PCA在语音检测中的应用研究

提出主元分析PCA(Principal Component Analysis)用于语音检测的方法研究．用主元分析法在多维空间中建立坐标轴，将待处理信号投影到该坐标轴中，通过分析投影结果判断是否为语音信号．通过将语音和非语音分别建立子空间，来区分语音和非语音信号．该方法不同于常规的语音时域、频域处理方法，而是在多维空间中对信号进行分析·实验结果表明，该方法准确率高、简单、容易实现，而且能区分多种非语音信号．

岷江干旱河谷典型阳坡土壤质量动态与评估

横断山区干旱河谷地区的土壤是制约植被恢复的一个关键要素，但干旱条件下土壤质量与动态演变状况并不清楚，本研究以岷江干旱河谷核心地段的土壤为对象，研究了阳坡褐土土壤的物理、化学以及生物学特征在海拔梯度（1800m、2000m、2200m）格局及其时间动态（2005-2007）变化，应用主成分分析综合评价了土壤质量及其时空差异性，明确了土壤质量的变化趋势。主要研究结论如下： 1) 海拔梯度上土壤物理性状的变化，2005 年和2007 年土壤物理性状综合质量随着海拔的升高均得到了优化，即海拔2200 m＞海拔2000 m＞海拔1800 m。 2) 海拔梯度上土壤化学性质的变化，土壤化学综合性质2005 年随海拔升高而趋于变得更优，而2007 年海拔2000 m 最优，海拔1800 m 则最差。 3) 海拔梯度上土壤生物学性质的变化，2005 年土壤生物学性质随海拔升高表现出趋于更好，2007 年海拔2000 m 最优而海拔1800 m 地段最差。 4) 从土壤物理、化学、生物学三方面出发，应用主成分分析，分别分析得出2005 年和2007 年不同海拔高度的土壤质量综合得分。根据综合得分得出土壤质量综合评价的排列顺序为：2005 海拔2200 m＞2007 年海拔2000 m＞2005 年海拔2000 m＞2007 年海拔1800 m＞2007 海拔2200 m＞2005 年海拔1800 m。2005年土壤综合质量随海拔升高而趋好，2007 年则以海拔2000 m 最优，海拔1800 m和2200 m 差异不大。 5）排除人为干扰后，干旱河谷土壤物理性状在海拔1800 m 略有恢复，海拔2000 m 变化不明显，而海拔2200 m 仍有退化趋势；土壤化学性质在海拔1800 m和2000 m 地段得到恢复，而海拔2200 m 处仍有退化；土壤生物学性质在海拔2000 m 地段呈恢复趋势，而1800 m 和2200 m 仍处于退化状态。综合质量分析表明，与2005 年相比，2007 年海拔1800 m 和2000 m 地段土壤质量趋于变优而海拔2200 m 地段仍有退化迹象。 Soil is a key factor that affect the restoration of vegetation in the Hengduan Mountains dry valley area. But the dynamics and quality of soil is not knowed in dry area. In this study, soil physiochemical and biological characteristics ranging from 1800~2200m above sea level from a typical south-facing slope at the Minjiang River dry valley area had been studied, and characteristics of changes in soil quality along altitudinal gradients and time scales were also discussed. The principal component analysis was used to assess the soil quality. The main results were as follows: 1) Changes in soil physical properties along altitudes. Soil physical properties obtained the optimization along with the elevation in 2005 and 2007. 2) Changes in soil chemical properties. It was summarized that soil chemical properties increased with elevation in 2005, but the soil of 2000 m was the best in 2007. 3) Changes in soil biological characteristics. Soil biological properties increased with elevation in 2005, but the soil of 2000 m was the best and 1800 m was the worst in 2007. 4) Change tendency of soil quality. With the soil physics, chemistry and biology characteristics, we analysised the change tendency of soil quality in altitudes. The result indicated that soil quality increased with altituded in 2005, and soil quality of 2000 m was the best in 2007. 5) In brief, the soil quality is by physics, chemistry as well as the biology synthesizes the influence the final outcome. And the soil quality's change was manifested by soil physics, chemistry and the biology characteristics. All the results indicated soil quality still degenerated at 2200 m in in the dry valley of Minjiang River. And soil quality of 1800 m and 2000 m resumed slight.

Artificial neural network classification based on high-performance liquid chromatography of urinary and serum nucleosides for the clinical diagnosis of cancer

Nucleosides in human urine and serum have frequently been studied as a possible biomedical marker for cancer, acquired immune deficiency syndrome (AIDS) and the whole-body turnover of RNAs. Fifteen normal and modified nucleosides were determined in 69 urine and 42 serum samples using high-performance liquid chromatography (HPLC). Artificial neural networks have been used as a powerful pattern recognition tool to distinguish cancer patients from healthy persons. The recognition rate for the training set reached 100%. In the validating set, 95.8 and 92.9% of people were correctly classified into cancer patients and healthy persons when urine and serum were used as the sample for measuring the nucleosides. The results show that the artificial neural network technique is better than principal component analysis for the classification of healthy persons and cancer patients based on nucleoside data. (C) 2002 Elsevier Science B.V. All rights reserved.

A QUANTITATIVE ASSESSMENT OF SOURCE CONTRIBUTIONS TO INHALABLE PARTICULATE MATTER POLLUTION IN METROPOLITAN BOSTON

In this paper, source apportionment techniques are employed to identify and quantify the major particle pollution source classes affecting a monitoring site in metropolitan Boston, MA. A Principal Component Analysis (PCA) of paniculate elemental data allows the estimation of mass contributions for five fine mass panicle source classes (soil, motor vehicle, coal related, oil and salt aerosols), and six coarse panicle source classes (soil, motor vehicle, refuse incineration, residual oil, salt and sulfate aerosols). Also derived are the elemental characteristics of those source aerosols and their contributions to the total recorded elemental concentrations (i.e. an elemental mass balance). These are estimated by applying a new approach to apportioning mass among various PCA source components: the calculation of Absolute Principal Component Scores, and the subsequent regression of daily mass and elemental concentrations on these scores.

Spatial variability in water quality and surface sediment diatom assemblages in a complex lake basin,lake of the woods,ontario,canada

Lake of the Woods (LOW) is an international waterbody spanning the Canadian provinces of Ontario and Manitoba, and the U.S. state of Minnesota. In recent years, there has been a perception that water quality has deteriorated in northern regions of the lake, with all increase in the frequency and intensity of toxin-producing cyanobacterial blooms. However, given the lack of long-term data these trends are difficult to verify. As a first step, we examine spatial and seasonal patterns in water quality in this highly complex lake on the Canadian Shield. Further, we examine surface sediment diatom assemblages across multiple sites to determine if they track within-take differences in environmental conditions. Our results show that there are significant spatial patterns in water quality in LOW. Principal Component Analysis divides the lake into three geographic zones based primarily on algal nutrients (i.e., total phosphorus, TP), with the highest concentrations at sites proximal to Rainy River. This variation is closely tracked by sedimentary diatom assemblages, with [TP] explaining 43% of the variation in diatom assemblages across sites. The close correlation between water quality and the surface sediment diatom record indicate that paleoecological models could be used to provide data on the relative importance of natural and anthropogenic sources of nutrients to the lake.

小麦抗旱生态分类中适合性聚类方法的研究

探索了适合于小麦品种抗旱生态分类的聚类方法 .选用 2 1个农艺性状和 15个冬小麦品种 (系 ) ,在聚类分析的各环节上 ,通过采用不同的策略 ,大规模进行了各种分类结果的比较 .结果表明 ,在与专家经验分类接近程度上 ,数据转换方法中 ,原始数据法依次大于普通相关阵基础上的方差极大正交旋转法、Promax斜交旋转法、主成份法 ;相似性度量上 ,欧氏距离大于马氏距离 ;聚类方式上 ,对应分析法和模糊聚类法大于最短距离法、最长距离法、类平均法 ;所有可组合的方法中 ,以对应分析法和直接用原始数据的模糊聚类法的分类结果最接近专家经验分类 .结合各方法理论上优缺点的分析与检验 ,认为这两种方法也是较理想的方法 .

Fast Haar Transform Based Feature Extraction for Face Representation and Recognition

Subspace learning is the process of finding a proper feature subspace and then projecting high-dimensional data onto the learned low-dimensional subspace. The projection operation requires many floating-point multiplications and additions, which makes the projection process computationally expensive. To tackle this problem, this paper proposes two simple-but-effective fast subspace learning and image projection methods, fast Haar transform (FHT) based principal component analysis and FHT based spectral regression discriminant analysis. The advantages of these two methods result from employing both the FHT for subspace learning and the integral vector for feature extraction. Experimental results on three face databases demonstrated their effectiveness and efficiency.

L1-Norm-Based 2DPCA

In this paper, we first present a simple but effective L1-norm-based two-dimensional principal component analysis (2DPCA). Traditional L2-norm-based least squares criterion is sensitive to outliers, while the newly proposed L1-norm 2DPCA is robust. Experimental results demonstrate its advantages.

Supervised Gaussian Process Latent Variable Model for Dimensionality Reduction

The Gaussian process latent variable model (GP-LVM) has been identified to be an effective probabilistic approach for dimensionality reduction because it can obtain a low-dimensional manifold of a data set in an unsupervised fashion. Consequently, the GP-LVM is insufficient for supervised learning tasks (e. g., classification and regression) because it ignores the class label information for dimensionality reduction. In this paper, a supervised GP-LVM is developed for supervised learning tasks, and the maximum a posteriori algorithm is introduced to estimate positions of all samples in the latent variable space. We present experimental evidences suggesting that the supervised GP-LVM is able to use the class label information effectively, and thus, it outperforms the GP-LVM and the discriminative extension of the GP-LVM consistently. The comparison with some supervised classification methods, such as Gaussian process classification and support vector machines, is also given to illustrate the advantage of the proposed method.

NMR and pattern recognition studies on the acute biochemical effects of Lu(NO3)(3)

Pattern recognition methods were applied to the analysis of 600 MHz H-1 NMR spectra of urine from rats dosed with compounds that induced organ-specific damage in the liver and kidney. Male Wistar rats were separated into groups (n=4) and each was treated with one of following compounds: HgCl2, CCl4, Lu(NO3)(3) and Changle (a kind of rare earth complex mixed with La, Ce, Pr and Nd). Urine samples from the rats dosed with HgCl2, CCl4 and Lu(NO3)(3) were collected over a 24 h time course and the samples from the rats administrated with Changle were gained after 3 months. These samples were measured by 600 MHz NMR spectroscopy. Each spectrum was data-processed to provide 223 intensity-related descriptors of spectra. Urine spectral data corresponding to the time intervals, 0-8 h (HgCl2 and CCl4), 4-8 (Lu(NO3)(3)) h and 90 d (Changle) were analyzed using principal component analysis (PCA). Successful classification of the toxicity and biochemical effects of Lu(NO3)(3) was achieved.

Investigation on acute biochemical effects of Ce(NO3)(3) on liver and kidney tissues by MAS H-1 NMR spectroscopic-based metabonontic approach

High resolution magic angle spinning (MAS)-H-1 nuclear magnetic resonance (NMR) spectroscopic-based metabonomic approach was applied to the investigation on the acute biochemical effects of Ce(No-3)(3). Male Wistar rats were administrated with various doses of Ce (NO3)(3)(2, 10, and 50 mg(.)kg(-1) body weight), and MAS H-1 NMR spectra of intact liver and kidney tissues were analyzed using principal component analysis to extract toxicity information. The biochemical effects of Ce (NO3)(3) were characterized by the increase of triglycerides and lactate and the decrease of glycogen in rat liver tissue, together with an elevation of the triglyceride level and a depletion of glycerophosphocholine and betaine in kidney tissues. The target lesions of Ce (NO3)(3) on liver and kidney were found by MAS NMR-based metabonomic method. This study demonstrates that the combination of MAS H-1 NMR and pattern recognition analysis can be an effective method for studies of biochemical effects of rare earths.

Comparison of nonlinear and linear PCA on surface wind, surface height, and SST in the South China Sea

We compared nonlinear principal component analysis (NLPCA) with linear principal component analysis (LPCA) with the data of sea surface wind anomalies (SWA), surface height anomalies (SSHA), and sea surface temperature anomalies (SSTA), taken in the South China Sea (SCS) between 1993 and 2003. The SCS monthly data for SWA, SSHA and SSTA (i.e., the anomalies with climatological seasonal cycle removed) were pre-filtered by LPCA, with only three leading modes retained. The first three modes of SWA, SSHA, and SSTA of LPCA explained 86%, 71%, and 94% of the total variance in the original data, respectively. Thus, the three associated time coefficient functions (TCFs) were used as the input data for NLPCA network. The NLPCA was made based on feed-forward neural network models. Compared with classical linear PCA, the first NLPCA mode could explain more variance than linear PCA for the above data. The nonlinearity of SWA and SSHA were stronger in most areas of the SCS. The first mode of the NLPCA on the SWA and SSHA accounted for 67.26% of the variance versus 54.7%, and 60.24% versus 50.43%, respectively for the first LPCA mode. Conversely, the nonlinear SSTA, localized in the northern SCS and southern continental shelf region, resulted in little improvement in the explanation of the variance for the first NLPCA.

Effect of water temperature on digestive enzyme activity and gut mass in sea cucumber Apostichopus japonicus (Selenka), with special reference to aestivation

The effect of water temperature on gut mass and digestive enzyme activity in sea cucumber Apostichopus japonicus, including relative gut mass (RGM), amylase, lipase, pepsin and trypsin activities were studied at temperatures of 7, 14, 21, and 28A degrees C over a period of 40 days. Results show that RGM significantly decreased after 40 days at 21A degrees C and markedly decreased over the whole experiment period at 28A degrees C; however, no significant effect of duration was observed at 7 or 14A degrees C. At 14A degrees C, trypsin activity significantly decreased over 10 and 20 days, then increased; amylase and trypsin activity significantly decreased after 40 days at 28A degrees C. However, no significant effect of duration was found on amylase, pepsin or trypsin activities in the other temperature treatment groups. At 28A degrees C, lipase activity peaked in 20 days and then markedly decreased to a minimum at the end of the experiment. On the other hand, pepsin activity at 28A degrees C continuously increased over the whole experimental period. Principle component analysis showed that sea cucumbers on day 40 in the 21A degrees C group and in the previous 20 days in the 28A degrees C group were in the prophase of aestivation. At 28A degrees C, sea cucumbers aestivated at 30-40 days after the start of the experiment. It is concluded that the effect of temperature on the digestion of A. japonicus is comparatively weak within a specific range of water temperatures and aestivation behavior is accompanied by significant changes in RGM and digestive enzyme activities.

One century record of contamination by polycyclic aromatic hydrocarbons and polychlorinated biphenyls in core sediments from the southern Yellow Sea

Sixteen polycyclic aromatic hydrocarbons (PAHs) and 28 polychlorinated biphenyls (PCBs) were measured at a 2-cm interval in a core sample from the middle of the southern Yellow Sea for elucidating their historical variations in inflow and sources. The chronology was obtained using the Pb-210 method. PAHs concentrations decreased generally with depth and two climax values occurred in 14-16 cm and 20-22 cm layers, demonstrating that the production and usage of PAHs might reach peaks in the periods of 1956-1962 and 1938-1944. The booming economy and the navy battles of the Second World War might explain why the higher levels were detected in the two layers. The result of principal component analysis (PCA) revealed that PAHs were primarily owing to the combustion product. Down-cored variation of PCB concentrations was complex. Higher concentrations besides the two peaks being the same as PAHs were detected from 4 to 8 cm, depositing from 1980 to 1992, which probably resulted from the disposal of the out-dated PCB-containing equipment. The average Cl percentage of PCBs detected was similar to that of the mixture of Aroclor 1254 and 1242, suggesting they might origin from the dielectrical and heat-transfer fluid. The total organic carbon (TOC) content played a prevalent role in the adsorption of high molecular weight PAHs (>= 4-ring), while no obvious relationship among total PCBs, the concentration of congeners, and TOC was found.