DMMP红外光谱的自动识别

介绍了模式识别技术在化学毒剂红外遥感监测领域应用的概况，探讨了线性分类器、分段线性分类器、反向传播人工神经网络(BP-ANN)分类器应用于红外光谱鉴别的可能性．用一个DMMP(甲基膦酸二甲酯)红外光谱数据样本集对上述三种分类器进行了实际的训练和鉴别性能预测，结果发现，分段线性分类器的性能优于另外两种分类器，鉴别率达到了80％以上．     

神经网络在DMMP红外光谱判别中的应用

介绍了神经网络在化学毒剂红外遥感监测领域应用的概况,探讨了反向传播人工神经网络分类器应用于红外光谱鉴别的可能性。用一个甲基膦酸二甲酯红外光谱数据样本集进行了实际的训练和鉴别性能预测。训练结果表明,这种分类器在一定条件下可以将959／5以上的样本正确分离;预测结果表明,经过适当训练的神经网络分类器可以获得70％以上的鉴别率,具备了一定的识别能力。     

红外化学遥感数字信号处理算法的研究进展

介绍了几种为远距离红外蒸汽信号监测开发的分类器设计，频域数字滤波，时域数字滤波等数字信号处理技术。对线性分类器，分段线性分类器和神经网络分类器等在红外化学遥感系统中的应用做了初步的探讨。对背景扣除技术，频域数字滤波技术，数字滤波的切趾方法等做了简要的描述。阐述了时域滤波技术的基本原理及实际应用。展望了红外化学遥感数字信号处理算法的研究前景。     

树状分类器法用于气体红外光谱数据的识别分类

介绍了一种新的分类方法一树状分类器法，它抛弃了传统的线性搜索，用一个超平面进行分类的局限，引入了多个超平面进行分类，从而对在特征空间分布复杂交错的、非线性可分的样本有着较好的分类效果。文中详细地介绍了其原理，并利用树状分类器进行算法训练和鉴别分类。通过实例比较说明，此方法应用于大气遥感红外光谱数据的复杂样本进行分类和识别时，相比于一个超平面是更行之有效的。     

硫酸软骨素掺假鉴定的太赫兹和红外光谱对比

研究太赫兹时域光谱(Terahertz Time-domain Spectroscopy,THz-TDS)技术和红外光谱技术用于硫酸软骨素掺假鉴定的可行性.将六偏磷酸钠混入鲨鱼硫酸软骨素中的样品作为掺假研究对象,利用上述两种技术对样品进行对比研究.研究发现,THz光谱和红外光谱谱图中六偏磷酸钠标样、鲨鱼硫酸软骨素标样与掺假(混合)样品谱线均表现出较明显的差异,可用于鉴别鲨鱼硫酸软骨素的六偏磷酸钠掺假.实验结果表明,此两种技术能够鉴别的六偏磷酸钠:鲨鱼硫酸软骨素最低质量比分别为1:15和1:1,THz-TDS表现出较为灵敏的检测性能;综合考虑,THz-TDS技术可以比较好的用于鲨鱼硫酸软骨素的六偏磷酸钠掺假检测.本工作为发展一种基于THz-TDS技术的准确、快速和无损鉴别鲨鱼硫酸软骨素掺假的新型光谱技术奠定了前期实验基础.     

基于高温黑体的傅里叶光谱测量系统响应度分段线性标定

傅里叶红外光谱仪（FTIR）光谱响应度的标定工作是FTIR红外光谱精准测量的基础。基于中国计量科学研究院（NIM）的ThermoGage HT9500型高温基准黑体辐射源,对NIM搭建的FTIR高温黑体红外辐射特性测量系统的光谱响应度,通过分段线性标定法进行了标定实验。建立并描述了FTIR测量高温黑体红外辐射特性系统响应度函数标定模型,并通过测量的黑体辐射源在1 273~1 973 K温区、1~14 m宽频谱内的红外光谱,对FTIR测量系统的光谱响应度进行了标定实验研究。结果表明:分段线性标定FTIR红外光谱测量系统方法具有良好可靠性。1 373~1 873 K温区的测量光谱与基于黑体标定的计算光谱在1~14 m频谱内平均偏差优于1%,黑体光谱辐射亮度峰值波长上反演得到的黑体计算温度与实际温度偏差优于0.45%。     

高光谱红外探测器性能研究

介绍了高光谱用红外探测器的性能及使用情况,并将其与国外同类型高光谱红外探测器的关键指标(如信噪比、暗电流、读出噪声等)进行了对比测试分析。经过衬底去除工艺,短波探测器的光谱响应达到0.4~2.6 μm,平均量子效率超过75%,动态范围内响应线性度拟合曲线的R²值都大于 0.99,半阱信噪比可达到1600。该探测器的性能超过了国外报道的同类器件,满足我国高光谱应用需求。     

一种多光谱红外舰船目标融合检测方法

针对复杂岸岛背景下的红外舰船目标检测问题,提出了一种多光谱融合红外舰船目标检测方法。首先根据不同谱段信息相互间的关系进行基于非下采样轮廓波变换(Nonsubsampled Contourlet Transform, NSCT)域的多级多光谱图像融合,然后利用LSD线段检测和聚类对融合后的图像进行岸岛线检测。采用选择性搜索算法生成初始目标候选区域,然后结合岸岛线空间位置以及舰船目标的几何特征和灰度特征约束剔除部分虚假目标区域,最后提取候选区域的方向梯度直方图(Histogram of Oriented Gradient, HOG)特征算子。利用线性支持向量机(Support Vector Machine, SVM)分类器进行分类识别,以检测出真实舰船目标。实验结果表明,与单谱段红外舰船目标检测方法相比,本文方法在检测精度上有较大提升。     

高光谱红外探测器性能研究

介绍了高光谱用红外探测器的性能及使用情况,并将其与国外同类型高光谱红外探测器的关键指标(如信噪比、暗电流、读出噪声等)进行了对比测试分析。经过衬底去除工艺,短波探测器的光谱响应达到0.4~2.6 μm,平均量子效率超过75%,动态范围内响应线性度拟合曲线的R²值都大于 0.99,半阱信噪比可达到1600。该探测器的性能超过了国外报道的同类器件,满足我国高光谱应用需求。     

太周探测：从60年代四大天文发现说起(上)

介绍了高光谱用红外探测器的性能及使用情况,并将其与国外同类型高光谱红外探测器的关键指标(如信噪比、暗电流、读出噪声等)进行了对比测试分析。经过衬底去除工艺,短波探测器的光谱响应达到0.4~2.6 μm,平均量子效率超过75%,动态范围内响应线性度拟合曲线的R²值都大于 0.99,半阱信噪比可达到1600。该探测器的性能超过了国外报道的同类器件,满足我国高光谱应用需求。     

辐射源识别系统中分类器设计及其应用

针对辐射源识别系统中分类器设计分析的不足,本文从分类器的两大基本任务拒识和鉴别出发,研究辐射源识别系统中的分类器设计。首先详细分析了拒识和鉴别先后执行顺序对系统性能的影响;然后阐述了拒识分类器和鉴别分类器设计所需要考虑的要点;最后根据当前分类器和工程应用的状况,分析适合于辐射源识别系统的分类器。     

Comparison of three rough surface classifiers

Texture analysis techniques are used to segment rough surfaces into regions of homogeneous texture. The performance of three rough surface classifiers was assessed and compared. The classifiers differ in their discrimination as well as in their input and computational requirements. Simulation and experiment were used to identify the limitations of the classifiers and to identify which classifier is best suited to a particular task. A series of guidelines for the choice of classifier is presented and justified.     

Motor Imagery EEG Fuzzy Fusion of Multiple Classification

Due to the volume conduction, electroencephalogram (EEG) gives a rather blurred image of brain activities. It is a challenge for generating satisfactory performance with EEG. This paper studies the multiple areas fusion of EEG classifiers to improve the motor imagery EEG classification performance. Two feature extraction methods are employed to extract the feature from three different areas of EEG. One is power spectral density (PSD), and the other is common spatial patterns (CSP). Classifiers are designed based on the well-known linear discrimination analysis (LDA). The fusion of the individual classifiers is realized by means of the Choquet fuzzy integral. It is demonstrated that the proposed method comes with better performance compared with the individual classifier.     

Study of on-line adaptive discriminant analysis for EEG-based brain computer interfaces

A study of different on-line adaptive classifiers, using various feature types is presented. Motor imagery brain computer interface (BCI) experiments were carried out with 18 naive able-bodied subjects. Experiments were done with three two-class, cue-based, electroencephalogram (EEG)-based systems. Two continuously adaptive classifiers were tested: adaptive quadratic and linear discriminant analysis. Three feature types were analyzed, adaptive autoregressive parameters, logarithmic band power estimates and the concatenation of both. Results show that all systems are stable and that the concatenation of features with continuously adaptive linear discriminant analysis classifier is the best choice of all. Also, a comparison of the latter with a discontinuously updated linear discriminant analysis, carried out in on-line experiments with six subjects, showed that on-line adaptation performed significantly better than a discontinuous update. Finally a static subject-specific baseline was also provided and used to compare performance measurements of both types of adaptation.     

A composite classifier system design: Concepts and methodology

This study explores the scope for achieving enhanced recognition system performance through deployment of a composite classifier system consisting of two or more component classifiers which belong to different categories. The domains of deployment of these individual components (classifiers) are determined by optimal partitioning of the problem space. The criterion for such optimal partitioning is determined in each case by the characteristics of the classifier components. An example, in terms of partitioning the feature space for optimal deployment of a composite system consisting of the linear and nearest neighbor (NN) classifiers as its components, is presented to illustrate the concepts, the associated methodology, and the possible benefits one could expect through such composite classifier system design. Here, the optimality of the partitioning is dictated by the linear class separability limitation of the linear classifier and the computational demand characteristics of the NN classifier. Accordingly, the criterion for the optimal feature space partitioning is set to be the minimization of the domain of application of the NN classifier, subject to the constraint that the linear classifier is to be deployed only in regions satisfying the underlying assumption of linear separability of classes. While many alternatives are available for the solution of the resulting constrained optimization problem, a specific technique-Sequential Weight Increasing Factor Technique (SWIFT)- was employed here for convenience in view of previous successful experience with this technique in other application areas. Numerical results derived using the well-known IRIS data set are furnished to demonstrate the effectiveness of the new concepts and methodology.     

A dynamic classifier selection and combination approach to image region labelling

In this paper we propose a ‘bank of classifiers’ approach to image region labelling and evaluate dynamic classifier selection and classifier combination approaches against a baseline approach that works with a single best classifier chosen using a validation set. In this analysis, image segmentation, feature extraction, and classification are treated as three separate steps of analysis. The classifiers used are each trained with a different texture feature representation of training images. The paper proposes a new knowledge-based predictive approach based on estimating the Mahalanobis distance between test sample feature values and the corresponding probability distribution function from training data that selectively triggers classifiers. This approach is shown to perform better than probability-based classifier combination (all classifiers are triggered but their decisions are fused with combination rules), and single classifier, respectively, based on classification rates and confusion matrices. The experiments are performed on the natural scene analysis application.     

Oblique projection realization of a Kernel-based Nonlinear Discriminator

Previously, a novel classifier called Kernel-based Nonlinear Discriminator （KND） was proposed to discriminate a pattern class from other classes by minimizing mean effect of the latter. To consider the effect of the target class, this paper introduces an oblique projection algorithm to determine the coefficients of a KND so that it is extended to a new version called extended KND （eKND）. In eKND construction, the desired output vector of the target class is obliquely projected onto the relevant subspace along the subspace related to other classes. In addition, a simple technique is proposed to calculate the associated oblique projection operator. Experimental results on handwritten digit recognition show that the algorithm performes better than a KND classifier and some other commonly used classifiers.     

基于可见/近红外反射光谱的稻米品种与真伪鉴别

利用可见/近红外光谱技术对市场上5种稻米进行了鉴别.以ASD FieldSpec3地物光谱仪采集了5种稻米的光谱数据,各获取35个样本,随机分成训练集(150份)和检验集(25份),并分别采取全波段与特征波段(400~500nm、910~1400nm与1940~2300nm)两种方法建立模型进行分析.光谱经S.Golay平滑和标准归一化(SNV)处理后,以主成分分析法(PCA)降维.将降维所得的前9个主成分数据作为BP人工神经网络(BP-ANN)的输入变量,稻米品种作为输出变量,建立3层BP-ANN鉴别模型.利用25个未知样对模型进行检验,结果表明两类模型预测准确率均高达100%,其中特征波段模型比全波段模型具有更高的预测精度,说明利用可见/近红外技术结合PCA-BP神经网络分析法进行稻米品种与真伪的快速、无损鉴别是可行的,且提取特征波段是优化模型的有效方法之一.     

Design of minimum-error optimal classifiers for patterns from distributions with Gaussian tails

Adaptive algorithms for designing two-category linear pattern classifiers have been developed and studied in recent years. When the pattern sets are nonseparable, the adaptive algorithms do not directly minimize the number of classification errors, which is the usual goal in pattern classifier design: furthermore, they also are not minimum-error optimal, i.e., they do not generally minimize the probability of error for the classifier. However, the least-mean-square (LMS) adaptive algorithm has been shown to yield classifiers that are asymptotically minimum-error optimal for patterns from Gaussian equal-covariance distributions. A technique is also known for designing asymptotically minimum-error optimal linear classifiers for patterns from Gaussian distributions with unequal covariance matrices. This paper shows that classifiers designed with the "error-correction" algorithms have these same asymptotic properties: the error-correction algorithms are asymptotically minimum-error optimal for patterns drawn from Gaussian equal-covariance distributions and they can be used to design asymptotically minimum-error optimal linear classifiers for patterns from Gaussian distributions with unequal covariance matrices. In addition, because the error-correction algorithms use only part of the patterns in determining the classifier weights, they are asymptotically minimum-error optimal for patterns from distributions that have only Gaussian tails in the regions where their patterns are misclassified or close to misclassified, and that are almost arbitrary elsewhere.