Correlation‐assisted nearest shrunken centroid classifier with applications for high dimensional spectral data

High throughput data are frequently observed in contemporary chemical studies. Classification through spectral information is an important issue in chemometrics. Linear discriminant analysis (LDA) fails in the large‐p‐small‐n situation for two main reasons: (1) the sample covariance matrix is singular when p > n and (2) there is an accumulation of noise in the estimation of the class centroid in high dimensional feature space. The Independence Rule is a class of methods used to overcome these drawbacks by ignoring the correlation information between spectral variables. However, a strong correlation is an essential characteristic of spectral data. We proposed a new correlation‐assisted nearest shrunken centroid classifier (CA‐NSC) to incorporate correlation information into the classification. CA‐NSC combines two sources of information [class centroid (mean) and correlation structure (variance)] to generate the classification. We used two real data analyses and a simulation study to verify our CA‐NSC method. In addition to NSC, we also performed a comparison with the soft independent modeling of class analogy (SIMCA) approach, which uses only correlation structure information for classification. The results show that CA‐NSC consistently improves on NSC and SIMCA. The misclassification rate of CA‐NSC is reduced by almost half compared with NSC in one of the real data analyses. Generally, correlation among variables will worsen the performance of NSC, even though the discriminatory information contained in the class centroid remains unchanged. If only correlation structure information is used (as in the case of SIMCA), the result will be satisfactory only when the correlation structure alone can provide sufficient information for classification. Copyright © 2015 John Wiley & Sons, Ltd.     

Random forests for functional covariates

We propose a form of random forests that is especially suited for functional covariates. The method is based on partitioning the functions' domain in intervals and using the functions' mean values across those intervals as predictors in regression or classification trees. This approach appears to be more intuitive to applied researchers than usual methods for functional data, while also performing very well in terms of prediction accuracy. The intervals are obtained from randomly drawn, exponentially distributed waiting times. We apply our method to data from Raman spectra on boar meat as well as near‐infrared absorption spectra. The predictive performance of the proposed functional random forests is compared with commonly used parametric and nonparametric functional methods and with a nonfunctional random forest using the single measurements of the curve as covariates. Further, we present a functional variable importance measure, yielding information about the relevance of the different parts of the predictor curves. Our variable importance curve is much smoother and hence easier to interpret than the one obtained from nonfunctional random forests.     

基于质子转移反应-飞行时间质谱快速鉴别不同产地闽北水仙茶

采用质子转移反应-飞行时间质谱仪(PTR-TOF-MS), 构建了3个产地(武夷山、建阳、建瓯)113个闽北水仙茶样品香气的化学指纹图谱, 对所得的闽北水仙茶香气指纹图谱进行主成分分析(PCA), 获得了不同产地闽北水仙茶样品的质谱信息特征, 然后采用软独立建模分类法(SIMCA)、K最邻近结点算法(KNN)、偏最小二乘判别分析法(PLS-DA)对闽北水仙茶的质谱信息进行了模式识别.结果表明, PTR-TOF-MS结合分类识别模式能有效区分不同产地的闽北水仙茶.PCA 提取了3个主成分, 累计贡献率为84.66%;3个识别模型的校正集判别正确率分别为89.38%、100.00%和100.00%, 预测集的判别正确率分别为83.18%、 96.46%和95.57%.基于此成功建立了不同产地的闽北水仙茶识别模型.本方法无需样品预处理、分析速度快、灵敏度高、对茶叶无损伤, 为茶叶产地溯源提供了新方法.     

支持向量机结台主成分分析辅助激光诱导击穿光谱技术识别鲜肉品种

为提高激光诱导击穿光谱技术(Laser-induced breakdown spectroscopy,LIBS)对鲜肉品种的识别率,采用支持向量机结合主成分分析算法辅助LIBS技术对鲜肉品种进行识别.对鲜肉切片用载玻片压平,采用LIBS技术对鲜肉组织(猪肉、牛肉和鸡肉)表面进行光谱数据的采集,每种鲜肉采集150幅光谱并进行随机排列,取前75幅光谱作为训练集建立模型,后75幅作为测试集测试建模结果.研究选取K、Ca、Na、Mg、Al、H、O等元素的49条归一化谱线数据进行主成分分析,并用所得数据建立支持向量机分类模型.结果表明,通过主成分分析降维,输入变量从49个优化减少到18个,模型建模速度从88.91 s降至55.52 s,提高了支持向量机的建模效率;并使预测集的平均识别率提高到89.11%.本研究为激光诱导击穿光谱技术在鲜肉品种快速分类领域提供了方法和数据参考.     

The behaviour of macromolecules in the flow through a sudden planar contraction

Analytic steady-state results for FENE-P model macromolecules, in the nearly coiled-up and nearly stretched state respectively, in general two-dimensional flow fields are derived. These results are utilized in the flow through a sudden planar contraction. Special emphasis is devoted to the structure tensor R R, which furnishes, among other things, the mean square extension and the average orientation of the macromolecules.     

Novel flame retardants containing cyclodextrin nanosponges and phosphorus compounds to enhance EVA combustion properties

A novel flame retardant intumescent system, aimed to improve the fire stability of ethylene vinyl acetate copolymer (EVA), has been prepared by melt blending of the copolymer and a complex of cyclodextrin nanosponge-phosphorus compounds. As compared to traditional systems, this complex, stable in processing conditions, has the advantage that nanosponges act as both carbon sources and foam forming agents while the phosphorus compounds are able to directly generate phosphoric acid in situ. In this context, cyclodextrin nanosponges undergo dehydration in presence of the acid source, generating water vapour and char, and thus protecting the copolymer against combustion. Different acid sources have been investigated in order to reach the optimum interaction with the nanosponges. Raman measurements and thermogravimetric analyses have shown that the cavities of nanosponges entrapped the phosphorus derivatives forming stable complexes at the temperature of EVA processing. Different amounts of these complexes (5, 10 and 15 wt.%) have been added to EVA via melt blending and their flame retardancy properties measured by UL94 test and cone calorimetry. Strongly modified burning kinetics, as compared to the behaviour of the neat copolymer, have been found by UL94 test: V2 classification has been achieved for every formulation regardless of the type and the amount of complex used. EVA combustion behaviour by cone calorimetry has also been significantly affected: the heat release rate decreased dramatically down to ca. 20% in the presence of these new additives.     

Classification with Gaussians and convex loss Ⅱ:improving error bounds by noise conditions

We continue our study on classification learning algorithms generated by Tikhonov regularization schemes associated with Gaussian kernels and general convex loss functions. Our main purpose of this paper is to improve error bounds by presenting a new comparison theorem associated with general convex loss functions and Tsybakov noise conditions. Some concrete examples are provided to illustrate the improved learning rates which demonstrate the effect of various loss functions for learning algorithms. In our ...     

Quantitative combination of volumetric MR imaging and MR spectroscopy data for the discrimination of meningiomas from metastatic brain tumors by means of pattern recognition

The analysis of information derived from magnetic resonance imaging (MRI) and spectroscopy (MRS) has been identified as an important indicator for discriminating among different brain pathologies. The purpose of this study was to investigate the efficiency of the combination of textural MRI features and MRS metabolite ratios by means of a pattern recognition system in the task of discriminating between meningiomas and metastatic brain tumors. The data set consisted of 40 brain MR image series and their corresponding spectral data obtained from patients with verified tumors. The pattern recognition system was designed employing the support vector machines classifier with radial basis function kernel; the system was evaluated using an external cross validation process to render results indicative of the generalization performance to “unknown” cases. The combination of MR textural and spectroscopic features resulted in 92.15% overall accuracy in discriminating meningiomas from metastatic brain tumors. The fusion of the information derived from MRI and MRS data might be helpful in providing clinicians a useful second opinion tool for accurate characterization of brain tumors.