改进复杂网络模型的形状特征提取

目的 传统的基于欧氏距离的复杂网络表示方法容易受形状的非刚性变形影响。鉴于此,提出一种基于复杂网络模型与相对一致性距离相结合的形状特征提取方法。方法 首先,提取形状的边界轮廓点作为网络的节点,利用节点间的相对一致性距离作为边的权值构建初始的复杂网络模型;然后,利用阈值演化方法对初始网络模型进行动态演化,得到一系列子网络;最后,提取不同演化阶段下子网络的拓扑特征,实现对形状特征的提取。结果 分类和检索实验结果表明,相比于传统的复杂网络描述方法,本文方法对形状图像具有更强的描述和识别能力。结论 相比于传统的距离度量,相对一致性距离对形状的非刚性变形具有更强的稳定性。     

A comparison of classification algorithms in terms of speed and accuracy after the application of a post-classification modal filter

Abstract

Four different supervised classification schemes—minimum distance, decision tree, maximum likelihood and a modified minimum distance classifier (the ‘deviant distance’ algorithm)—were applied to Landsat Thematic Mapper imagery. They were compared in terms of speed of computation and classification accuracy. The processing time required by each classifier was noted and accuracy of each calculated from contingency tables. Modal filters (3×3 and 9×9) were then applied to the classified images and the processing times and classification accuracies were compared. In this empirical study it was found that although the maximum likelihood algorithm provided the most accurate classification, the use of a faster algorithm, such as minimum distance followed by the application of a modal filter, could provide classifications of similar accuracy in less than half the time taken by the supervised maximum likelihood algorithm.     

A Multiple Classifier System to improve mapping complex land covers: a case study of wetland classification using SAR data in Newfoundland,Canada

ABSTRACT

There are currently various classification algorithms, each with its own advantages and limitations. It is expected that fusing different classifiers in a way that the advantages of each are selected can boost the accuracy in the classification of complex land covers, such as wetlands, compared to using a single classifier. Classification of wetlands using remote-sensing methods is a challenging task because of considerable similarities between wetland classes. This fact is more important when utilizing synthetic aperture radar (SAR) data, which contain speckle noise. Consequently, discriminating wetland classes using only SAR data is generally not as accurate as using some other satellite data, such as optical imagery. In this study, a new Multiple Classifier System (MCS), which combines five different algorithms, was proposed to improve the classification accuracy of similar land covers. This system was then applied to classify wetlands in a study area in Newfoundland, Canada, using multi-source and multi-temporal SAR data. The results demonstrated that the proposed MCS was more accurate for the classification of wetlands in terms of both overall and class accuracies compared to applying one specific algorithm. Therefore, it is expected that the proposed system improves the classification accuracy of other complex landscapes.     

PG-RNN: using position-gated recurrent neural networks for aspect-based sentiment classification

Recently, recurrent neural networks (RNN) have achieved great success in the aspect-based sentiment classification task. Existing approaches always focus on capture the local (attentive) representation or global representation independently, while how to integrate them is not well studied. To address this problem, we propose a Position-Gated Recurrent Neural Networks (PG-RNN) model that considered aspect word position information. PG-RNN can integrate global and local information dynamically for aspect-based sentiment classification. Specifically, first, we propose a positional RNN model to integrate the aspect position information into the sentence encoder to enhance the latent representation. Unlike the existing work, we use kernel function to model position information instead of discrete distance values. Second, we design a representation absorption gating to absorb local positional representation and global representation dynamically. Experiments on five benchmark datasets show the significant advantages of our proposed model. More specifically, we achieve a maximum improvement of 7.38% over the classic attention-based RNN model in terms of accuracy.

     

PCA与移动窗小波变换的高光谱决策融合分类

目的 高光谱数据具有较高的谱间分辨率和相关性,给分类处理带来了一定的困难.为了提高分类精度,提出一种结合PCA与移动窗小波变换的高光谱决策融合分类算法.方法 首先,利用相关系数矩阵对原始高光谱数据进行波段分组;然后,利用主成分分析对每组数据进行谱间降维;再根据提出的移动窗小波变换法进行空间特征提取;最后,采用线性意见池(LOP)决策融合规则对多分类器的分类结果进行融合.结果 采用两组来自不同传感器的数据进行实验,所提算法的分类精度和Kappa系数均高于已有的5种分类算法.与SVM-RBF算法相比,本文算法的分类精度高出了8％左右.结论 实验结果表明,本文算法充分挖掘了高光谱图像的谱间-空间信息,能有效提高分类正确率,在小样本情况下和噪声环境中也具有良好的分类性能.     

S-Space: A new concept for information extraction from imaging spectrometer data

Imaging spectroscopy records the solar reflected spectrum at a fine spectral resolution and in a large number of bands thereby producing a spectral profile associated with each pixel in an image. This type of data tends to be highly correlated and we intend to harness the information of this spectral dependence by introducing the S-space concept. This concept in conjunction with measures of spatial dependence allows one to visualize the spectral profile as a regionalized variable where distance is measured in wavelengths. Unlike image space, S-space is one-dimensional. We illustrate the S-space concept using a CASI image of a forest scene and an AVIRIS image of an urban scene. This new technique provides spectral correlation information for each individual spectral profile on a per-pixel basis rather than the spectral variability across the entire image as is traditionally done in remote sensing investigations. As an example of the possibilities, spectral dependence was quantified using the semivariogram in S-space. A model of spatial dependence was then fitted to each semivariogram and the model parameters used as input to a classification algorithm in order to extract land cover information. To compare our approach with standard techniques, we used the first three principal components to produce a land cover classification. The semivariogram model parameter derived classification results displayed a better spatial contiguity and greatly diminished the dimensionality of the dataset. We also discuss future directions for the use of the S-space concept.     

基于熵加权K-means全局信息聚类的高光谱图像分类

目的 高光谱图像波段数目巨大，导致在解译及分类过程中出现“维数灾难”的现象。针对该问题，在K-means聚类算法基础上，考虑各个波段对不同聚类的重要程度，同时顾及类间信息，提出一种基于熵加权K-means全局信息聚类的高光谱图像分类算法。方法 首先，引入波段权重，用来刻画各个波段对不同聚类的重要程度，并定义熵信息测度表达该权重。其次，为避免局部最优聚类，引入类间距离测度实现全局最优聚类。最后，将上述两类测度引入K-means聚类目标函数，通过最小化目标函数得到最优分类结果。结果 为了验证提出的高光谱图像分类方法的有效性，对Salinas高光谱图像和Pavia University高光谱图像标准图中的地物类别根据其光谱反射率差异程度进行合并，将合并后的标准图作为新的标准分类图。分别采用本文算法和传统K-means算法对Salinas高光谱图像和Pavia University高光谱图像进行实验，并定性、定量地评价和分析了实验结果。对于图像中合并后的地物类别，光谱反射率差异程度大，从视觉上看，本文算法较传统K-means算法有更好的分类结果；从分类精度看，本文算法的总精度分别为92.20%和82.96%， K-means算法的总精度分别为83.39%和67.06%，较K-means算法增长8.81%和15.9%。结论 提出一种基于熵加权K-means全局信息聚类的高光谱图像分类算法，实验结果表明，本文算法对高光谱图像中具有不同光谱反射率差异程度的各类地物目标均能取得很好的分类结果。     

Comparison of a new algorithm with the supervised classifications

In this study, a new classification algorithm in which only the selected pixels have been attempted to be classified (selected pixels classification: SPC) has been introduced and compared with the well known supervised classification methods such as maximum likelihood, minimum distance, nearest neighbour and condensed nearest neighbour. To examine the algorithm, Landsat Thematic Mapper (TM) data have been used to classify the crop cover in the selected region. It is clearly demonstrated that the SPC method has the higher accuracy with comparable CPU times.     

FUZZY LABELS,IMPRECISION AND CONTEXTUAL DEPENDENCY Comments on Milan Zelený's “Cognitive Equilibrium: a Knowledge-based Theory of Fuzziness and Fuzzy Sets”

Formal concept analysis is a method of exploratory data analysis that aims at the extraction of natural clusters from object-attribute data tables. The clusters, called formal concepts, are naturally interpreted as human-perceived concepts in a traditional sense and can be partially ordered by a subconcept-superconcept hierarchy. The hierarchical structure of formal concepts (so-called concept lattice) represents a structured information obtained automatically from the input data table. The present paper focuses on the analysis of input data with a predefined hierarchy on attributes thus extending the basic approach of formal concept analysis. The motivation of the present approach derives from the fact that very often, people (consciously or unconsciously) attach various importance to attributes which is then reflected in the conceptual classification based on these attributes. We define the notion of a formal concept respecting the attribute hierarchy. Formal concepts which do not respect the hierarchy are considered not relevant. Elimination of the non-relevant concepts leads to a reduced set of extracted concepts making the discovered structure of hidden concepts more comprehensible. We present basic formal results on our approach as well as illustrating examples.     

An innovative technique for web text watermarking (AITW)

ABSTRACT

Embedding a hidden stream of bits in a cover file to prevent illegal use is called digital watermarking. The cover file could be a text, image, video, or audio. In this study, we propose invisible watermarking based on the text included in a webpage. Watermarks are based on predefined structural and syntactic rules, which are encrypted and then converted into zero-width control characters using binary model classification before embedding into a webpage. This concept means that HTML (Hyper Text Markup Language) is used as a cover file to embed the hashed and transparent zero-width watermarks. We have implemented the proposed invisible watermarking against various attacks to reach optimum robustness.     

融合最小化失真与模型保持的隐写算法

目的 为了保证载密图像的抗统计分析能力同时避免对特定载体模型的过度优化,提出一种以最小化失真为目标的隐写算法。方法 算法以各方向元素基团为基本单元定义失真函数,以Fisher准则函数的极大值为标准对失真参数进行优化,将失真函数与统计特征相关联。在秘密信息的嵌入过程中,首先依据邻域系统将图像载体分为若干元素阵列,令不同的阵列对应不同的特征子集,再利用Gibbs抽样和STC(Syndrome-trellis code)编码实现对这些有所差异的特征子集的集成,从而在最小化失真的同时保持载体的统计特征。结果 在3组不同维数的检测算法下比较该算法与同类算法的分类误差。结果表明,该算法能更好地保持统计模型,嵌入率为0.5 bit/pixle时相应特征集的检测误差仍高于0.4,面临高维检测时算法同样具有较高的安全性。结论 该算法借助最小失真思想实现了隐写前后统计特征的保持,且有效避免了在不完整模型上的过度优化,拥有比同类算法更好的适应性和安全性。     

A dictionary matrix generation based compression and bitwise embedding mechanisms for ECG signal classification

The Electrocardiogram (ECG) signal processing is one of the exciting research areas in recent days. Ensuring security to the patient’s confidential information is a demanding critical task in many healthcare systems. So, the traditional works developed the security mechanisms for embedding the original ECG signal with the image, audio, or video. But, it does not focus on reducing the size of the original message before transmitting it to others. Also, it has significant limitations of inefficient security, increased complexity, and reduced classification accuracy. To rectify this issue, our research proposed the new embedding mechanism to improve the security of patient’s health information. In this system, the original ECG signals compressed at the initial stage by using the proposed Dictionary Matrix Generation (DMG) algorithm. Then, the compressed signals embedded within the cover image by using the Bitwise Embedding (BE) mechanism. At the receiver side, the bedded goal is de-embedded and decompressed by using the DMG and BE algorithms. The features such as spectral and peak values of the signal are extracted for increasing the efficiency of classification. Classification and detection of abnormality present in ECG signal of patient is the most essential part. To achieve this, we proposed the Modified Dynamic Classification (MDC) algorithm based on the features. In this work, the novelty is implemented in the compression, embedding, and classification stages. The proposed system reduces the data loss during transmission, memory storage and time complexity. The overall process evaluated by using PTB diagnostic ECG database. In experiments, the proposed classification technique provides the accuracy of 98.39% and it proved that the proposed method had highest performances than existing methods such as PNN, SVM and RF classification.

     

Structured approach to land cover mapping or the Atlantic zone of Costa Rica using single date TM data

Abstract

A structured approach to land cover mapping, involving different stages of field work and processing of remote sensing data, is presented. The Processing of TM data of one acquisition date was done by Analysing the Digital data-Structure (PAD) to produce optimum imagery for land-cover mapping of the Atlantic zone in Costa Rica.

Three stages were evaluated:

1. Image-processing in the pre-fieldwork stage to obtain insight into the overall variation of the scene.

2. Small scale reconnaissance fieldwork, and processing thereafter, directed towards the production of thematic imagery guided by the properties of objects and features.

3. Medium scale reconnaissance fieldwork and classification.

With this method we made use of statistical data, such as standard deviations and correlation coefficients, graphic presentations of mean values for the evaluation of ratios as well as variance percentages expressed by principal components. The selection of training fields for statistic calculation was considered to be essential for the final result.     

基于粗糙集和图论的电力系统故障诊断方法

将粗糙集与图论相结合处理电力系统故障诊断,提出了故障决策表图的新概念,得到一种基于粗糙集和图论的电力系统故障诊断方法,并进一步提出了故障信息覆盖度和故障诊断规则分级的概念.利用故障决策表图及其邻接矩阵,得到了快速识别决策表核属性和属性约简的方法,并将规则分级应用于故障规则提取.利用所提出的方法对具体实例进行处理,仿真结果表明,该方法能有效地减少时间和空间复杂度,可根据设定的阈值提取诊断规则.     

卷积神经网络和深度置信网络在SAR影像冰水分类的性能评估

目的 海冰分类是海冰监测的主要任务之一。目前基于合成孔径雷达SAR影像的海冰分类方法分为两类：一类是基于海冰物理特性与SAR成像特征等进行分类,这需要一定的专业背景;另一类基于传统的图像特征分类,需要人为设计特征,受限于先验知识。近年来深度学习在图像分类和目标识别方面取得了巨大的成功,为了提高海冰分类精度及海冰分类速度,本文尝试将卷积神经网络（CNN）和深度置信网络（DBN）用于海冰的冰水分类,评估不同类型深度学习模型在SAR影像海冰分类方面的性能及其影响因素。方法 首先根据加拿大海冰服务局（CIS）的冰蛋图构建海冰的冰水数据集;然后设计卷积神经网络和深度置信网络的网络架构;最后评估两种模型在不同训练样本尺寸、不同数据集大小和网络层数、不同冰水比例的测试影像以及不同中值滤波窗口的分类性能。结果 两种模型的总体分类准确率达到93%以上,Kappa系数0.8以上,根据分类结果得到的海冰区域密集度与CIS的冰蛋图海冰密集度数据一致。海冰的训练样本尺寸对分类结果影响显著,而训练集大小以及网络层数的影响较小。在本文的实验条件下,CNN和DBN网络的最佳分类样本尺寸分别是16×16像素和32×32像素。结论 利用CNN和DBN模型对SAR影像海冰冰水分类,并进行性能分析。发现深度学习模型用于SAR影像海冰分类具有潜力,与现有的海冰解译图的制作流程和信息量相比,基于深度学习模型的SAR影像海冰分类可以提供更加详细的海冰地理分布信息,并且减小时间和资源成本。     

Classification and Concept Consistency

Abstract

This article investigates the extent to which undergraduates consistently use a single mechanism as a basis for classifying mathematical objects. We argue that the concept image/concept definition distinction focuses on whether students use an accepted definition but does not necessarily capture the more basic notion that there should be a fixed basis for classification. We examine students’ classifications of real sequences before and after exposure to definitions of increasing and decreasing; we develop an abductive plausible explanations method to estimate the consistency within the participants’ responses and suggest that this provides evidence that many students may lack what we call concept consistency.     

结合类内和类间距离的可能聚类分割算法

目的 为了进一步提高噪声图像分割的抗噪性和准确性,提出一种结合类内距离和类间距离的改进可能聚类算法并将其应用于图像分割。方法 该算法避免了传统可能性聚类分割算法中仅仅考虑以样本点到聚类中心的距离作为算法的测度,将类内距离与类间距离相结合作为算法的新测度,即考虑了类内紧密程度又考虑了类间离散程度,以便对不同的聚类结构有较强的稳定性和更好的抗噪能力,并且将直方图融入可能模糊聚类分割算法中提出快速可能模糊聚类分割算法,使其对各种较复杂图像的分割具有即时性。结果 通过人工合成图像和实际遥感图像分割测试结果表明,本文改进可能聚类算法是有效的,其分割轮廓清晰,分类准确且噪声较小,其误分率相比其他算法至少降低了2个百分点,同时能获得更满意的分割效果。结论 针对模糊C-均值聚类分割算法和可能性聚类分割算法对于背景和目标颜色相近的图像分类不准确的缺陷,将类内距离与类间距离相结合作为算法的测度有效的解决了图像分割归类问题,并且结合直方图提出快速可能模糊聚类分割算法使其对于大篇幅复杂图像也具有适用性。     

自适应对称自回归模型的压缩图像内插方法

目的 大多数图像内插方法只考虑低分辨率图像的下采样降质过程,忽略编码噪声的影响。提出一种新的自适应对称自回归模型的压缩图像内插方法。方法 假设局部图像相似的图像块具有相同的图像内插模型。方法分为训练和重建两个阶段。在训练阶段,首先对训练图像采用主成分分析提取图像块的局部梯度主方向,根据方向进行一次分类,分别建立各个方向的对称自回归模型和训练集;其次对每个方向的训练集,根据图像基元特征,利用K均值聚类方法进行二次分类;最后对每个二次分类训练子集,选择其所属方向类的模型,使用有约束的最小二乘法估计对应于该子集的模型系数。在重建阶段,首先根据测试图像块的局部梯度主方向,确定方向类别,再计算测试块基元特征和该方向类中所有聚类中心的欧氏距离,选择具有最小欧氏距离的聚类中心的自回归模型用于内插。结果 采用8种不同的测试图像在JPEG的2种量化方式条件下进行测试,与7种典型的图像内插相比,结果表明本文方法能够有效地克服编码噪声的影响,峰值信噪比(PSNR)和结构相似度(SSIM)均优于其他方法。结论 本文方法具有较低的复杂度,可以适用于图像通信中增强图像的分辨率。     

极化SAR相干斑抑制的非局部加权最小均方误差滤波算法

目的 相干斑的存在严重影响了极化合成孔径雷达(PolSAR)的影像质量.对相干斑的抑制是使用SAR数据的必不可少的预处理程序.提出一种基于非局部加权的线性最小均方误差(LMMSE)滤波器的极化SAR滤波的方法.方法 该方法的主要过程是利用非局部均值的理论来获取LMMSE估计器中像素样本的权重.同时,在样本像素的选取过程中,利用待处理像素的极化散射特性和邻域块的异质性来排除不相似像素以加速算法,同时达到保持点目标和自适应调节块窗口大小的目的.结果 模拟影像和真实影像上进行的实验结果表明,采用这种方法滤波后影像的质量得到明显改善.和传统的LMMSE算法相比,无论是单视的影像还是多视的影像,本文方法去噪结果的等效视数都高出8视以上;峰值信噪比也提升了5.8 dB.同时,去噪后影像分类的总体精度也达到了83％以上,该方法的运行效率也比非局部均值算法有了较大提升.结论 本文方法不仅能够有效抑制相干斑噪声,还能较好地保持边缘和细节信息以及极化散射特性.这将会为后续高效利用SAR数据提供保障.     

A NEW FUZZY-DATA MINING METHOD FOR PATTERN CLASSIFICATION BY PRINCIPAL COMPONENT ANALYSIS

ABSTRACT

Data mining techniques can be used to discover useful information by exploring and analyzing data. The aim of this article is to propose a new fuzzy-data mining method to find a compact set consisting of fuzzy if-then classification rules with high classification capability using the genetic algorithm. Furthermore, for not reducing the usefulness of the proposed method for classification problems with high dimensional feature space, the curse dimensionality resulting from the grid partition is overcome in the proposed method by employing the principal component analysis to reduce the dimensions. Through computer simulations, it can be seen that the proposed method is comparable to the other fuzzy classification methods on the well-known iris data, the appendicitis data, and the cancer data.