资源类型

期刊论文 23

年份

2023 1

2022 3

2021 3

2019 1

2018 2

2017 1

2016 1

2015 1

2014 1

2012 2

2009 2

2008 1

2007 1

2006 2

2004 1

展开 ︾

关键词

人脸识别 2

特征抽取 2

乡村基层治理体系 1

二维线性鉴别分析 1

刀具状态监测;流形学习;降维;扩散映射分析;内蕴特征提取 1

创新规划编制与管理方式 1

勒让德多项式 1

半监督;主动学习;集成学习;混合判别分析;故障分类 1

厄米多项式 1

土地供给模式 1

基于内容的卫星图像配准;特征点分布;图像配准;线性判别准则;遥感;尺度不变特征变换 1

多类Adaboost算法 1

广义最佳鉴别矢量集 1

广义置信度 1

悬索桥 1

手写汉字识别 1

承重索 1

拉盖尔多项式 1

改进的二次鉴别函数 1

展开 ︾

检索范围:

排序: 展示方式:

Cusp points and assembly changing motions in the PRR-PR-PRR planar parallel manipulator

《机械工程前沿(英文)》 2023年 第18卷 第2期 doi: 10.1007/s11465-022-0743-x

摘要: Most parallel manipulators have multiple solutions to the direct kinematic problem. The ability to perform assembly changing motions has received the attention of a few researchers. Cusp points play an important role in the kinematic behavior. This study investigates the cusp points and assembly changing motions in a two degrees of freedom planar parallel manipulator. The direct kinematic problem of the manipulator yields a quartic polynomial equation. Each root in the equation determines the assembly configuration, and four solutions are obtained for a given set of actuated joint coordinates. By regarding the discriminant of the repeated roots of the quartic equation as an implicit function of two actuated joint coordinates, the direct kinematic singularity loci in the joint space are determined by the implicit function. Cusp points are then obtained by the intersection of a quadratic curve and a cubic curve. Two assembly changing motions by encircling different cusp points are highlighted, for each pair of solutions with the same sign of the determinants of the direct Jacobian matrices.

关键词: planar parallel manipulator     assembly changing motions     cusp points     quartic polynomial     discriminant of repeated roots    

The adoption of repeated measurement of variance analysis and Shapiro–Wilk test

《医学前沿(英文)》 2022年 第16卷 第4期   页码 659-660 doi: 10.1007/s11684-021-0908-8

Local uncorrelated local discriminant embedding for face recognition

Xiao-hu MA,Meng YANG,Zhao ZHANG

《信息与电子工程前沿(英文)》 2016年 第17卷 第3期   页码 212-223 doi: 10.1631/FITEE.1500255

摘要: The feature extraction algorithm plays an important role in face recognition. However, the extracted features also have overlapping discriminant information. A property of the statistical uncorrelated criterion is that it eliminates the redundancy among the extracted discriminant features, while many algorithms generally ignore this property. In this paper, we introduce a novel feature extraction method called local uncorrelated local discriminant embedding (LULDE). The proposed approach can be seen as an extension of a local discriminant embedding (LDE) framework in three ways. First, a new local statistical uncorrelated criterion is proposed, which effectively captures the local information of interclass and intraclass. Second, we reconstruct the affinity matrices of an intrinsic graph and a penalty graph, which are mentioned in LDE to enhance the discriminant property. Finally, it overcomes the small-sample-size problem without using principal component analysis to preprocess the original data, which avoids losing some discriminant information. Experimental results on Yale, ORL, Extended Yale B, and FERET databases demonstrate that LULDE outperforms LDE and other representative uncorrelated feature extraction methods.

关键词: Feature extraction     Local discriminant embedding     Local uncorrelated criterion     Face recognition    

INTERFERENCE BY NON-HOST PLANT ROOTS AND ROOT EXUDATES IN THE INFECTION PROCESSES OF PHYTOPHTHORA NICOTIANAE

《农业科学与工程前沿(英文)》 2021年 第8卷 第3期   页码 447-459 doi: 10.15302/J-FASE-2021399

摘要:

Crop rotations are widely used because they can significantly reduce the incidence of pests and diseases. The interactions between non-host roots and pathogens may be key in the inhibition of soilborne pathogens in crop rotations. Interactions between fennel (Foeniculum vulgare) roots/root exudates and Phytophthora nicotianae were investigated because of the known allelopathy between fennel and tobacco (Nicotiana tabacum). The effects of the key compounds in the fennel rhizosphere on the mycelial growth and zoospore behavior of P. nicotianae were assessed. The roots of fennel attracted P. nicotianae zoospores and inhibited their motility and the germination of cystospores, with some cystospores rupturing. 4-ethylacetophenone, vanillin and N-formylpiperidine were consistently identified in the fennel rhizosphere and were found to interfere with the infection of P. nicotianae, especially vanillin. Hyphae treated with these compounds produced more abnormal branches and accumulated reactive oxygen species. These interspecific interactions between non-host roots and pathogens were found to be an important factor in the inhibition by fennel of infection by P. nicotianae.

 

关键词: fennel and tobacco rotation     infection behavior     Phytophthora nicotianae     reactive oxygen species     vanillin    

Answer for questions of repeated measurements of variance analysis and distribution test of data — Authors

《医学前沿(英文)》 2022年 第16卷 第4期   页码 661-664 doi: 10.1007/s11684-021-0907-9

Crushed rocks stabilized with organosilane and lignosulfonate in pavement unbound layers: Repeated load

Diego Maria BARBIERI, Inge HOFF, Chun-Hsing HO

《结构与土木工程前沿(英文)》 2021年 第15卷 第2期   页码 412-424 doi: 10.1007/s11709-021-0700-5

摘要: The creation of the new “Ferry-Free Coastal Highway Route E39” in southwest Norway entails the production of a remarkable quantity of crushed rocks. These resources could be beneficially employed as aggregates in the unbound courses of the highway itself or other road pavements present nearby. Two innovative stabilizing agents, organosilane and lignosulfonate, can significantly enhance the key properties, namely, resilient modulus and resistance against permanent deformation, of the aggregates that are excessively weak in their natural state. The beneficial effect offered by the additives was thoroughly evaluated by performing repeated load triaxial tests. The study adopted the most common numerical models to describe these two key mechanical properties. The increase in the resilient modulus and reduction in the accumulated vertical permanent deformation show the beneficial impact of the additives. Furthermore, a finite element model was created to simulate the repeated load triaxial test by implementing nonlinear elastic and plastic constitutive relationships.

关键词: organosilane     lignosulfonate     crushed rocks     pavement unbound layers     repeated load triaxial test     finite element analysis    

An approach for mechanical fault classification based on generalized discriminant analysis

LI Wei-hua, SHI Tie-lin, YANG Shu-zi

《机械工程前沿(英文)》 2006年 第1卷 第3期   页码 292-298 doi: 10.1007/s11465-006-0022-2

摘要: To deal with pattern classification of complicated mechanical faults, an approach to multi-faults classification based on generalized discriminant analysis is presented. Compared with linear discriminant analysis (LDA), generalized discriminant analysis (GDA), one of nonlinear discriminant analysis methods, is more suitable for classifying the linear non-separable problem. The connection and difference between KPCA (Kernel Principal Component Analysis) and GDA is discussed. KPCA is good at detection of machine abnormality while GDA performs well in multi-faults classification based on the collection of historical faults symptoms. When the proposed method is applied to air compressor condition classification and gear fault classification, an excellent performance in complicated multi-faults classification is presented.

关键词: generalized discriminant     non-separable     abnormality     classification     multi-faults classification    

K+ and Na+ fluxes in roots of two Chinese Iris populations

Pinfang LI,Biao ZHANG

《农业科学与工程前沿(英文)》 2014年 第1卷 第2期   页码 144-149 doi: 10.15302/J-FASE-2014016

摘要: Maintenance of ion homeostasis, particularly the regulation of K and Na uptake, is important for all plants to adapt to salinity. Observations on ionic response to salinity and net fluxes of K , Na in the root exhibited by plants during salt stress have highlighted the need for further investigation. The objectives of this study were to compare salt adaptation of two Chinese Iris ( Pall. var. (Fisch.) Koidz.) populations, and to improve understanding of adaptation to salinity exhibited by plants. Plants used in this study were grown from seeds collected in the Xinjiang Uygur Autonomous Region (Xj) and Beijing Municipality (Bj), China. Hydroponically-grown seedlings of the two populations were supplied with nutrient solutions containing 0.1 (control) and 140 mmol·L NaCl. After 12 days, plants were harvested for determination of relative growth rate and K , Na concentrations. Net fluxes of K , Na from the apex and along the root axis to 10.8 mm were measured using non-invasive micro-test technique. With 140 mmol·L NaCl treatment, shoots for population Xj had larger relative growth rate and higher K concentration than shoots for population Bj. However, the Na concentrations in both shoots and roots were lower for Xj than those for Bj. There was a lower net efflux of K found in population Xj than by Bj in the mature zone (approximately 2.4-10.8 mm from root tip). However, no difference in the efflux of Na between the populations was obtained. Population Xj of continued to grow normally under NaCl stress, and maintained a higher K /Na ratio in the shoots. These traits, which were associated with lower K leakage, help population Xj adapt to saline environments.

关键词: Iris lactea Pall. var. chinensis (Fisch.) Koidz     population     K+ and Na+     ion flux     non-invasive micro-test technique    

Effect of repeated gonadotropin stimulation on ovarian reserves and proliferation of ovarian surface

Linlin LIANG, Bei XU, Guijin ZHU

《医学前沿(英文)》 2009年 第3卷 第2期   页码 220-226 doi: 10.1007/s11684-009-0037-2

摘要: This study aimed to evaluate the effect of repeated ovarian stimulation (OS) on the ovarian follicular population and morphology in female mice and its influence on the embryo’s developmental ability, and the profile of the ovarian surface epithelium (OSE). A total of 75 mice were enrolled in this experiment and randomly assigned into three groups: repeated ovarian stimulated group [ =25; receiving 5 IU pregnant mare serum gonadotrophin (PMSG) and human chorionic gonadotropin (hCG) at 6 day intervals for 5 cycles]; single ovarian stimulated group ( =25; receiving 5 IU PMSG and hCG for 1 cycle), and control group ( =25; without additional treatment). The follicle number at various stages and the morphologies were recorded respectively in the three groups. The harvested oocytes or embryos, cleavage rate, good quality embryo rate, and blastocyst production rate were counted and calculated, and the proliferations of ovarian surface epithelium were evaluated respectively. In the three groups, the single ovarian stimulation treatment significantly increased the mean number of ovarian oocytes or embryos (39.25±10.77 one-cell embryos/female); on the other hand, repeated gonadotropin stimulation obtained the lowest mean number (5.15± 2.81 eggs/female, <0.01). Repeated ovarian stimulation also tended to decrease normal follicles of primary follicles (66.67%) and secondary follicles (72.86%), and got the lowest cleavage rate (67.47%), lowest good quality embryo rate (2.41%), and lowest blastocyst production rate (0). The OSE cells adjacent to the antral follicles and corpus luteum (CL) in the repeated ovarian stimulated group (81.8%) had a significantly higher proliferation rate than the other groups. The proliferation rate of the OSE in the single ovarian stimulated group (56.4%) was significantly higher than that in the control group (37.5%) ( <0.01). In conclusion, single ovarian stimulation may produce more oocytes/embryos. However, repeated gonadotropin stimulation may have a negative effect on the ovarian follicular quality, the number of mature retrieved oocytes, and the embryo quality, even increasing the chance of ovarian cancer.

关键词: gonadotropin-releasing hormone     ovarian reserve     embryo developmental ability     ovarian surface epithelium    

基于模糊集理论的二维线性鉴别分析新方法

郑宇杰,杨静宇,吴小俊,李勇智

《中国工程科学》 2007年 第9卷 第2期   页码 49-53

摘要:

二维线性鉴别分析(2DLDA)是一种直接基于矩阵的特征提取方法,跳过传统的基于Fisher鉴别准则 的线性鉴别分析方法中必须先将二维矩阵转化成一维矢量的过程,有效地提高了特征提取速度且避免了小样本问题,其识别率优于传统的Fisherface方法。结合模糊集理论,提出了一种新的2DLDA算法——模糊2DLDA (F1DLDA)算法。首先采用FKNN算法得到相应的样本分布信息,并按其对最后得到的特征向量所作的贡献融入 到特征抽取过程中,得到有效的样本特征向量集。实验表明,F2DLDA算法的性能优于传统的2DLDA算法和Fisherface算法。

关键词: 二维线性鉴别分析     模糊二维线性鉴别分析     模糊集理论     特征提取     模糊k近邻    

Evaluation and prediction of slope stability using machine learning approaches

《结构与土木工程前沿(英文)》 2021年 第15卷 第4期   页码 821-833 doi: 10.1007/s11709-021-0742-8

摘要: In this paper, the machine learning (ML) model is built for slope stability evaluation and meets the high precision and rapidity requirements in slope engineering. Different ML methods for the factor of safety (FOS) prediction are studied and compared hoping to make the best use of the large variety of existing statistical and ML regression methods collected. The data set of this study includes six characteristics, namely unit weight, cohesion, internal friction angle, slope angle, slope height, and pore water pressure ratio. The whole ML model is primarily divided into data preprocessing, outlier processing, and model evaluation. In the data preprocessing, the duplicated data are first removed, then the outliers are filtered by the LocalOutlierFactor method and finally, the data are standardized. 11 ML methods are evaluated for their ability to learn the FOS based on different input parameter combinations. By analyzing the evaluation indicators R 2, MAE, and MSE of these methods, SVM, GBR, and Bagging are considered to be the best regression methods. The performance and reliability of the nonlinear regression method are slightly better than that of the linear regression method. Also, the SVM-poly method is used to analyze the susceptibility of slope parameters.

关键词: slope stability     factor of safety     regression     machine learning     repeated cross-validation    

统计不相关最佳鉴别矢量集的本质研究

吴小俊,杨静宇,王士同,刘同明,Josef Kittler

《中国工程科学》 2004年 第6卷 第2期   页码 44-47

摘要:

对统计不相关最佳鉴别矢量集的本质进行研究,在基于总体散布矩阵特征分解的基础上,构造了一种白化变换,使得变换后的样本空间中的总体散布矩阵为单位矩阵,这样使得传统的最佳鉴别矢量集算法得到的均是具有统计不相关的最佳鉴别矢量集,从而揭示了统计不相关最佳鉴别变换的本质——白化变换加普通的线性鉴别变换。该方法的最大优点在于所获得的最优鉴别矢量同时具有正交性和统计不相关性。该方法对代数特征抽取具有普遍适用性。用ORL人脸数据库的数值实验,验证了该方法的有效性。

关键词: 模式识别     特征抽取     鉴别分析     广义最佳鉴别矢量集     人脸识别    

集成增强主动学习混合判别分析模型及其在半监督故障分类中的应用 Research Article

王伟俊1,王云2,王君1,方信昀3,何雨辰1

《信息与电子工程前沿(英文)》 2022年 第23卷 第12期   页码 1814-1827 doi: 10.1631/FITEE.2200053

摘要: 故障分类作为过程监控中不可缺少的部分,其性能高度依赖于过程知识的充分性。然而,由于采样条件有限及实验室分析昂贵,数据标签总是难以获取,这可能导致分类性能下降。为了解决这个难题,本文提出一种新的半监督故障分类方法,其中每个未标记样本相对于特定标记数据集的价值采用增强的主动学习来评估。具有高价值的未标记样本将作为训练数据集的补充信息。此外,引入了几个合理的指标和准则大大降低了人工标注的干扰。最后,通过数值例子和田纳西伊士曼过程(TEP)评估了该方法的故障分类有效性。

关键词: 半监督;主动学习;集成学习;混合判别分析;故障分类    

Repeated batch fermentation with water recycling and cell separation for microbial lipid production

Yumei WANG, Wei LIU, Jie BAO

《化学科学与工程前沿(英文)》 2012年 第6卷 第4期   页码 453-460 doi: 10.1007/s11705-012-1210-8

摘要: Large waste water disposal was the major problem in microbial lipid fermentation because of low yield of lipid. In this study, the repeated batch fermentation was investigated for reducing waste water generated in the lipid fermentation of an oleaginous yeast CX1 strain. The waste fermentation broth was recycled in the next batch operation after the cells were separated using two different methods, centrifugation and flocculation. Two different sugar substrates, glucose and inulin, were applied to the proposed operation. The result showed that at least 70% of the waste water was reduced, while lipid production maintained satisfactory in the initial four cycles. Furthermore, it is suggested that CX1 cells might produce certain naturally occurring inulin hydrolyzing enzyme(s) for obtaining fructose and glucose from inulin directly. Our method provided a practical option for reducing the waste water generated from microbial lipid fermentation.

关键词: batch fermentation     microbial lipid     Trichosporon cutaneum CX1     flocculation     waste water recycle    

A novel multimode process monitoring method integrating LDRSKM with Bayesian inference

Shi-jin REN,Yin LIANG,Xiang-jun ZHAO,Mao-yun YANG

《信息与电子工程前沿(英文)》 2015年 第16卷 第8期   页码 617-633 doi: 10.1631/FITEE.1400263

摘要: A local discriminant regularized soft -means (LDRSKM) method with Bayesian inference is proposed for multimode process monitoring. LDRSKM extends the regularized soft -means algorithm by exploiting the local and non-local geometric information of the data and generalized linear discriminant analysis to provide a better and more meaningful data partition. LDRSKM can perform clustering and subspace selection simultaneously, enhancing the separability of data residing in different clusters. With the data partition obtained, kernel support vector data description (KSVDD) is used to establish the monitoring statistics and control limits. Two Bayesian inference based global fault detection indicators are then developed using the local monitoring results associated with principal and residual subspaces. Based on clustering analysis, Bayesian inference and manifold learning methods, the within and cross-mode correlations, and local geometric information can be exploited to enhance monitoring performances for nonlinear and non-Gaussian processes. The effectiveness and efficiency of the proposed method are evaluated using the Tennessee Eastman benchmark process.

关键词: Multimode process monitoring     Local discriminant regularized soft k-means clustering     Kernel support vector data description     Bayesian inference     Tennessee Eastman process    

标题 作者 时间 类型 操作

Cusp points and assembly changing motions in the PRR-PR-PRR planar parallel manipulator

期刊论文

The adoption of repeated measurement of variance analysis and Shapiro–Wilk test

期刊论文

Local uncorrelated local discriminant embedding for face recognition

Xiao-hu MA,Meng YANG,Zhao ZHANG

期刊论文

INTERFERENCE BY NON-HOST PLANT ROOTS AND ROOT EXUDATES IN THE INFECTION PROCESSES OF PHYTOPHTHORA NICOTIANAE

期刊论文

Answer for questions of repeated measurements of variance analysis and distribution test of data — Authors

期刊论文

Crushed rocks stabilized with organosilane and lignosulfonate in pavement unbound layers: Repeated load

Diego Maria BARBIERI, Inge HOFF, Chun-Hsing HO

期刊论文

An approach for mechanical fault classification based on generalized discriminant analysis

LI Wei-hua, SHI Tie-lin, YANG Shu-zi

期刊论文

K+ and Na+ fluxes in roots of two Chinese Iris populations

Pinfang LI,Biao ZHANG

期刊论文

Effect of repeated gonadotropin stimulation on ovarian reserves and proliferation of ovarian surface

Linlin LIANG, Bei XU, Guijin ZHU

期刊论文

基于模糊集理论的二维线性鉴别分析新方法

郑宇杰,杨静宇,吴小俊,李勇智

期刊论文

Evaluation and prediction of slope stability using machine learning approaches

期刊论文

统计不相关最佳鉴别矢量集的本质研究

吴小俊,杨静宇,王士同,刘同明,Josef Kittler

期刊论文

集成增强主动学习混合判别分析模型及其在半监督故障分类中的应用

王伟俊1,王云2,王君1,方信昀3,何雨辰1

期刊论文

Repeated batch fermentation with water recycling and cell separation for microbial lipid production

Yumei WANG, Wei LIU, Jie BAO

期刊论文

A novel multimode process monitoring method integrating LDRSKM with Bayesian inference

Shi-jin REN,Yin LIANG,Xiang-jun ZHAO,Mao-yun YANG

期刊论文