和Gabor滤波器的优势,提出了一种双通道CNN和三维Gabor滤波器相结合的高光谱图像分类方法Gabor-DC-CNN.首先利用二维卷积神经网络(2D-CNN)模型处理原始高光谱图像数据,提取图像的深层空间特征;同时利用一维卷积神经网络(1D-CNN)模型处理三维Gabor特征数据,进一步提取图像的深层光谱-纹理特征.连接2个CNN模型的全连接层实现特征融合,并将融合特征输入到分类层中完成分类.实验结果表明,该方法能够有效地提高分类精度,在Indian Pines,Pavia University和Kennedy Space Center 3组数据上分别达到98.95%,99.56%和99.67%.     

Multiple model regression estimation

This paper presents a new learning formulation for multiple model estimation (MME). Under this formulation, training data samples are generated by several (unknown) statistical models. Hence, most existing learning methods (for classification or regression) based on a single model formulation are no longer applicable. We describe a general framework for MME. Then we introduce a constructive support vector machine (SVM)-based methodology for multiple regression estimation. Several empirical comparisons using synthetic and real-life data sets are presented to illustrate the proposed approach for multiple model regression formulation.     

Cyclic learning rate based HybridSN model for hyperspectral image classification

Classification of remotely sensed hyperspectral images (HSI) is a challenging task due to the presence of a large number of spectral bands and due to the less available data of remotely sensed HSI. The use of 3D-CNN and 2D-CNN layers to extract spectral and spatial features shows good test results. The recently introduced HybridSN model for the classification of remotely sensed hyperspectral images is the best to date compared to the other state-of-the-art models. But the test performance of the HybridSN model decreases significantly with the decrease in training data or number of training epochs. In this paper, we have considered cyclic learning for training of the HybridSN model, which shows a significant increase in the test performance of the HybridSN model with 10%, 20%, and 30% training data and limited number of training epochs. Further, we introduce a new cyclic function (ncf) whose training and test performance is comparable to the existing cyclic learning rate policies. More precisely, the proposed HybridSN(ncf ) model has higher average accuracy compared to HybridSN model by 19.47%, 1.81% and 8.33% for Indian Pines, Salinas Scene and University of Pavia datasets respectively in case of 10% training data and limited number of training epochs.

     

结合超像元和子空间投影支持向量机的高光谱图像分类

目的 高光谱图像包含了丰富的空间、光谱和辐射信息,能够用于精细的地物分类,但是要达到较高的分类精度,需要解决高维数据与有限样本之间存在矛盾的问题,并且降低因噪声和混合像元引起的同物异谱的影响。为有效解决上述问题,提出结合超像元和子空间投影支持向量机的高光谱图像分类方法。方法 首先采用简单线性迭代聚类算法将高光谱图像分割成许多无重叠的同质性区域,将每一个区域作为一个超像元,以超像元作为图像分类的最小单元,利用子空间投影算法对超像元构成的图像进行降维处理,在低维特征空间中执行支持向量机分类。本文高光谱图像空谱综合分类模型,对几何特征空间下的超像元分割与光谱特征空间下的子空间投影支持向量机（SVMsub）,采用分割后进行特征融合的处理方式,将像元级别转换为面向对象的超像元级别,实现高光谱图像空谱综合分类。结果 在AVIRIS（airbone visible/infrared imaging spectrometer）获取的Indian Pines数据和Reflective ROSIS（optics system spectrographic imaging system）传感器获取的University of Pavia数据实验中,子空间投影算法比对应的非子空间投影算法的分类精度高,特别是在样本数较少的情况下,分类效果提升明显;利用马尔可夫随机场或超像元融合空间信息的算法比对应的没有融合空间信息的算法的分类精度高;在两组数据均使用少于1%的训练样本情况下,同时融合了超像元和子空间投影的支持向量机算法在两组实验中分类精度均为最高,整体分类精度高出其他相关算法4%左右。结论 利用超像元处理可以有效融合空间信息,降低同物异谱对分类结果的不利影响;采用子空间投影能够将高光谱数据变换到低维空间中,实现有限训练样本条件下的高精度分类;结合超像元和子空间投影支持向量机的算法能够得到较高的高光谱图像分类精度。     

面向图像复原的分层贝叶斯局部高斯混合模型

近年来使用高斯模型作为块先验的贝叶斯方法取得了优秀的图像去噪性能,但是这一方法在去噪之外的逆问题求解方面性能不太稳定。提出一种基于分层贝叶斯的高斯混合模型对图像块建模,对模型参数引入先验知识,利用Gaussian-Wishart分布对均值和协方差矩阵的概率分布建模,使得块估计过程更加稳定。基于邻近块的相干性,利用L2范数度量完成局部窗口中相似块的聚类,局部窗口相似块利用特定均值和协方差的多元高斯概率分布建模,利用累加平方图及快速傅里叶变换的数值优化方法,加快相似性度量的计算时间。使用基于马式距离的高斯分布相似度的聚合权重,结合图像上的空间域高斯相似度,更好地拟合自然图像的统计特性。通过实验验证了提出的模型在图像复原求解中的有效性。     

基于TSNE和多尺度稀疏自编码的高光谱图像分类

针对高光谱图像存在维数“灾难”、特征以及空间信息利用不足的问题,结合深度学习、流形学习及多尺度空间特征的最新进展,提出了一种TSNE和多尺度稀疏自编码网络的高光谱图像分类算法。利用TSNE算法对高光谱图像进行降维,再对每个像元的邻域进行多尺度空间特征提取,利用加入空谱联合信息的像元训练稀疏自编码网络模型并通过softmax分类器进行分类,减少计算复杂度,提高分类精确度。通过对Indian Pines及Pavia University两组数据进行实验,结果表明,提出的算法与其他五种算法相比分类效果更好。     

基于混合关节肢体模型的深度人体姿态估计方法

提出基于关节外观和关节间空间关系的模型与深层神经网络结构(DCNN)相结合的混合模型,解决人体姿态估计问题.首先,对人体构建图像模型以表示人体关节与肢体.然后,根据标注信息将图像分解为以关节为中心的若干图像块,作为训练输入数据.最后,得到一个可以解决多个分类的DCNN网络,用于人体姿态估计.文中方法对人体表示更灵活,有效提升关节点的检测率及正确检测的比率.     

Maximum likelihood estimation of Gaussian mixture models using stochastic search

Gaussian mixture models (GMM), commonly used in pattern recognition and machine learning, provide a flexible probabilistic model for the data. The conventional expectation–maximization (EM) algorithm for the maximum likelihood estimation of the parameters of GMMs is very sensitive to initialization and easily gets trapped in local maxima. Stochastic search algorithms have been popular alternatives for global optimization but their uses for GMM estimation have been limited to constrained models using identity or diagonal covariance matrices. Our major contributions in this paper are twofold. First, we present a novel parametrization for arbitrary covariance matrices that allow independent updating of individual parameters while retaining validity of the resultant matrices. Second, we propose an effective parameter matching technique to mitigate the issues related with the existence of multiple candidate solutions that are equivalent under permutations of the GMM components. Experiments on synthetic and real data sets show that the proposed framework has a robust performance and achieves significantly higher likelihood values than the EM algorithm.     

Spatial factors influencing building age prediction and implications for urban residential energy modelling

Urban energy consumption is expected to continuously increase alongside rapid urbanization. The building sector represents a key area for curbing the consumption trend and reducing energy-related emissions by adopting energy efficiency strategies. Building age acts as a proxy for building insulation properties and is an important parameter for energy models that facilitate decision making. The present study explores the potential of predicting residential building age at a large geographical scale from open spatial data sources in eight municipalities in the German federal state of North-Rhine Westphalia. The proposed framework combines building attributes with street and block metrics as classification features in a Random Forest model. Results show that the addition of urban fabric metrics improves the accuracy of building age prediction in specific training scenarios. Furthermore, the findings highlight the way in which the spatial disposition of training and test samples influences classification accuracy. Additionally, the paper investigates the impact of age misclassification on residential building heat demand estimation. The age classification model leads to reasonable errors in energy estimates, in various scenarios of training, which suggests that the proposed method is a promising addition to the urban energy modelling toolkit.