检索结果-南通市图书馆

同方期刊数据库

Orthogonal Discriminant Improved Local Tangent Space Alignment Based Feature Fusion for Face Recognition

在线全文

学校读者我要写书评

暂无评论

Journal of Shanghai Jiaotong university(Science) 2013年第4期18卷 425-433页

作者：张强蔡云泽许晓鸣 School of Electronic Information and Electrical Engineering Shanghai Jiaotong University University of Shanghai for Science and Technology Shanghai Academy of Systems Science

Improved local tangent space alignment (ILTSA) is a recent nonlinear dimensionality reduction method which can efficiently recover the geometrical structure of sparse or non-uniformly distributed data manifold. In this paper, based on combination of modified maximum margin criterion and ILTSA, a novel feature extraction method named orthogonal discriminant improved local tangent space alignment (ODILTSA) is proposed. ODILTSA can preserve local geometry structure and maximize the margin between different classes simultaneously. Based on ODILTSA, a novel face recognition method which combines augmented complex wavelet features and original image features is developed. Experimental results on Yale, AR and PIE face databases demonstrate the effectiveness of ODILTSA and the feature fusion method.

关键词： manifold learning linear extension orthogonal discriminant improved local tangent space alignment (ODILTSA) augmented Gabor-like complex wavelet transform face recognition information fusion

Pandemic Policymaking

在线全文

学校读者我要写书评

暂无评论

Journal of Social Computing 2021年第1期2卷 14-26页

作者： Philip D.Waggoner niversity of Chicago ChicagoIL 60637USAand also with Columbia UniversityNew YorkNY 10027USA.

This study leverages a high dimensional manifold learning design to explore the latent structure of the pandemic policymaking space only based on bill-level characteristics of pandemic-focused bills from 1973 to *** indicate the COVID-19 era of policymaking maps extremely closely onto prior periods of related *** suggests that there is striking uniformity in Congressional policymaking related to these types of large-scale crises over time,despite currently operating in a unique era of hyperpolarization,division,and ineffective governance.

关键词： manifold learning computational social science congress policymaking COVID-19

manifold contraction for semi-supervised classification

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2010年第6期53卷 1170-1187页

作者： HU EnLiang 1,2 , CHEN SongCan 1 & YIN XueSong 1 1 School of Computer Science & Engineering, Nanjing University of Aeronautics & Astronautics, Nanjing 210016, China 2 School of Mathematics, Yunnan Normal University, Kunming 650092, China School of Computer Science & Engineering Nanjing University of Aeronautics & Astronautics Nanjing China School of Mathematics Yunnan Normal University Kunming China

The generalization ability of classification is often closely related to both the intra-class compactness and the inter-class *** to the fact that many current dimensionality reduction methods, regarded as a pre-processor, often lead to the poor classification performance on real-life data, in this paper, a new data preprocessing technique called manifold contraction(MC) is proposed for the classification-oriented learning *** main motivation behind MC lies in seeking a proper mapping of contracting the given multiple-manifold data such that the ratio of the intra-class to the inter-class scatters is ***, in order to properly control the contraction level in MC, an adaptive MC(AMC) criterion is developed in the semi-supervised *** to its generality, MC can be not only applied in original space and reproducing kernel Hilbert space(RKHS), but also easily incorporated with dimensionality reduction method for further improvement of classification *** final experimental results show that MC, as a data preprocessor, is effective and promising in the subsequent classification learning, especially in small-size labeled sample case.

关键词： manifold learning dimensionality reduction lower-dimensional embedding semi-supervised learning classification manifold contraction adaptive manifold contraction

FAST FEATURE RANKING AND ITS APPLICATION TO FACE RECOGNITION

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Transactions of Nanjing University of Aeronautics and Astronautics 2013年第4期30卷 389-396页

作者：潘锋王建东宋广为牛奔顾其威 College of Management Shenzhen University College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics

A fast feature ranking algorithm for classification in the presence of high dimensionahty and small sample size is proposed. The basic idea is that the important features force the data points of the same class to maintain their intrinsic neighbor relations, whereas neighboring points of different classes are no longer to stick to one an- other. Applying this assumption, an optimization problem weighting each feature is derived. The algorithm does not involve the dense matrix eigen-decomposition which can be computationally expensive in time. Extensive exper- iments are conducted to validate the significance of selected features using the Yale, Extended YaleB and PIE data- sets. The thorough evaluation shows that, using one-nearest neighbor classifier, the recognition rates using 100-- 500 leading features selected by the algorithm distinctively outperform those with features selected by the baseline feature selection algorithms, while using support vector machine features selected by the algorithm show less prominent improvement. Moreover, the experiments demonstrate that the proposed algorithm is particularly effi- cient for multi-class face recognition problem.

关键词： feature selection feature ranking manifold learning Laplacian matrix

Supervised Kernel Uncorrelated Discriminant Neighborhood Preserving Projections

在线全文

学校读者我要写书评

暂无评论

Journal of Donghua University(English Edition) 2012年第5期29卷 446-449页

作者：罗磊周晖徐晨李丹美 School of Electronics and Information Nantong University School of Information Science and Technology Donghua University

To separate each pattern class more strongly and deal with nonlinear ease, a new nonlinear manifold learning algorithm named supervised kernel uneorrelated diseriminant neighborhood preserving projections （SKUDNPP） is proposed. The algorithm utilizes supervised weight and kernel technique which makes the algorithm cope with classifying and nonlinear problems competently. The within-class geometric structure is preserved, while maximizing the between-class distance. And the features extracted are statistically uneorrelated by introducing an uneorrelated constraint. Experiment results on millimeter wave （MMW） radar target recognition show that the method can give competitive results in comparison with current papular algorithms.

关键词： manifold learning dimensionality reduction kernel technique uncorrelated discriminant neighborhood preserving projections

An Unsupervised Kernel Optimization in Dimensional Reduction

在线全文

学校读者我要写书评

暂无评论

An Unsupervised Kernel Optimization in Dimensional Reduction

Probability Reconstruction based on Graph Distance Neighbor Network for Visualizing Data 36

第25届中国控制与决策会议

作者： Yuqing Shi Shiqiang Du Weilan Wang School of Electrical Engineering Northwest University for Nationalities School of Mathematics and Computer Science Northwest University for Nationalities

ISBN: (纸本)9781467355322

Subspace analysis is an effective dimensional reduction approach for face recognition. Finding a suitable low dimensional subspace is a key step of subspace analysis, for it has a direct effect on recognition performance. In this paper, we propose a new subspace analysis method called center kernel unsupervised discriminant projection (CKUDP). The kernel trick is adopted to allow the efficient computation of unsupervised discriminant projection in high-dimensional feature space. Moreover, a center solution for obtaining the optimal feature vectors in feature space is presented which can preserve the most discriminative information. Experiments results on the ORL database and Yale database demonstrate the utility of the proposed approach.

关键词： kernel method manifold learning central kernel unsupervised discriminant analysis

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Probability Reconstruction based on Graph Distance Neighbor ...

LLE-BASED CLASSIFICATION ALGORITHM FOR MMW RADAR TARGET RECOGNITION

第36届中国控制会议

作者： Jincong Lin Jingqi Yan Department of Automation Shanghai Jiao Tong University

ISBN: (纸本)9781538629185

In the era of information exploration,it is an urgent need to process and analyze high-dimensional data sets which may contain thousands of *** high-dimensional data can be unfolded in a two or three-dimensional map,we can intuitively learn about the main structure of the data,which will greatly benefit data exploration and pattern *** visualization technique which aims to reveal the low-dimensional manifold embedded in the high-dimensional data can complete the challenging task *** paper introduces a new visualization algorithm called probability reconstruction based on graph distance neighbor network（PR-GDNN）.The PR-GDNN algorithm uses the graph distance to construct a neighbor network,then performs the probability reconstruction inferred from the neighborhood relationship,and finally minimizes the Kullback-Leibler *** these operations,the PR-GDNN algorithm has a better performance than the classical embedding algorithms in revealing the structure of *** keeping the local *** qualitative and quantitative comparisons on three standard data sets demonstrate the superiority of the proposed algorithm.

关键词： Visualization manifold learning Dimensionality reduction Graph distance Probability reconstruction

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Electronics(China) 2010年第1期27卷 139-144页

作者： Luo Lei Li Yuehua Luan Yinghong School of Electronic Engineering and Optoelectronic Technology Nanjing University of Science and Technology Nanjing 210094 China

In this paper,a new multiclass classification algorithm is proposed based on the idea of Locally Linear Embedding(LLE),to avoid the defect of traditional manifold learning algorithms,which can not deal with new sample *** algorithm defines an error as a criterion by computing a sample's reconstruction weight using ***,the existence and characteristics of low dimensional manifold in range-profile time-frequency information are explored using manifold learning algorithm,aiming at the problem of target recognition about high range resolution MilliMeter-Wave(MMW) *** new algorithm is applied to radar target *** experiment results show the algorithm is *** with other classification algorithms,our method improves the recognition precision and the result is not sensitive to input parameters.

关键词： manifold learning Locally Linear Embedding(LLE) Multi-class classification MilliMeter-Wave(MMW) Target recognition

A feature extraction method for synthetic aperture radar(SAR) automatic target recognition based on maximum interclass distance

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2011年第10期54卷 2520-2524页

作者： WANG Bing HUANG YuLin YANG JianYu WU JunJie School of Electronic Engineering University of Electronic Science and Technology of China ( UESTC) Chendu 611731 China

Synthetic aperture radar(SAR) automatic target recognition is an important application in *** to extract features has restricted the application of SAR technology *** this paper,a new feature extraction method for SAR automatic target recognition based on maximum interclass distance is proposed,which integrates class and neighborhood *** method can reinforce discriminative power using maximum interclass distance,so it can improve recognition rate effectively.

关键词： synthetic aperture radar (SAR) automatic target recognition (ATR) manifold learning feature extraction

同方期刊数据库