不同产地黄柏的近红外指纹图谱鉴别分析

建立用近红外漫反射光谱鉴别不同产地黄柏药材的新方法.采集不同产地的黄柏药材及其伪品的近红外漫反射光谱,用模式识别方法进行聚类分析,建立判别模型并用三重交叉验证的方法对模型稳定性进行验证.黄柏样品与伪品能较好地区分开;建立模型后对已知训练集样本的分类精度高达100%,对未知样本的预测精度达到100%,该模型具有很好的预测性能,这说明了所建方法性能优良,能够适用于黄柏药材的不同种植产地分类鉴别.近红外光谱法简便、快速、不破坏样品,结合模式识别方法能够准确鉴别正品、伪品以及不同产地的黄柏药材.     

一种自适应的非参数判别分析方法

线性判别分析(LDA)是在包括人脸识别等多个应用领域被广泛采用的降维方法.但是,由于LDA是基于各类均服从高斯分布的假设,导致其类间散度矩阵的定义会产生相邻类别的重叠问题.因此,我们提出了一种自适应的非参数判别分析方法(ANDA),此方法通过增加位于类边界附近样本点在类间散度矩阵中的权重的方法来增大不同类的相邻样本点之间的距离.本文通过在FERET以及ORL人脸库上的实验把ANDA方法与传统的PCA+LDA,Orthogonal LDA(OLDA)和非参数判剐分析(NDA)进行了比较,实验结果表明本文提出的方法优于其他方法.     

FUDT在苹果近红外光谱分类中的应用

苹果的分类是苹果采收后商品化处理的重要环节。为了快速、无损和有效地实现苹果的分类,利用近红外光谱技术采集四种苹果的近红外反射光谱,用主成分分析对高维的近红外光谱进行降维处理,分别运行线性判别分析,二次判别分析,模糊非相关判别转换和Foley-Sammon判别分析提取鉴别信息,用k-近邻分类器进行分类。分类结果表明,模糊非相关判别转换能更好地提取苹果近红外光谱的品种鉴别信息,达到了最高的分类准确率。     

一种基于马氏距离的线性判别分析分类算法

对于一个特定的模式识别问题,表达和识别模式的特征具有不同的形式,它们在物理意义上是完全不同的,而且在数量级具有很大差别。该文提出了一种基于马氏距离的线性判别分析分类算法,选取判别函数为马氏距离,可以适用于具有不同类型特征值的分类问题。将该算法应用于UCI中Credit-A、Credit-G、Iris和Vehicle四个数据库的分类,并采用K次交叉验证方法进行实验。从实验结果中可知,与ENTROPY算法和C4．5（8）算法分类效果相比较,该文所提出的线性判别分析算法计算简单,识别率较高,是一种实际可行的分类算法。     

纳税人诚信的判别分析研究

纳税评估工作的核心是判别纳税人的诚信水平,为了弥补现有技术解决手段的缺乏,在建立科学的纳税评估指标体系基础上,应用多元统计判别分析方法,建立纳税人诚信判别函数,并收集实际数据作实证研究,对模型进行参数估计和预测,证实了该判别分析是识别纳税人诚信的有力工具。     

苹果近红外光谱的特征提取和分类研究

采用近红外光谱分析法对不同种类的苹果样品进行分类,提出一种基于非相关判别转换的苹果近红外光谱定性分析新方法。实验分别采用主成分分析、Fisher判别分析和非相关判别转换三种方法对苹果光谱数据进行特征提取,并使用K-近邻分类算法建立三种苹果分类识别模型,最后使用"留一"交叉验证法进行模型检验。结果表明,使用非相关判别转换方法建立的模型正确识别率优于使用主成分分析和Fisher判别分析建立的模型。     

一种新的基于DCT变换的线性判别分析

对于高维复杂模式识别问题,传统的线性判别分析通常首先采用PCA变换来降低模式的维数,然后再求取最优判别矢量集。然而PCA变换是以判别信息的损失为代价的,故无法保证所提取的特征是最优的。DCT变换具有"能量聚集特性"和变换的保距特性,文中正是基于此特性,提出一种新的基于DCT变换的线性判别分析方法,同时,也给出了一种在该模型下的最优判别矢量集的直接求解方法。实验表明,文中算法具有计算速度快、识别率高的优点。     

一种用于人脸识别的图优化线性判别分析算法

提出一个面向人脸识别的基于图优化的线性判别分析降维算法。该算法首先定义同类性的关联邻接矩阵和异类性的互斥邻接矩阵;然后以两个邻接矩阵作为作用因子分别建立两种不同样本之间的权值矩阵;最后通过这两个度量权值矩阵的相关投影完成数据的降维。在Yale、YaleB和UMIST人脸库的实验验证了该算法的有效性。     

一种新的聚类判别分析框架及其实证研究*

在分析经典聚类判别分析方法实质的基础上,提出了一种新的聚类判别分析框架,改进了一种基于样本指标值频度计算的两总体判别分析算法,提高了在对所有参与建立判别模型的样本进行判别时的计算速度;给出了建立在此改进判别分析算法基础上的一种动态聚类判别分析算法的设计,并实现了所有算法。进行相应的实证研究,结果表明以此聚类判别分析框架对给定样本集合进行分析,可以迅速得到多个合理的聚类结果以及对聚类结果的清晰解释,既可以对已有的聚类结果进行验证,又可以进行数据的探索性分析。     

基于流形距离的半监督判别分析

大量无类别标签的数据具有对分类有用的信息,有效地利用这些信息来提高分类精确度,是半监督分类研究的主要内容.提出了一种基于流形距离的半监督判别分析(semi-supervised discriminant analysis based on manifold distance,简称SSDA)算法,通过定义的流形距离,能够选择位于流形上的数据点的同类近邻点、异类近邻点以及全局近邻点,并依据流形距离定义数据点与其各近邻点之间的相似度,利用这种相似度度量构造算法的目标函数.通过在ORL,YALE人脸数据库上的实验表明,与现有算法相比,数据集通过该算法降维后,能够使基于距离的识别算法具有更高的分类精确度.同时,为了解决非线性降维问题,提出了Kernel SSDA,同样通过实验验证了算法的有效性.     

基于规范化KDDA的人脸识别

传统的PCA和LDA算法受限于“小样本问题”,且对象素的高阶相关性不敏感。本文将核函数方法与规范化LDA相结合,将原图像空间通过非线性映射变换到高维特征空间,并借助于“核技巧”在新的空间中应用鉴别分析方法。通过对ORL人脸库的大量实验研究表明,本文方法在特征提取方面明显优于PCA,KPCA,LDA等其他传统的人脸识别方法,在简化分类器的同时,也可以获得高识别率。     

Discriminant analysis and similarity measure

The cosine similarity measure is often applied after discriminant analysis in pattern recognition. This paper first analyzes why the cosine similarity is preferred by establishing the connection between the cosine similarity based decision rule in the discriminant analysis framework and the Bayes decision rule for minimum error. The paper then investigates the challenges inherent of the cosine similarity and presents a new similarity that overcomes these challenges. The contributions of the paper are thus three-fold. First, the application of the cosine similarity after discriminant analysis is discovered to have its theoretical roots in the Bayes decision rule. Second, some inherent problems of the cosine similarity such as its inadequacy in addressing distance and angular measures are discussed. Finally, a new similarity measure, which overcomes the problems by integrating the absolute value of the angular measure and the l_p norm (the distance measure), is presented to enhance pattern recognition performance. The effectiveness of the proposed new similarity measure in the discriminant analysis framework is evaluated using a large scale, grand challenge problem, namely, the Face Recognition Grand Challenge (FRGC) problem. Experimental results using 36,818 FRGC images on the most challenging FRGC experiment, the FRGC Experiment 4, show that the new similarity measure improves face recognition performance upon other popular similarity measures, such as the cosine similarity measure, the normalized correlation, and the Euclidean distance measure.     

Discriminant pattern recognition using transformation-invariant neurons

To overcome the problem of invariant pattern recognition, Simard, LeCun, and Denker (1993) proposed a successful nearest-neighbor approach based on tangent distance, attaining state-of-the-art accuracy. Since this approach needs great computational and memory effort, Hastie, Simard, and S?ckinger (1995) proposed an algorithm (HSS) based on singular value decomposition (SVD), for the generation of nondiscriminant tangent models. In this article we propose a different approach, based on a gradient-descent constructive algorithm, called TD-Neuron, that develops discriminant models. We present as well comparative results of our constructive algorithm versus HSS and learning vector quantization (LVQ) algorithms. Specifically, we tested the HSS algorithm using both the original version based on the two-sided tangent distance and a new version based on the one-sided tangent distance. Empirical results over the NIST-3 database show that the TD-Neuron is superior to both SVD- and LVQ-based algorithms, since it reaches a better trade-off between error and rejection.     

Discriminant analysis using certain normed exponential densities with emphasis on remote sensing application

The Bayes discriminant analysis based upon the normality assumption for population models does not lead to an exact evaluation of probabilities of correct classification and of misclassification unless it is restricted to a simplest possible situation. In order to overcome this and other computational difficulties that one faces in a complex situation such as the remote sensing, certain alternative densities are posed as models for the observations. It is shown that for a Bayes discriminant analysis these densities lead to piecewise linear discriminant functions even when the covariance matrices are unequal (a property not enjoyed in the normal case) and provide a theoretical solution for evaluating probabilities of correct classification and of misclassification. Also, some computational advantages are achieved.     

Face recognition using Gabor-based complete Kernel Fisher Discriminant analysis with fractional power polynomial models

The selection of kernel function and its parameter influences the performance of kernel learning machine. The difference geometry structure of the empirical feature space is achieved under the different kernel and its parameters. The traditional changing only the kernel parameters method will not change the data distribution in the empirical feature space, which is not feasible to improve the performance of kernel learning. This paper applies kernel optimization to enhance the performance of kernel discriminant analysis and proposes a so-called Kernel Optimization-based Discriminant Analysis (KODA) for face recognition. The procedure of KODA consisted of two steps: optimizing kernel and projecting. KODA automatically adjusts the parameters of kernel according to the input samples and performance on feature extraction is improved for face recognition. Simulations on Yale and ORL face databases are demonstrated the feasibility of enhancing KDA with kernel optimization.     

Discriminant subspace analysis: a Fukunaga-Koontz approach

The Fisher Linear Discriminant (FLD) is commonly used in pattern recognition. It finds a linear subspace that maximally separates class patterns according to the Fisher Criterion. Several methods of computing the FLD have been proposed in the literature, most of which require the calculation of the so-called scatter matrices. In this paper, we bring a fresh perspective to FLD via the Fukunaga-Koontz Transform (FKT). We do this by decomposing the whole data space into four subspaces with different discriminability, as measured by eigenvalue ratios. By connecting the eigenvalue ratio with the generalized eigenvalue, we show where the Fisher Criterion is maximally satisfied. We prove the relationship between FLD and FKT analytically, and propose a unified framework to understanding some existing work. Furthermore, we extend our our theory to Multiple Discriminant Analysis (MDA). This is done by transforming the data into intra- and extra-class spaces, followed by maximizing the Bhattacharyya distance. Based on our FKT analysis, we identify the discriminant subspaces of MDA/FKT, and propose an efficient algorithm, which works even when the scatter matrices are singular, or too large to be formed. Our method is general and may be applied to different pattern recognition problems. We validate our method by experimenting on synthetic and real data.     

Discriminant analysis of nitrogen treatments in switchgrass and high biomass sorghum using leaf and canopy-scale reflectance spectroscopy

Recent advances in imaging, laboratory, and field spectroscopy (sometimes referred to as hyperspectral remote sensing) provide a unique opportunity to obtain critical information needed for understanding nitrogen (N) management in crop production systems. Therefore, the objective of this study was to identify wavelength regions and phenological timing useful for the prediction of N status from canopy and leaf spectra. Leaf and canopy spectral data were collected using an ASD FieldSpec FR spectroradiometer (350–2500 nm) at monthly intervals during 2011 and 2012. The crops evaluated in the study were switchgrass ‘Alamo’ (Panicum virgatum L.) and high biomass sorghum ‘Blade 5200’ (Sorghum bicolor) grown to evaluate N applications rates on biomass yield and quality. The optimal wavelengths were determined based on principal component analysis (PCA) and the separation of the N treatments using stepwise discriminant analysis (SDA). The results showed similar canopy and leaf-scale reflectance for high biomass sorghum but not for switchgrass. The wavelengths found to be most important for separating the N treatments were 520–560, 650–690 nm (visible region), and 710–730 nm (red-edge region). Triangular greenness index (TGI) was the most useful index for discriminating the N application rates. The best time for differentiating the different N treatments was 4–6 weeks after planting or 2–4 weeks after N fertilization in high biomass sorghum and within 4 weeks after green-up in switchgrass. In general, the results indicate that spectroscopy is a viable tool that could be used to estimate the biochemical and biophysical characteristics in bioenergy crop production systems.     

闭环回路气提法的烟叶香气成分特征判别研究

为了比较不同产地不同香型烟叶风格特征的差异,应用闭环回路气提法(Closed-Loop Stripping Analysis,CLSA)对我国5大烟叶产区(黄淮、东南、西南、长江中上游、北方)3种不同香型122个C3F等级烟叶进行挥发、半挥发成分指纹图谱研究;结合组分对香型的贡献性、烟叶中的含量及试验结果的重复性,选取20种挥发、半挥发性成分作为检测对象,采用判别分析方法(Discriminant Analysis,DA)对其含量差异进行了比较分析。结果表明:挥发、半挥发成分与香型及产地关系明显,同香型不同产地差异很大,①浓香型烟叶整体挥发、半挥发成分含量较高,香味物质含量较突出,但是新植二烯含量在3种香型中最低,东南、黄淮两大产区差异较大。②中间香型挥发、半挥发成分没有较为突出的个性特征,整体上,北方产区与其他产区差异明显。③清香型烟叶中的新植二烯含量为3种香型中最高,是清香特色的主要因素之一,福建地区与云南、四川等地差异较大:     

Discriminant analysis of promoter regions in Escherichia coli sequences

We have previously developed a general method based on the statistical technique of discriminant analysis to predict splice junctions in eukaryotic mRNA sequences [Nakata, K., Kanehisa, M. and DeLisi, C. (1985) Nucleic Acids Res., 13, 5327-5340]. In order to evaluate further applicability of this method, we now analyze the promoter region of Escherichia coli sequences. The attributes used for discrimination include the accuracy of consensus sequence patterns measured by the perceptron algorithm, the thermal stability map, the base composition and the Calladine-Dickerson rules for helical twist angle, roll angle, torsion angle and propeller twist angle. When applied to selected E. coli sequences in the GenBank database, the method correctly identifies 75% of the true promoter regions.