Dimensionality reduction techniques play an important role in data mining. Kernel entropy component analysis( KECA) is a newly developed method for data transformation and dimensionality reduction. This paper conducte...Dimensionality reduction techniques play an important role in data mining. Kernel entropy component analysis( KECA) is a newly developed method for data transformation and dimensionality reduction. This paper conducted a comparative study of KECA with other five dimensionality reduction methods,principal component analysis( PCA),kernel PCA( KPCA),locally linear embedding( LLE),laplacian eigenmaps( LAE) and diffusion maps( DM). Three quality assessment criteria, local continuity meta-criterion( LCMC),trustworthiness and continuity measure(T&C),and mean relative rank error( MRRE) are applied as direct performance indexes to assess those dimensionality reduction methods. Moreover,the clustering accuracy is used as an indirect performance index to evaluate the quality of the representative data gotten by those methods. The comparisons are performed on six datasets and the results are analyzed by Friedman test with the corresponding post-hoc tests. The results indicate that KECA shows an excellent performance in both quality assessment criteria and clustering accuracy assessing.展开更多
The accurate extraction and classification of leather defects is an important guarantee for the automation and quality evaluation of leather industry. Aiming at the problem of data classification of leather defects,a ...The accurate extraction and classification of leather defects is an important guarantee for the automation and quality evaluation of leather industry. Aiming at the problem of data classification of leather defects,a hierarchical classification for defects is proposed.Firstly,samples are collected according to the method of minimum rectangle,and defects are extracted by image processing method.According to the geometric features of representation, they are divided into dot,line and surface for rough classification. From analysing the data which extracting the defects of geometry,gray and texture,the dominating characteristics can be acquired. Each type of defect by choosing different and representative characteristics,reducing the dimension of the data,and through these characteristics of clustering to achieve convergence effectively,realize extracted accurately,and digitized the defect characteristics,eventually establish the database. The results showthat this method can achieve more than 90% accuracy and greatly improve the accuracy of classification.展开更多
Liquid state methanol and ethanol under different temperatures have been investigated by FT-NIR(Fourier transform nearinfrared) spectroscopy,generalized two-dimensional(2D) correlation spectroscopy,and PCA(principal c...Liquid state methanol and ethanol under different temperatures have been investigated by FT-NIR(Fourier transform nearinfrared) spectroscopy,generalized two-dimensional(2D) correlation spectroscopy,and PCA(principal component analysis) . First,the FT-NIR spectra were measured over a temperature range of 30-64(or 30-71) °C,and then the 2D correlation spectra were computed.Combining near-infrared spectroscopy,generalized 2D correlation spectroscopy,and references,we analyzed the molecular structures(especially the hydrogen bond) of methanol and ethanol,and performed the NIR band assignments. The PCA method was employed to verify the results of the 2D analysis.This study will be helpful to the understanding of these reagents.展开更多
Dysregulation of neurotransmitter metabolism in the central nervous system contributes to mood disorders such as depression, anxiety, and post–traumatic stress disorder. Monoamines and amino acids are important types...Dysregulation of neurotransmitter metabolism in the central nervous system contributes to mood disorders such as depression, anxiety, and post–traumatic stress disorder. Monoamines and amino acids are important types of neurotransmitters. Our previous results have shown that disco-interacting protein 2 homolog A(Dip2a) knockout mice exhibit brain development disorders and abnormal amino acid metabolism in serum. This suggests that DIP2A is involved in the metabolism of amino acid–associated neurotransmitters. Therefore, we performed targeted neurotransmitter metabolomics analysis and found that Dip2a deficiency caused abnormal metabolism of tryptophan and thyroxine in the basolateral amygdala and medial prefrontal cortex. In addition, acute restraint stress induced a decrease in 5-hydroxytryptamine in the basolateral amygdala. Additionally, Dip2a was abundantly expressed in excitatory neurons of the basolateral amygdala, and deletion of Dip2a in these neurons resulted in hopelessness-like behavior in the tail suspension test. Altogether, these findings demonstrate that DIP2A in the basolateral amygdala may be involved in the regulation of stress susceptibility. This provides critical evidence implicating a role of DIP2A in affective disorders.展开更多
提出了模块2DPCA(two-d im ensional princ ipal component analysis)的人脸识别方法。模块2DPCA方法先对图像矩阵进行分块,将分块得到的子图像矩阵直接用于构造总体散布矩阵,然后利用总体散布矩阵的特征向量进行图像特征抽取。与基于...提出了模块2DPCA(two-d im ensional princ ipal component analysis)的人脸识别方法。模块2DPCA方法先对图像矩阵进行分块,将分块得到的子图像矩阵直接用于构造总体散布矩阵,然后利用总体散布矩阵的特征向量进行图像特征抽取。与基于图像向量的鉴别方法(比如PCA)相比,该方法在特征抽取之前不需要将子图像矩阵转化为图像向量,能快速地降低鉴别特征的维数,可以完全避免使用矩阵的奇异值分解,特征抽取方便;此外,模块2DPCA是2DPCA的推广。在ORL和NUST603人脸库上的试验结果表明,模块2DPCA方法在识别性能上优于PCA,比2DPCA更具有鲁棒性。展开更多
提出了一种基于共同向量结合2维主成分分析(2-dimen- sional principal component analysis,2DPCA)的人脸识别方法.共同向量由图像通过Gram-Schmidt正交变换而求得,具有该类图像共同不变的性质.原始图像与该类其同向量之间的差分向量通...提出了一种基于共同向量结合2维主成分分析(2-dimen- sional principal component analysis,2DPCA)的人脸识别方法.共同向量由图像通过Gram-Schmidt正交变换而求得,具有该类图像共同不变的性质.原始图像与该类其同向量之间的差分向量通过2DPCA处理,依据最小距离测试得到识别结果.实验在ORL和Yale人脸数据库进行测试,结果表明本文提出的方法有较好的识别性能.展开更多
提出一种改进的基于Gabor小波变换和二维主分量分析2DPCA(2-Dimensional Principal component analysis)的掌纹识别。2DPCA克服了传统Gabor小波变换后直接进行主分量分析PCA(Principal component analysis)遇到的维数灾难问题,并且将PCA...提出一种改进的基于Gabor小波变换和二维主分量分析2DPCA(2-Dimensional Principal component analysis)的掌纹识别。2DPCA克服了传统Gabor小波变换后直接进行主分量分析PCA(Principal component analysis)遇到的维数灾难问题,并且将PCA与Fisher线性判别FLD(Fisher Linear Discriminate)结合起来,利用了以前仅用于降维的PCA特征和FLD特征相融合进行掌纹识别。基于PolyU掌纹库的实验结果表明,该方法不仅有更高的识别率,而且维数更低。展开更多
最近,非局部滤波方法已成为滤波领域的研究热点.本文深入研究了基于预选择的非局部滤波方法,指出了已有方法在提取图像片特征方面存在的不足,利用二维主成分分析(Two-dimensional principal component analysis,2DPCA)提出了一种有效的...最近,非局部滤波方法已成为滤波领域的研究热点.本文深入研究了基于预选择的非局部滤波方法,指出了已有方法在提取图像片特征方面存在的不足,利用二维主成分分析(Two-dimensional principal component analysis,2DPCA)提出了一种有效的非局部滤波方法.该方法对基于预选择的非局部滤波方法的主要贡献有:1)用于提取图像片特征的面向图像片的2DPCA;2)基于相似距离直方图的相似集自动选取方法;3)相似距离权重参数局部自适应选取方法.实验结果表明,本文方法对弱梯度、人脸、纹理以及分段光滑图像均能取得较好的滤波效果.展开更多
针对航空图像中的水面尾迹,提出了一种基于方向极傅里叶频谱二维主成分分析(Two-dimensional principal component analysis,2DPCA)的尾迹自动检测算法.该方法根据子图像的纹理方向,对傅里叶频谱进行极坐标变换,使得到的方向极傅里叶频...针对航空图像中的水面尾迹,提出了一种基于方向极傅里叶频谱二维主成分分析(Two-dimensional principal component analysis,2DPCA)的尾迹自动检测算法.该方法根据子图像的纹理方向,对傅里叶频谱进行极坐标变换,使得到的方向极傅里叶频谱具有平移和旋转不变性.相对于文献中对极频谱的直接划分作为纹理特征,本文对它进行一次列二维主成分分析,一次行二维主成分分析和两次二维主成分分析,实验结果表明本文方法具有更高的分类识别率,其中两次二维主成分分析的分类识别率最高.对40幅图像的测试结果表明,本文的方法能够有效地自动检测航空图像中的水面尾迹纹理。展开更多
提出了一种对角离散余弦变换(Discrete Cosine Transform,DCT)和二维主元分析(Two-Dimensional Principal Component Analysis,2DPCA)相结合的人脸识别方法。该算法首先将人脸图像转换成对角图像,同时利用DCT压缩并重建人脸图像;然后通...提出了一种对角离散余弦变换(Discrete Cosine Transform,DCT)和二维主元分析(Two-Dimensional Principal Component Analysis,2DPCA)相结合的人脸识别方法。该算法首先将人脸图像转换成对角图像,同时利用DCT压缩并重建人脸图像;然后通过2DPCA进行特征提取得到人脸识别特征;最后运用最近邻分类器进行识别。基于ORL(Olivetti Research Laboratory)、受污损ORL及Yale人脸数据库的实验结果证明了该算法的有效性。展开更多
基金Climbing Peak Discipline Project of Shanghai Dianji University,China(No.15DFXK02)Hi-Tech Research and Development Programs of China(No.2007AA041600)
文摘Dimensionality reduction techniques play an important role in data mining. Kernel entropy component analysis( KECA) is a newly developed method for data transformation and dimensionality reduction. This paper conducted a comparative study of KECA with other five dimensionality reduction methods,principal component analysis( PCA),kernel PCA( KPCA),locally linear embedding( LLE),laplacian eigenmaps( LAE) and diffusion maps( DM). Three quality assessment criteria, local continuity meta-criterion( LCMC),trustworthiness and continuity measure(T&C),and mean relative rank error( MRRE) are applied as direct performance indexes to assess those dimensionality reduction methods. Moreover,the clustering accuracy is used as an indirect performance index to evaluate the quality of the representative data gotten by those methods. The comparisons are performed on six datasets and the results are analyzed by Friedman test with the corresponding post-hoc tests. The results indicate that KECA shows an excellent performance in both quality assessment criteria and clustering accuracy assessing.
文摘The accurate extraction and classification of leather defects is an important guarantee for the automation and quality evaluation of leather industry. Aiming at the problem of data classification of leather defects,a hierarchical classification for defects is proposed.Firstly,samples are collected according to the method of minimum rectangle,and defects are extracted by image processing method.According to the geometric features of representation, they are divided into dot,line and surface for rough classification. From analysing the data which extracting the defects of geometry,gray and texture,the dominating characteristics can be acquired. Each type of defect by choosing different and representative characteristics,reducing the dimension of the data,and through these characteristics of clustering to achieve convergence effectively,realize extracted accurately,and digitized the defect characteristics,eventually establish the database. The results showthat this method can achieve more than 90% accuracy and greatly improve the accuracy of classification.
基金supported by the Medical Scientific Research Foundation of Guangdong Province,China(B2009043)
文摘Liquid state methanol and ethanol under different temperatures have been investigated by FT-NIR(Fourier transform nearinfrared) spectroscopy,generalized two-dimensional(2D) correlation spectroscopy,and PCA(principal component analysis) . First,the FT-NIR spectra were measured over a temperature range of 30-64(or 30-71) °C,and then the 2D correlation spectra were computed.Combining near-infrared spectroscopy,generalized 2D correlation spectroscopy,and references,we analyzed the molecular structures(especially the hydrogen bond) of methanol and ethanol,and performed the NIR band assignments. The PCA method was employed to verify the results of the 2D analysis.This study will be helpful to the understanding of these reagents.
基金supported by the STI 2030—Major Projects 2021ZD0204000,No.2021ZD0204003 (to XZ)the National Natural Science Foundation of China,Nos.32170973 (to XZ),32071018 (to ZH)。
文摘Dysregulation of neurotransmitter metabolism in the central nervous system contributes to mood disorders such as depression, anxiety, and post–traumatic stress disorder. Monoamines and amino acids are important types of neurotransmitters. Our previous results have shown that disco-interacting protein 2 homolog A(Dip2a) knockout mice exhibit brain development disorders and abnormal amino acid metabolism in serum. This suggests that DIP2A is involved in the metabolism of amino acid–associated neurotransmitters. Therefore, we performed targeted neurotransmitter metabolomics analysis and found that Dip2a deficiency caused abnormal metabolism of tryptophan and thyroxine in the basolateral amygdala and medial prefrontal cortex. In addition, acute restraint stress induced a decrease in 5-hydroxytryptamine in the basolateral amygdala. Additionally, Dip2a was abundantly expressed in excitatory neurons of the basolateral amygdala, and deletion of Dip2a in these neurons resulted in hopelessness-like behavior in the tail suspension test. Altogether, these findings demonstrate that DIP2A in the basolateral amygdala may be involved in the regulation of stress susceptibility. This provides critical evidence implicating a role of DIP2A in affective disorders.
文摘提出了模块2DPCA(two-d im ensional princ ipal component analysis)的人脸识别方法。模块2DPCA方法先对图像矩阵进行分块,将分块得到的子图像矩阵直接用于构造总体散布矩阵,然后利用总体散布矩阵的特征向量进行图像特征抽取。与基于图像向量的鉴别方法(比如PCA)相比,该方法在特征抽取之前不需要将子图像矩阵转化为图像向量,能快速地降低鉴别特征的维数,可以完全避免使用矩阵的奇异值分解,特征抽取方便;此外,模块2DPCA是2DPCA的推广。在ORL和NUST603人脸库上的试验结果表明,模块2DPCA方法在识别性能上优于PCA,比2DPCA更具有鲁棒性。
文摘提出了一种基于共同向量结合2维主成分分析(2-dimen- sional principal component analysis,2DPCA)的人脸识别方法.共同向量由图像通过Gram-Schmidt正交变换而求得,具有该类图像共同不变的性质.原始图像与该类其同向量之间的差分向量通过2DPCA处理,依据最小距离测试得到识别结果.实验在ORL和Yale人脸数据库进行测试,结果表明本文提出的方法有较好的识别性能.
文摘提出一种改进的基于Gabor小波变换和二维主分量分析2DPCA(2-Dimensional Principal component analysis)的掌纹识别。2DPCA克服了传统Gabor小波变换后直接进行主分量分析PCA(Principal component analysis)遇到的维数灾难问题,并且将PCA与Fisher线性判别FLD(Fisher Linear Discriminate)结合起来,利用了以前仅用于降维的PCA特征和FLD特征相融合进行掌纹识别。基于PolyU掌纹库的实验结果表明,该方法不仅有更高的识别率,而且维数更低。
文摘最近,非局部滤波方法已成为滤波领域的研究热点.本文深入研究了基于预选择的非局部滤波方法,指出了已有方法在提取图像片特征方面存在的不足,利用二维主成分分析(Two-dimensional principal component analysis,2DPCA)提出了一种有效的非局部滤波方法.该方法对基于预选择的非局部滤波方法的主要贡献有:1)用于提取图像片特征的面向图像片的2DPCA;2)基于相似距离直方图的相似集自动选取方法;3)相似距离权重参数局部自适应选取方法.实验结果表明,本文方法对弱梯度、人脸、纹理以及分段光滑图像均能取得较好的滤波效果.
文摘针对航空图像中的水面尾迹,提出了一种基于方向极傅里叶频谱二维主成分分析(Two-dimensional principal component analysis,2DPCA)的尾迹自动检测算法.该方法根据子图像的纹理方向,对傅里叶频谱进行极坐标变换,使得到的方向极傅里叶频谱具有平移和旋转不变性.相对于文献中对极频谱的直接划分作为纹理特征,本文对它进行一次列二维主成分分析,一次行二维主成分分析和两次二维主成分分析,实验结果表明本文方法具有更高的分类识别率,其中两次二维主成分分析的分类识别率最高.对40幅图像的测试结果表明,本文的方法能够有效地自动检测航空图像中的水面尾迹纹理。
基金广东省自然科学基金(the Natural Science Foundation of Guangdong Province of China under Grant No.032356)北京大学视觉与听觉信息处理国家重点实验室开放课题基金项目(No.0505)
文摘提出了一种对角离散余弦变换(Discrete Cosine Transform,DCT)和二维主元分析(Two-Dimensional Principal Component Analysis,2DPCA)相结合的人脸识别方法。该算法首先将人脸图像转换成对角图像,同时利用DCT压缩并重建人脸图像;然后通过2DPCA进行特征提取得到人脸识别特征;最后运用最近邻分类器进行识别。基于ORL(Olivetti Research Laboratory)、受污损ORL及Yale人脸数据库的实验结果证明了该算法的有效性。