课程文献中心 更多>>

关键词： feature selection   generalized partial least squares regression   small samples   land cover   OBIA   PARTIAL LEAST-SQUARES   HYPERSPECTRAL DATA   ALGORITHMS  

摘要： Land cover information extraction through object-based image analysis (OBIA) has become an important trend in remote sensing, thanks to the increasing availability of high-resolution imagery. Segmented objects have a large number of features that cause high-dimension and low-sample size problems in the classification process. In this study, on the basis of a partial least squares generalized linear regression (PLSGLR), we propose a group corrected PLSGLR, known as G-PLSGLR, that aims to reduce the redundancy of object features for land cover identifications. Using Gaofen-2 images, the area of interest was segmented and sampled to generate small sample-size training datasets with 51 object features. The features selected by G-PLSGLR were compared against a guided regularized random forest (GRRF) in metrics of reduction rate, feature redundancy, and accuracy assessment of classification. Three indicators of overall accuracy (OA), user's accuracy (UA), and producer's accuracy (PA) were applied for accuracy assessment in this paper. The result shows that the G-PLSGLR achieved a reduction rate of 9.27 with a feature redundancy of 0.29, and a value of OA 90.63%. The GRRF achieved a reduction rate of 1.61 with a feature redundancy of 0.42, and a value of OA 85.56%. The PA of each land cover category was more than 95% using features selected by G-PLSGLR, while the PA ranged from 77 to 96% using features selected by GRRF. The UA of G-PLSGLR-selected features ranged from 70 to 80% except for grass land and bare land, which achieved 10% higher UA than GRRF-selected features. The G-PLSGLR method we proposed has the advantages of a large reduction rate, low feature redundancy, and high classification performance, which can be applied in OBIA-based land cover classification.

关键词： physiologically based pharmacokinetic modeling   drug interactions   Monte Carlo   in vitro-in vivo correlations (IVIVC)   nonlinear regression   biliary excretion   biliary recycling   hepatic metabolism   hepatic transport   TISSUE DISTRIBUTION   CYCLOSPORINE-A   HEPATIC-UPTAKE   GEMFIBROZIL   TRANSPORTER   DISPOSITION   PREDICTION   HUMANS   ENZYMES   ROSUVASTATIN  

摘要： Hypothetical substrates undergoing transporter-mediated hepatic uptake, metabolism, and enterohepatic circulation with different rate-determining processes with a combination of inhibition constants (K-i) for hepatic uptake, metabolism, and biliary excretion processes were generated with a constant K-i for uptake and incorporated into a physiologically based pharmacokinetic model. Analyses of the kinetic model suggested that the fraction of substrates excreted in the bile to the total elimination by the liver (f(bile)) can be estimated under certain conditions from kinetic analyses of their blood concentration-time profiles. Using the generated time profiles of substrates with and without coadministration of inhibitors, various pharmacokinetic parameters involving f(bile) and K-i for the hepatic uptake, metabolism, and biliary excretion of drugs were back-calculated by fitting. Comparing parameters obtained with the original parameter sets by fitting, the K-i were found to be well estimated under the following conditions: the initial estimates for inhibition constants were relatively good, which corresponds to the case for obtaining reliable in vitro inhibition constants. In conclusion, the integration of top-down analyses with bottom-up estimates (experimental determination) of inhibition constants can be used to estimate in vivo inhibition constants and f(bile) reliably. (C) 2017 American Pharmacists Association (R). Published by Elsevier Inc. All rights reserved.

关键词： image classification   confident unlabeled samples   sparse coding   semisupervised learning   multiclass linear classifier   DISCRIMINATIVE DICTIONARY   FACE RECOGNITION   K-SVD   REPRESENTATION  

摘要： Sparse coding has achieved very excellent performance in image classification tasks, especially when the supervision information is incorporated into the dictionary learning process. However, there is a large amount of unlabeled samples that are expensive and boring to annotate. We propose an image classification algorithm by semisupervised sparse coding with confident unlabeled samples. In order to make the learnt sparse coding more discriminative, we select and annotate some confident unlabeled samples. A minimization model is developed in which the reconstruction error of the labeled, the selected unlabeled and the remaining unlabeled data and the classification error are integrated, which enhances the discriminant property of the dictionary and sparse representations. The experimental results on image classification tasks demonstrate that our algorithm can significantly improve the image classification performance. (C) 2017 SPIE and IS&T

关键词： Problem posing   Problem solving   Interaction   Mathematics conceptual understanding   Prospective primary teachers   PROSPECTIVE ELEMENTARY   STUDENTS  

摘要： Existing studies have quantitatively evidenced the relatedness between problem posing and problem solving, as well as the magnitude of this relationship. However, the nature and features of this relationship need further qualitative exploration. This paper focuses on exploring the interactions, i.e., mutual effects and supports, between problem posing and problem solving. More specifically, this paper analyzes the forms of interactions that happened between these two activities, the ways that those interactions supported prospective primary teachers' conceptual understanding, and the difficulties that prospective teachers encountered while engaged in alternating problem-posing and problem-solving activities. The results indicate that problem posing contributes to problem-solving effectiveness while problem solving supports participants in posing more reasonable problems. Finally, multiple difficulties that demonstrate prospective primary teachers' misunderstanding with fractions and their operations provide insight for teacher educators to design problem-posing tasks involving fractions.

关键词： Spectroscopy   Fuel classification   Wavenumber selection   Diesel/biodiesel   INFRARED-SPECTROSCOPY   CLASSIFICATION   PLS   ADULTERATION   SPECTROMETRY   RECOGNITION   MEDICINES   VARIABLES   SPECTRA   MODELS  

摘要： In recent years, spectroscopy techniques such as Near infrared (NIR) and Fourier Transform Infrared (Frill) have been widely adopted as analytical tools in different fields and with several purposes. NIR and MR data are typically comprised of hundreds or even thousands of highly correlated wavenumbers, fact that can jeopardize the accuracy of several statistical techniques. In light of that, wavenumber selection emerges as an important step in prediction and classification tasks based on spectroscopy data. This paper proposes a novel framework for wavenumber selection aimed at classifying samples into proper categories, which is applied to two data sets from the petroleum sector. The method relies on two main stages: determination of intervals based on the distance between the average spectra of the classes and selection of the most suitable intervals through cross-validation. An improvement in the misclassification rate was achieved for a NIR spectra data set of diesel, decreasing that metric from 13.90% to 11.63% after the application of the proposed method while retaining 23.19% of the original wavenumbers. As for the biodiesel STIR data set, the method yielded a misclassification rate of 1.21% while retaining 4.95% of the original variables; misclassification rate was 4.71% when all wavenumbers were used. The proposed method also outperformed traditional approaches for wavenumber selection.

关键词： 煤质检验   选煤过程   指导作用  

摘要： 煤炭资源在能源利用和经济发展过程中的作用越来越重要,尤其是煤化工技术的发展,在很大程度上提高了煤炭资源的利用率。而在选煤过程中,按照一定的选择标准选择适合各种煤化工技术生产的煤炭资源十分重要,是保证实现煤炭资源利用率最大化的关键。选煤过程中参照的标准很多,其中对煤炭资源的质量进行检验对选煤工作具有一定的指导性。

关键词： 试验室样品   初级制备   分类管理   规范化管理  

摘要： 试验室样品的初级制备与分类管理对于相关工作而言,占据了极为重要的地位,是保证其余工作有序进行的重要前提。所以,文章中主要针对试验室的这两种工作,提出了自己的几点见解,希望能够为有关从业者提供参考。

关键词： Aluminum alloys   LIBS   Artificial neural networks   Shredding   SITE QUANTITATIVE-ANALYSIS   ELEMENTAL ANALYSIS   LIBS   IDENTIFICATION  

摘要： Every year throughout the world > 50 million vehicles reach the end of their life, producing millions of tons of automotive waste. The current strategies for the separation of the non-ferrous waste fraction, contain mainly aluminum, magnesium, zinc and copper alloys, involve high investment and operational costs, and pose environmental concerns. The European project SHREDDERSORT, in which our research group was actively involved, aimed to overcome this issue by developing a new dry sorting technology for the shredding of non-ferrous automotive wastes. This work represents one step of the complex SHREDDERSORT project, dedicated to the development of a strategy based on Laser Induced Breakdown Spectroscopy (LIBS) for the sorting of light alloys. LIBS was here applied in laboratory for the analysis of stationary aluminum shredder samples. To process the LIBS spectra a methodological approach based on artificial neural networks was used. Although separation could in principle be based on simple emission line ratios, the neural networks approach enables more reproducible results, which can accommodate the unavoidable signal variations due to the low intrinsic reproducibility of the LIBS systems. The neural network separated samples into different clusters and estimates their elemental concentrations. (C) 2017 Published by Elsevier B.V.

关键词： 债券   求偿途径   持有至到期投资   期中违约   账务处理  

摘要： 当前,债券违约频发,投资风险加大。结合案例分析,重新定义摊余成本的概念,并针对持有至到期投资期中违约的账务处理提出设想,避免账务处理出现大的偏差,保证会计信息的及时性和真实性。