期刊文献+
共找到357篇文章
< 1 2 18 >
每页显示 20 50 100
Time-variant reliability analysis of three-dimensional slopes based on Support Vector Machine method 被引量:4
1
作者 陈昌富 肖治宇 张根宝 《Journal of Central South University》 SCIE EI CAS 2011年第6期2108-2114,共7页
In the reliability analysis of slope, the performance functions derived from the most available stability analysis procedures of slopes are usually implicit and cannot be solved by first-order second-moment approach. ... In the reliability analysis of slope, the performance functions derived from the most available stability analysis procedures of slopes are usually implicit and cannot be solved by first-order second-moment approach. A new reliability analysis approach was presented based on three-dimensional Morgenstem-Price method to investigate three-dimensional effect of landslide in stability analyses. To obtain the reliability index, Support Vector Machine (SVM) was applied to approximate the performance function. The time-consuming of this approach is only 0.028% of that using Monte-Carlo method at the same computation accuracy. Also, the influence of time effect of shearing strength parameters of slope soils on the long-term reliability of three-dimensional slopes was investigated by this new approach. It is found that the reliability index of the slope would decrease by 52.54% and the failure probability would increase from 0.000 705% to 1.966%. In the end, the impact of variation coefficients of c andfon reliability index of slopes was taken into discussion and the changing trend was observed. 展开更多
关键词 slope engineering Morgenstern-Price method three dimension support Vector Machine time-variant reliability
下载PDF
COMPACTLY SUPPORTED NON-TENSOR PRODUCT FORM TWO-DIMENSION WAVELET FINITE ELEMENT 被引量:2
2
作者 金坚明 薛鹏翔 +1 位作者 徐应祥 朱亚莉 《Applied Mathematics and Mechanics(English Edition)》 SCIE EI 2006年第12期1673-1686,共14页
Some theorems of compactly supported non-tensor product form two-dimension Daubechies wavelet were analysed carefully. Compactly supported non-tensor product form two-dimension wavelet was constructed, then non-tensor... Some theorems of compactly supported non-tensor product form two-dimension Daubechies wavelet were analysed carefully. Compactly supported non-tensor product form two-dimension wavelet was constructed, then non-tensor product form two dimension wavelet finite element was used to solve the deflection problem of elastic thin plate. The error order was researched. A numerical example was given at last. 展开更多
关键词 compactly supported non-tensor product two-dimension wavelet interpolation function elastic thin plate DEFLECTION finite element
下载PDF
The Fracture Density and Fractal Dimension Prediction Based on Support Vector Machine
3
作者 Lei Zhao Liehui Zhang Yilin Wang 《International Journal of Geosciences》 2013年第4期672-679,共8页
The key of effective development for the fractured reservoir is to describe the distribution of the fracture and build the fracture geological model. To acquire more optimal exploration and development of the oilfield... The key of effective development for the fractured reservoir is to describe the distribution of the fracture and build the fracture geological model. To acquire more optimal exploration and development of the oilfield, objective geologic model of reservoir fractures is needed for further knowledge of the spatial distribution condition of fractures. Adopting well-logging and seismic techniques can be expensive and usually yield multiple solutions, yet resolution will disturb the seismic method, making it difficult to acquire accurate and sound fracture parameters from seismic data. In this paper, the theoretical foundation for support vector machine, fractal geometry, combined the various information in geology, logging, well core, seism and field outcrop about the fracture and calculate the parameters of the fracture (fracture density and fractal dimension), and the good foundation is established for fractured reservoir description of discrete fracture network model. Based on analysis of conventional prediction methods of development indices and factor influencing the parameters of the fracture, a support vector machine method is established to predict the parameters of the fracture. The new support vector machine method is based on time series analysis to select the kernel function. Trains and tests the support vector machine network with historical data to construct the support vector regression prediction model. A case was fit into the model to test and analyse its reliability, the results suggested that the model had a high prediction performance, and could be well applied to the prediction of fracture parameters. 展开更多
关键词 Fractured RESERVOIR support VECTOR Machine FRACTURE Density FRACTAL dimension MATLAB
下载PDF
A three-dimensional digital visualization model of cervical nerves in a healthy person 被引量:1
4
作者 Jiaming Cao Dong Fu Sen Li 《Neural Regeneration Research》 SCIE CAS CSCD 2013年第20期1829-1836,共8页
Three-dimensional reconstruction nerve models are classically obtained from two-dimensional images of "visible human" frozen sections. However, because of the flexibility of nerve tissues and small color differences... Three-dimensional reconstruction nerve models are classically obtained from two-dimensional images of "visible human" frozen sections. However, because of the flexibility of nerve tissues and small color differences compared with surrounding tissues, the integrity and validity of nerve tissues can be impaired during milling. Thus, in the present study, we obtained two-dimensional data from a healthy volunteer based on continuous CT angiography and magnetic resonance myelography. Semi-automatic segmentation and reconstruction were then conducted at different thresholds in different tissues using Mimics software. Small anatomical structures such as muscles and cervical nerves were reconstructed using the medical computer aided design module. Three-dimensional digital models of the cervical nerves and their surrounding structures were successfully developed, which allowed visualization of the spatial relation of anatomical structures with a strong three-dimensional effect, distinct appearance, clear distribution, and good continuity, precision, and integrality. These results indicate the validity of a three-dimensional digital visualization model of healthy human cervical nerves, which overcomes the disadvantages of milling, avoids data loss, and exhibits a realistic appearance and three-dimensional image. 展开更多
关键词 neural regeneration CERVICAL THREE-dimension CT magnetic resonance myelography cervical plexus phrenic nerve vagus nerve recurrent laryngeal nerve GANGLION stellate ganglion grants-supported paper NEUROREGENERATION
下载PDF
Aeroelastic modeling of wind loading on a cable-net supported glass wall 被引量:1
5
作者 Zhifu Gu Letian Yang Yan Li Bin Chen 《Acta Mechanica Sinica》 SCIE EI CAS CSCD 2010年第3期409-415,共7页
Wind loading study on a cable-net supported glass wall is conducted by means of wind tunnel tests. An equiva- lent aeroelastic model is designed and constructed. Response of displacements of the wall is measured and a... Wind loading study on a cable-net supported glass wall is conducted by means of wind tunnel tests. An equiva- lent aeroelastic model is designed and constructed. Response of displacements of the wall is measured and analyzed. In order to design a glass wall under wind loading, the "wind- vibration factor" is estimated and discussed. In fact, the mech- anism of wind acting on the wall is commonly known not only as positive pressure, but also as negative pressure caused by the flow separation on the corners of the building. Due to the diffidence in the mechanism of wind acting, two typi- cal response cases are classified. The results show that the dynamic response of the structure caused by the negative pressure is stronger than that of the positive pressure case. To determine the aerodynamic wind loading on a flexible part of structure on a building, wind tunnel study may be useful and play an important role. 展开更多
关键词 Wind tunnel study Cable-net supported glasswall - Wind-vibration factor Aeroelastic model
下载PDF
基于ELDA降维与MPA-SVM的滚动轴承故障诊断方法 被引量:1
6
作者 刘运航 宋宇博 朱大鹏 《噪声与振动控制》 CSCD 北大核心 2024年第3期117-124,共8页
为了提高滚动轴承故障诊断精度,提出一种基于偏心线性判别分析(Eccentric Linear Discriminant Analysis,ELDA)降维算法与经海洋捕食者算法(Marine Predators Algorithm,MPA)优化的支持向量机(Support Vector Machine,SVM)相结合的滚动... 为了提高滚动轴承故障诊断精度,提出一种基于偏心线性判别分析(Eccentric Linear Discriminant Analysis,ELDA)降维算法与经海洋捕食者算法(Marine Predators Algorithm,MPA)优化的支持向量机(Support Vector Machine,SVM)相结合的滚动轴承故障诊断方法。首先对轴承信号应用时域和频域分析方法构建高维特征集,其次应用自适应最大似然估计方法(Adaptive Maximum Likelihood Estimation,AMLE)进行固有维度估计,利用ELDA算法进行二次特征提取,充分挖掘敏感特征,降低冗余特征对故障诊断的影响;最后将低维敏感可分矩阵输入到MPA-SVM分类器中识别故障类型。实验分析表明,所提方法能有效缩短训练时长并提高诊断准确率。 展开更多
关键词 故障诊断 滚动轴承 特征降维 海洋捕食者算法 支持向量机
下载PDF
DEVELOPING EXPERT DECISION SUPPORT SYSTEM WTH VP-EXPERT AND LOTUS 1-2-3 IN RE-BLENDING BY USE
7
作者 舒航 杨鹏 《Journal of China University of Mining and Technology》 1994年第2期104-111,共8页
An expert decision support system (EDSS) for multi-bins balance and contro1 of orequality in production ore bins of some large-scale open pit iron mine in China has been developed byexpert svitem tool software VP-EXPE... An expert decision support system (EDSS) for multi-bins balance and contro1 of orequality in production ore bins of some large-scale open pit iron mine in China has been developed byexpert svitem tool software VP-EXPERT and integration software LOTUS 1-2-3 in this paper. Itis known by practicing that a medium-scale EDSS constructed on microcomputer is completcly, feaasible by means of VP-EXEPERT to construct knowledge base system (KBS), LOTUS 1-2-3 tomake decision support system (DSS) and link them with BAT. 展开更多
关键词 VP-EXPERT LOTUS 1-2-3 ore-blending expert System decision support system expert decision support system
下载PDF
EXACT SOLUTION FOR RECTANGULAR SLAB WITH THREE EDGES SIMPLY-SUPPORTED AND OTHER FREE
8
作者 YU TENGHAIDepartment of Mathematics 《内江师范学院学报》 1996年第2期1-7,共7页
In this paper,we give all-sided pastic analysis of the rectangular slab with three edges simply-supported and other free.Here we discuss the following four cases:(1)The uniformly distributedload over the area a slab.(... In this paper,we give all-sided pastic analysis of the rectangular slab with three edges simply-supported and other free.Here we discuss the following four cases:(1)The uniformly distributedload over the area a slab.(2).A concentrated load act at midpoint of free edges slab.(3)A concen-trated load act at the center a slab.(4)The line load act along free edge of slab. 展开更多
关键词 The RECTANGULAR SLAB with three EDGES simply - supportED and OTHER free have wide the use value. But up to now only find the EXACT solution that a concentrated load act at midpoint of free edye a slab. The EXACT solution of OTHER support force
下载PDF
A Novel Way to Prepareγ-A1_2O_3 Supported SO_4^(2-)/ZrO_2 Solid Superacid Catalysts for n-Butane Isomerization
9
作者 Ting LEI Yi TANG +2 位作者 Wei Ming HUA Jin Suo XU Zi GAO (Department of Chemistry, Fudan University, Shanghai 200433) 《Chinese Chemical Letters》 SCIE CAS CSCD 2000年第1期89-92,共4页
Highly active solid superacid catalysts for n-butane isomerization, SZ/A1_2O_3-P, were prepared by supporting SO-(4-2)/ZrO2, (SZ) on y-A1_2O_3 carrier using a precipitation method. The activities of some catalysts wer... Highly active solid superacid catalysts for n-butane isomerization, SZ/A1_2O_3-P, were prepared by supporting SO-(4-2)/ZrO2, (SZ) on y-A1_2O_3 carrier using a precipitation method. The activities of some catalysts were enhanced significantly j The activity of the most active sample. 60%SZ/Al_2O3-P, was even about 2 times more active than that of the SZ catalyst. 展开更多
关键词 SO_4^(2-)/ZrO_2 n-Butane Isomerization γ-A1_2O_3 supported superacid catalysts.
下载PDF
NEW SOLID BASE DERIVED FROM AIPO4-5 SUPPORTED KF
10
作者 Jian Hua ZHU Qin Hug XU Hideshi HATTORI(Chemistry Department, Nanjing University.Nanjing 210093,China.)(Centre for Advanced Research of Energy Technology, Hokkaido University,Sapporo 060.Japan) 《Chinese Chemical Letters》 SCIE CAS CSCD 1996年第7期671-674,共4页
Dispersion of KF on AlPO4-5 molecular sieve created basic sites and caused 1654 cm- band of bidentate carbonate in CO2 adsorption.After pre-treated above 823K. 5%KF/AlPO4-5exhibited basic catalytic activity in the iso... Dispersion of KF on AlPO4-5 molecular sieve created basic sites and caused 1654 cm- band of bidentate carbonate in CO2 adsorption.After pre-treated above 823K. 5%KF/AlPO4-5exhibited basic catalytic activity in the isomerization of butenes at 273K. and the activity increasedwith the pre-treatment temperature up to 923K. 展开更多
关键词 NEW SOLID BASE DERIVED FROM AIPO4-5 supportED KF
下载PDF
基于DIGWO-VMD-CMPE的轴承故障识别方法
11
作者 辛昊 鲁玉军 朱轩逸 《机电工程》 CAS 北大核心 2024年第2期205-215,共11页
针对滚动轴承故障信号特征提取困难和识别准确率低的问题,提出了一种基于维度学习的改进灰狼优化算法(DIGWO)优化变分模态分解(VMD)和复合多尺度排列熵(CMPE)的轴承故障识别方法。首先,采用基于维度学习的狩猎(DLH)搜索策略、余弦收敛因... 针对滚动轴承故障信号特征提取困难和识别准确率低的问题,提出了一种基于维度学习的改进灰狼优化算法(DIGWO)优化变分模态分解(VMD)和复合多尺度排列熵(CMPE)的轴承故障识别方法。首先,采用基于维度学习的狩猎(DLH)搜索策略、余弦收敛因子a和个体狼ω位置更新的方法将灰狼优化算法(GWO)改进为DIGWO,并利用DIGWO算法的自适应性优化VMD分解,得到了多个本征模态函数(IMFs);然后,利用复合多尺度排列熵计算IMFs的特征值,选取适当维数的特征,构建了故障特征向量;最后,利用DIGWO算法优化支持向量机(SVM)的惩罚系数C和径向基函数g,建立了DIGWO-SVM滚动轴承故障诊断分类器,并利用滚动轴承的振动数据验证了算法的有效性。研究结果表明:基于CMPE的DIGWO-SVM滚动轴承故障诊断方法能够有效地识别轴承的运行状况,识别准确率达到了99.42%,相较于PSO-SVM、SSA-SVM方法提高了7.75%、1.68%,证明了该方法的分类性能在滚动轴承故障诊断中更具优势。 展开更多
关键词 基于维度学习的改进灰狼优化算法 变分模态分解 复合多尺度排列熵 支持向量机 本征模态函数 基于维度学习的狩猎
下载PDF
SVM-KNN分类器——一种提高SVM分类精度的新方法 被引量:133
12
作者 李蓉 叶世伟 史忠植 《电子学报》 EI CAS CSCD 北大核心 2002年第5期745-748,共4页
本文提出了一种将支持向量机分类和最近邻分类相结合的方法 ,形成了一种新的分类器 .首先对支持向量机进行分析可以看出它作为分类器实际相当于每类只选一个代表点的最近邻分类器 ,同时在对支持向量机分类时出错样本点的分布进行研究的... 本文提出了一种将支持向量机分类和最近邻分类相结合的方法 ,形成了一种新的分类器 .首先对支持向量机进行分析可以看出它作为分类器实际相当于每类只选一个代表点的最近邻分类器 ,同时在对支持向量机分类时出错样本点的分布进行研究的基础上 ,在分类阶段计算待识别样本和最优分类超平面的距离 ,如果距离差大于给定阈值直接应用支持向量机分类 ,否则代入以每类的所有的支持向量作为代表点的K近邻分类 .数值实验证明了使用支持向量机结合最近邻分类的分类器分类比单独使用支持向量机分类具有更高的分类准确率 。 展开更多
关键词 SVM-KNN分类器 SVM分类精度 支持向量机 最近邻分类 模式识别 人工智能
下载PDF
2RPU-UPR并联机构在天线支撑中的应用 被引量:9
13
作者 许允斗 仝少帅 +3 位作者 王贝 鞠忠金 姚建涛 赵永生 《中国机械工程》 EI CAS CSCD 北大核心 2019年第14期1748-1755,共8页
为了解决现有天线支撑机构不能同时满足高承载能力与大工作空间的要求,采用并联机构2RPU-UPR作为天线支撑机构,并对机构进行设计与实验。分析了并联机构2RPU-UPR的受力特征并建立了静力平衡方程。提出了最大承载能力与驱动分支运动范围... 为了解决现有天线支撑机构不能同时满足高承载能力与大工作空间的要求,采用并联机构2RPU-UPR作为天线支撑机构,并对机构进行设计与实验。分析了并联机构2RPU-UPR的受力特征并建立了静力平衡方程。提出了最大承载能力与驱动分支运动范围两个优化指标,采用统一目标函数法建立两个指标的综合评价函数,对支撑机构关键尺度进行了优化设计,得到了一组机构性能优异的结构尺寸;研制了天线支撑机构实验样机,并进行了实验,实验结果表明:提出的天线支撑机构不仅能够承受大载荷,而且能满足横摇±90°、纵摇±90°的大工作空间需求,具有良好的应用前景。 展开更多
关键词 天线支撑机构 并联机构 尺度优化 结构设计
下载PDF
基于LS-SVM的装备需求时间序列预测 被引量:6
14
作者 刘文法 王旭 张建邦 《弹箭与制导学报》 CSCD 北大核心 2006年第S4期780-783,共4页
支持向量机(SVM)是一种基于结构风险最小化原理的学习技术,是一种新的具有很好泛化性能的数据挖掘工具。文中在最小二乘支持向量机(LS-SVM)回归算法的基础上,引入了混沌理论时间序列理论的相空间和嵌入维数概念,建立了LS-SVM时间序列预... 支持向量机(SVM)是一种基于结构风险最小化原理的学习技术,是一种新的具有很好泛化性能的数据挖掘工具。文中在最小二乘支持向量机(LS-SVM)回归算法的基础上,引入了混沌理论时间序列理论的相空间和嵌入维数概念,建立了LS-SVM时间序列预测模型,并应用于武器装备需求预测,预测结果证实了该模型和方法的有效性。 展开更多
关键词 支持向量机 时间序列 混沌 相空间 嵌入维数
下载PDF
基于D-score与支持向量机的混合特征选择方法 被引量:5
15
作者 谢娟英 雷金虎 +1 位作者 谢维信 高新波 《计算机应用》 CSCD 北大核心 2011年第12期3292-3296,共5页
F-score作为特征评价准则时,没有考虑不同特征的不同测量量纲对特征重要性的影响。为此,提出一种新的特征评价准则D-score,该准则不仅可以衡量样本特征在两类或多类之间的辨别能力,而且不受特征测量量纲对特征重要性的影响。以D-score... F-score作为特征评价准则时,没有考虑不同特征的不同测量量纲对特征重要性的影响。为此,提出一种新的特征评价准则D-score,该准则不仅可以衡量样本特征在两类或多类之间的辨别能力,而且不受特征测量量纲对特征重要性的影响。以D-score为特征重要性评价准则,结合前向顺序搜索、前向顺序浮动搜索以及后向浮动搜索三种特征搜索策略,以支持向量机分类正确率评价特征子集的分类性能得到三种混合的特征选择方法。这些特征选择方法结合了Filter方法和Wrapper方法的各自优势实现特征选择。对UCI机器学习数据库中9个标准数据集的实验测试,以及与基于改进F-score与支持向量机的混合特征选择方法的实验比较,表明D-score特征评价准则是一种有效的样本特征重要性,也即特征辨别能力衡量准则。基于该准则与支持向量机的混合特征选择方法实现了有效的特征选择,在保持数据集辨识能力不变情况下实现了维数压缩。 展开更多
关键词 D-score F-score 支持向量机 特征选择 评估准则 维压缩
下载PDF
基于分形维数和GA-SVM的风电机组齿轮箱轴承故障诊断 被引量:20
16
作者 时培明 梁凯 +1 位作者 赵娜 安淑君 《计量学报》 CSCD 北大核心 2018年第1期61-65,共5页
对风机齿轮箱轴承故障诊断进行了研究,提出一种基于分形维数和遗传算法支持向量机(GA-SVM)相结合的故障诊断算法。基于常用的时域特征参数作为支持向量机的识别参数,引入分形维数特征参数来提升支持向量机的识别精度。提出了基于遗传算... 对风机齿轮箱轴承故障诊断进行了研究,提出一种基于分形维数和遗传算法支持向量机(GA-SVM)相结合的故障诊断算法。基于常用的时域特征参数作为支持向量机的识别参数,引入分形维数特征参数来提升支持向量机的识别精度。提出了基于遗传算法(GA)的支持向量机参数优化的模型,通过GA的寻优自动获得最优的支持向量机参数。采用某风场的风电机组齿轮箱轴承数据进行故障诊断,实验表明,所提出的GA-SVM模型很好地解决了参数选择的问题,同时基于分形维数的特征参数也提高了风电机组轴承故障的识别准确率。 展开更多
关键词 计量学 轴承故障诊断 风电齿轮箱 分形维数 遗传算法支持向量机 识别准确率
下载PDF
基于两种GMM-UBM多维概率输出的SVM语音情感识别 被引量:2
17
作者 黄永明 章国宝 +1 位作者 董飞 达飞鹏 《计算机应用研究》 CSCD 北大核心 2011年第1期98-101,共4页
针对GMM应用于情感识别时区分能力较弱的缺点,提出了一种将GMM与SVM有效结合的算法:基于GMM-UBM多维概率输出的SVM语音情感识别方法。该方法将GMM-UBM模型对一条语音的情感特征参数的两种多维概率输出(与特征向量同维、与GMM阶数同维)作... 针对GMM应用于情感识别时区分能力较弱的缺点,提出了一种将GMM与SVM有效结合的算法:基于GMM-UBM多维概率输出的SVM语音情感识别方法。该方法将GMM-UBM模型对一条语音的情感特征参数的两种多维概率输出(与特征向量同维、与GMM阶数同维)作为SVM分类器的特征参数,既利用了GMM表征数据本身统计特性的能力,又保留了SVM判决能力强的特点。在柏林情感语音库与汉语情感语料库上进行的实验结果表明,该方法在语音情感识别上的平均识别率较标准GMM方法提高1.7%~3.7%。 展开更多
关键词 语音情感识别 特征向量同维GMM—UBM多维概率输出 GMM阶数同维GMM—UBM多维概率输出 支持向量机(SVM)
下载PDF
一种采用CCPSO-SVM的煤与瓦斯突出预测方法 被引量:4
18
作者 黄为勇 邵晓根 陈奎 《计算机科学》 CSCD 北大核心 2012年第11期216-220,225,共6页
为了有效地对矿井煤与瓦斯突出进行预测,提出了一种基于完全混沌粒子群优化(CCPSO)与支持向量机(SVM)的矿井煤与瓦斯突出预测方法。该方法将矿井工作面前方煤体瓦斯涌出量动态变化时间序列的多重分维谱作为特征指标,应用支持向量(SVM)... 为了有效地对矿井煤与瓦斯突出进行预测,提出了一种基于完全混沌粒子群优化(CCPSO)与支持向量机(SVM)的矿井煤与瓦斯突出预测方法。该方法将矿井工作面前方煤体瓦斯涌出量动态变化时间序列的多重分维谱作为特征指标,应用支持向量(SVM)构建预测模型,模型的参数向量由改进的完全混沌粒子群优化算法和测试集样本集分类错误率最小准则选择和优化。实验结果证明,该方法是有效的,它为煤与瓦斯突出预测提供了一种新途径。 展开更多
关键词 煤与瓦斯突出 预测 支持向量机 完全混沌粒子群优化 多重分维谱
下载PDF
基于PSO-SVM的高光谱数据降维的可靠性研究 被引量:2
19
作者 臧卓 林辉 杨敏华 《中国农学通报》 CSCD 北大核心 2011年第31期47-52,共6页
PSO结合SVM算法对高光谱数据波段进行优化,每次搜索结果不一定相同,因此很多学者对此类算法的可靠性存在疑问。为了证明PSO-SVM降维算法的可靠性,利用PSO-SVM算法对杉木和马尾松的幼中成熟林的高光谱原始数据、一阶微分变换数据、对数... PSO结合SVM算法对高光谱数据波段进行优化,每次搜索结果不一定相同,因此很多学者对此类算法的可靠性存在疑问。为了证明PSO-SVM降维算法的可靠性,利用PSO-SVM算法对杉木和马尾松的幼中成熟林的高光谱原始数据、一阶微分变换数据、对数变换数据及归一化变换数据进行降维运算,对降维后选择的波段分别利用支持向量机(SVM)、BP神经网络、Mahalanobis距离分类法、Fisher分类法及贝叶斯分类法进行分类,分类结果中,Fisher分类法的结果最好,所有的分类结果均在90%以上,SVM和BP神经网络的分类结果都保持在80%以上,贝叶斯分类法分类精度最差,所有分类结果均未超过90%,最差结果为43.75%。同时,将PSO-SVM与PCA算法进行对比分析,发现在马尾松和杉木的分类过程中PSO-SVM算法优于PCA算法。最后得出结论,PSO-SVM算法提取的特征对Fisher、SVM及BP神经网络分类法有效;当光谱数据差异非常微小时,PSO-SVM比PCA对特征的提取更有效。 展开更多
关键词 高光谱 降维 分类 粒子群(PSO) 支持向量机(SVM)
下载PDF
双正则化参数的L_2-SVM参数选择 被引量:2
20
作者 姚程宽 许建华 《计算机工程与应用》 CSCD 2014年第8期99-102,246,共5页
寻找支持向量机(SVM)的最优参数是支持向量机研究领域的热点之一。2范数软间隔SVM(L2-SVM)将样本转化成线性可分,在原始单正则化参数L2-SVM的基础上,提出双正则化参数的L2-SVM,获得它的对偶形式,从而确定了最优化的目标函数。然后结合... 寻找支持向量机(SVM)的最优参数是支持向量机研究领域的热点之一。2范数软间隔SVM(L2-SVM)将样本转化成线性可分,在原始单正则化参数L2-SVM的基础上,提出双正则化参数的L2-SVM,获得它的对偶形式,从而确定了最优化的目标函数。然后结合梯度法,提出了一种新的支持向量机参数选择的新方法(Doupenalty-Gradient)。实验使用了10个基准数据集,结果表明,Doupenalty-Gradient方法是可行且有效的。对于实验所用的样本,极大地改善了分类精度。 展开更多
关键词 统计学习理论 支持向量机 VC维 参数选择
下载PDF
上一页 1 2 18 下一页 到第
使用帮助 返回顶部