一种基于规范互信息和动态冗余信号识别技术的特征选择方法

为了实现对模式识别、信号处理等领域中数据的有效表达,提出了一种基于规范互信息和动态冗余信号识别技术的特征选择方法。该方法采用规范互信息对特征相关性和冗余性进行测量,并通过一种动态冗余信号识别技术在特征全集中进行冗余特征的筛选。分类实验结果表明所提特征选择方法性能优于典型的特征选择方法。     

Learning algorithm for pattern classification using cellular neuralnetworks

A new learning algorithm for pattern classification using cellular neural networks is described. The authors show that patterns belonging to the training set as well as patterns outside it can be classified reliably using the proposed algorithm. Comparisons with well established classification techniques clearly highlight the performances of the approach developed herein     

基于矩阵灰建模的单次P300检测新方法

针对少导联P300单次提取识别率较低的问题,提出了一种基于矩阵灰建模的参数模型法提取特征的方法,提高了P300单次识别率.首先对脑电信号进行预处理,然后选择导联组合,接着对每个Epoch进行建模,将模型参数作为特征向量输入SVM分类识别.结果表明,单次P300的平均识别率为91.43%,叠加平均3次正确率可高达97.87%.     

P2P网络聚合流量识别技术研究

对等体网络P2P（Peer-to-Peer）应用系统中对等体主机的行为特征与P2P业务流量特征多样化、复杂化,使得单纯利用一种典型特征的P2P流量分类技术的识别精度不高。文中提出了一种新的P2P流量多阶段识别方法,该方法根据P2P应用流量的一系列固有特征,可以从聚合网络流中识别P2P流量。通过实验表明,丈中所提出的方法P2P流识别精度可达99．7％,同时错误分类精度0．3％。     

数据库样本缺失下的雷达辐射源识别

目前,基于机器学习的雷达辐射源识别技术大多以训练集和测试集同分布为假设,当雷达数据库样本不足导致与信号真实分布存在偏差时,传统的分类方法效果不佳.为此,将迁移学习理论引入识别系统,设计了一种基于结构发现与再平衡的雷达辐射源信号识别方法.通过对数据库和待识别辐射源信号样本进行聚类分析发现数据结构信息,通过重采样处理修正其分布差异.将新采样数据输入支持向量机进行训练并对侦收样本进行识别.仿真实验表明,在新训练样本集上学习的模型对测试集的分类性能有了很大的提升.     

一种创新性激光图像三维目标识别算法

针对径向基神经网络在激光图像分类识别中识别率低及训练时间长的问题,提出粗糙集与神经网络相结合的方法,将粗糙集算法简约后的样本特征作为神经网络的前置输入。首先建立不同视点的激光主动成像三维仿真图像,然后提取17个目标特征,并采用粗糙集算法选择分类的属性,从17个特征中筛选出5个影响决策的特征属性,最后选用4层径向基神经网络作为基本的网络结构,并采用在各层节点上与粗糙集相结合方法识别目标。仿真结果表明,结合粗糙集的集成神经网络方法识别正确率保持在80%以上,与未结合粗糙集的神经网络相当,但训练与识别时间缩短10倍以上。     

强混叠模式下基于神经元捕获/抑制原理的分类器设计

目前的许多分类器设计方法,如多层感知器网络(MLP)、支持向量机(SVM)、相关向量机(RVM)、径向基函数网络(RBF)等,实际是非线性映射加线性分类的方法,即将输入空间的非线性可分问题经非线性映射到另一空间,在那一空间实现线性分类.本文则开拓性的运用脉冲耦合神经网络神经元的点火捕获的思想,提出了一种基于耦合神经元点火捕获/抑制特性的分类器设计方法,使一类样本对应神经元总是较其它类样本对应神经元先点火以实现对样本的有效分类.所设计的分类器可实现对样本空间中任意复杂分布训练样本的非线性稳健分类,特别是有效实现复杂混叠模式的模式稳健分类,大量复杂混叠模式分类问题的仿真实验验证了本文方法的有效性和可行性,并应用于微波暗室实测一维距离像数据的自动目标识别中.     

A minimum entropy based switched adaptive predictor for lossless compression of images

The gradient adjusted predictor (GAP) uses seven fixed slope quantization bins and a predictor is associated with each bin, for prediction of pixels. The slope bin boundary in the same appears to be fixed without employing a criterion function. This paper presents a technique for slope classification that results in slope bins which are optimum for a given set of images. It also presents two techniques that find predictors which are statistically optimal for each of the slope bins. Slope classification and the predictors associated with the slope bins are obtained off-line. To find a representative predictor for a bin, a set of least-squares (LS) based predictors are obtained for all the pixels belonging to that bin. A predictor, from the set of predictors, that results in the minimum prediction error energy is chosen to represent the bin. Alternatively, the predictor is chosen, from the same set, based on minimum entropy as the criterion. Simulation results, of the proposed method have shown a significant improvement in the compression performance as compared to the GAP. Computational complexity of the proposed method , excluding the training process, is of the same order as that of GAP.     

基于神经网络的海面溢油图像分类算法

提出了一种基于Gabor变换、KPCA和神经网络的图像分类方法。首先对图像进行Gabor滤波,获得不同方向的特征参数;然后提取图像的KPCA作为图像的特征,最后利用神经网络进行分类。通过对实验分类结果的定量分析可知,该方法可以获得精度比最小分类模型方法以及最大似然分布模型方法高的分类结果。     

基于邻域最小生成树的半监督极化SAR图像分类方法

该文针对极化SAR图像分类中只有少量标记样本的问题,提出了一种基于邻域最小生成树的半监督极化SAR图像分类方法。该方法针对极化SAR图像以像素为分类对象的特点,结合自训练方法的思想,利用极化SAR图像像素点的空间信息,提出了基于邻域最小生成树辅助学习的样本选择策略,增加自训练过程中被选择无标记样本的可靠性,扩充标记样本数量,训练更好的分类器。最终用训练好的分类器对极化SAR图像进行测试。对3组真实的极化SAR图像进行测试,实验结果表明,该方法在只有少量标记样本的情况下能获得满意的分类结果,且分类正确率明显优于传统的分类算法。      

利用CNN的海上目标探测背景分类方法

该文主要研究基于卷积神经网络（Convolutional Neural Networks,CNN）的海上目标探测背景分类方法.以CNN中的经典网络LeNet为例,基于IPIX雷达实测数据集,进行控制变量的模型训练,对分类准确率、训练速度、一维信号的二维特征图变化等进行分析,基于实测数据集验证了利用CNN在一维雷达回波信号中进行海杂波与噪声分类的可行性,并同步分析了数据预处理、单个样本序列长度、网络结构参数等影响因素对分类准确率的影响,并针对典型探测场景分类进行了验证.结果表明,LeNet卷积神经网络在海上探测背景区分方面,具有很高的分类准确率,并且数据预处理方式、单个样本序列长度对结果影响显著,而网络结构参数有一定的调节区间,在此区间内调整,影响不显著,所提方法在顺/逆浪向、高/低海况条件下杂波分类与杂噪分类方面具有很高的准确率.     

Partially Supervised classification of remote sensing images through SVM-based probability density estimation

A general problem of supervised remotely sensed image classification assumes prior knowledge to be available for all the thematic classes that are present in the considered dataset. However, the ground-truth map representing that prior knowledge usually does not really describe all the land-cover typologies in the image, and the generation of a complete training set often represents a time-consuming, difficult and expensive task. This problem affects the performances of supervised classifiers, which erroneously assign each sample drawn from an unknown class to one of the known classes. In the present paper, a classification strategy is described that allows the identification of samples drawn from unknown classes through the application of a suitable Bayesian decision rule. The proposed approach is based on support vector machines (SVMs) for the estimation of probability density functions and on a recursive procedure to generate prior probability estimates for known and unknown classes. In the experiments, both a synthetic dataset and two real datasets were used.     

Representative band selection for hyperspectral image classification

High dimensional curse for hyperspectral images is one major challenge in image classification. In this work, we introduce a novel spectral band selection method by representative band mining. In the proposed method, the distance between two spectral bands is measured by using disjoint information. For band selection, all spectral bands are first grouped into clusters, and representative bands are selected from these clusters. Different from existing clustering-based band selection methods which select bands from each cluster individually, the proposed method aims to select representative bands simultaneously by exploring the relationship among all band clusters. The optimal representative band selection is based on the criteria of minimizing the distance inside each cluster and maximizing the distance among different representative bands. These selected bands can be further applied in hyperspectral image classification. Experiments are conducted on the 92AV3C Indian Pine data set. Experimental results show that the disjoint information-based spectral band distance measure is effective and the proposed representative band selection approach outperforms state-of-the-art methods for high dimensional image classification.     

基于L1范数凸包数据描述的多观测样本分类算法

为建立高维空间样本分布的最佳覆盖为目标来实现覆盖分类,该文提出基于L1范数凸包数据描述的多观测样本分类算法。首先对训练集的每个类别以及测试集的多观测样本分别构造凸包模型,这样多观测样本的分类就转化为凸包模型的相似性度量问题。若测试集的凸包模型与训练集无重叠,采用L1范数距离测度进行凸包模型之间的相似性度量;若有重叠,采用L1范数距离测度进行收缩凸包(reduced convex hulls)之间的相似性度量。然后采用最近邻准则作为多观测样本的分类决策。在3个数据库上进行的实验结果,表明该文提出方法对于多观测样本分类具有可行性和有效性。     

基于触摸显示屏的人机交互手势分析

针对触摸显示屏的操作特点提出了一种基于元动作的触摸手势分类和表示方法,根据人机交互要求定义了一套笔画触摸手势,提出了基于RBF神经网络的笔画触摸手势训练和识别方法。测试结果表明,所提出的方法能够快速、准确地对触摸手势进行训练和识别,可以为带触摸屏的设备提供一个更加自然、直观的人机交互手段。     

Biologically Inspired Feature Manifold for Scene Classification

Biologically inspired feature (BIF) and its variations have been demonstrated to be effective and efficient for scene classification. It is unreasonable to measure the dissimilarity between two BIFs based on their Euclidean distance. This is because BIFs are extrinsically very high dimensional and intrinsically low dimensional, i.e., BIFs are sampled from a low-dimensional manifold and embedded in a high-dimensional space. Therefore, it is essential to find the intrinsic structure of a set of BIFs, obtain a suitable mapping to implement the dimensionality reduction, and measure the dissimilarity between two BIFs in the low-dimensional space based on their Euclidean distance. In this paper, we study the manifold constructed by a set of BIFs utilized for scene classification, form a new dimensionality reduction algorithm by preserving both the geometry of intra BIFs and the discriminative information inter BIFs termed Discriminative and Geometry Preserving Projections (DGPP), and construct a new framework for scene classification. In this framework, we represent an image based on a new BIF, which combines the intensity channel, the color channel, and the C1 unit of a color image; then we project the high-dimensional BIF to a low-dimensional space based on DGPP; and, finally, we conduct the classification based on the multiclass support vector machine (SVM). Thorough empirical studies based on the USC scene dataset demonstrate that the proposed framework improves the classification rates around 100% relatively and the training speed 60 times for different sites in comparing with previous gist proposed by Siagian and Itti in 2007.     

Consensual and Hierarchical Classification of Remotely Sensed Multispectral Images

Consensual and hierarchical approaches are developed for the classification of remotely sensed multispectral images. The proposed method consists of preprocessing of input patterns, generating multiple classification results by hierarchical neural networks, and a combining scheme to generate a consensus of multiple classification results. Transformations of input patterns by random matrices and nonlinear filtering are used for preprocessing. By varying the input patterns, the multiple classification results are generated with sufficiently independent errors by using a single type of classifier. This helps to improve classification performance when the multiple classification results are combined. Hierarchical neural networks involve the use of successive classifiers which are tuned to reduce the remaining errors to increase the classification performance. This structure includes detection schemes to decide whether successive classifiers are utilized for each input. Consensual and hierarchical approaches generate more reliable and accurate results based on group decision.     

Neural network approach to land cover mapping

A pattern classification method is proposed for remote sensing data using neural networks. First, the authors apply the error backpropagation (BP) algorithm to classify the remote sensing data. In this case, the classification performance depends on a training data set. In order to get stable and precise classification results, the training data set is selected based on geographical information and Kohonen's self-organizing feature map. Using the training data set and the error backpropagation algorithm, a layered neural network is trained such that the training patterns are classified with a specified accuracy. After training the neural network, some pixels are deleted from the original training data set if they are incorrectly classified and a new training data set is built up. Once training is complete, a testing data set is classified by using the trained neural network. The classification results of LANDSAT TM data show that this approach produces excellent results which are more realistic and noiseless compared with a conventional Bayesian method     

基于同步压缩小波变换的主信号抑制技术

在辐射源个体识别(SEI)技术中,能量较高的主信号往往导致微弱个体特征稳定性降低,进而影响最终的个体识别效果。为了解决该问题并提升辐射源个体识别性能,该文提出基于同步压缩小波变换的主信号抑制技术。首先,利用静态小波变换完成对带噪信号的去噪预处理;然后,利用同步压缩小波变换完成对主信号的检测和抑制,并以均方根误差和皮尔逊相关系数为数值指标,验证算法的有效性;最后,在主信号抑制的基础上,利用分形理论中盒维数完成对信号的特征提取,并利用单核支持向量机验证个体识别性能。实验结果表明,与主信号抑制之前相比,主信号抑制算法下个体识别率提升了10%左右,验证了同步压缩小波变换的主信号抑制算法对辐射源个体识别率提升的有效性。     

Identification of active users in synchronous CDMA multiuserdetection

The level of multiple access interference (MAI) in code division multiple access (CDMA) communication systems is a time-varying parameter related to the number of active users. Almost all existing multiuser detection schemes were designed based on a priori information of the active users. In many situations, however, the multiuser receiver does not know the number of active users, and the receiver designed for the detection of all users may lead to poor performance. To develop a more efficient detection scheme in practical applications, we propose a two-stage detection structure consisting of preprocessing (identification) and postprocessing (detection). In the preprocessing, we apply the subspace concept and a method based on the multiple signal classification (MUSIC) algorithm to identify the active users while requiring only a priori knowledge of all of the users' signature sequences. The proposed preprocessor is shown to be asymptotically near-far resistant, and to have the ability to identify the active users in a simple and reliable way. While in the detection process, as we efficiently use the active users' information in every observation interval, the performance is clearly improved compared to the conventional structure without identification. Moreover, the effect of imperfect identification on the decorrelating detector is also extensively analyzed. Though the decorrelating detector's inherent near-far resistant characteristic is impaired by imperfect identification, the proposed structure still outperforms the conventional structure in the general near-far environment