2007-09-25
由于生物发酵过程具有复杂性和高度非线性的特点，采用模糊最小二乘支持向量机方法，将模糊化思想引入到最小二乘支持向量机中，并应用到青霉素发酵过程建模中，仿真结果表明，模糊最小二乘支持向量机方法具有良好的
2011-01-10
本文提出了一种基于提升小波和最小二乘支持向量机的大坝变形预测方法，即通过提升小波分析提取大坝监测数据效应量，分别对各效应量使用最小二乘支持向量机模型进行训练预测，然后将各分量的预测结果合成，作为最终
高等学校博士学科点专项科研基金（20070294023）
国家自然科学基金资助项目（51079046）
中央高校基本科研业务费项目（50909041）
河海大学水利水电学院；河海大学 水文水资源与水利工程科学国家重点实验室,河海大学水利水电学院；河海大学 水文水资源与水利工程科学国家重点实验室,河海大学水利水电学院；河海大学 水文水资源与水利工程科学国家重点实验室
#水利工程#
He Yong,Cen Haiyan ,Bao Yidan ,Huang Min
The estimation of nitrogen status non-destructively in oilseed rape in a crop-growing period was performed using reflectance spectroscopy with least-squares support vector (LS-SVM). This study was conducted at the experiment farm of Zhejiang University, Hangzhou, China. The SPAD value was used as a reference data that reflects nitrogen status in oilseed rape. A total of 159 oilseed rape leaf samples were used for visible and near infrared reflectance spectroscopy at 325-1075 nm using a field spectroradiometer. The reflectance data processed by median filter was applied for LS-SVM regression model to predict SPAD values. The performance of LS-SVM with RBF kernel function and five input variables derived from scores of partial least squares (PLS) latent variables (LVs) was investigated. To serve this purpose, the grid-search technique using 5-fold cross-validation was used to find out the optimal values of two important parameters in LS-SVM regression model. At the same time, LS-SVM model was compared with PLS and back propagation neural network (BPNN) methods. The results showed that LS-SVM was superior to the conventional linear and non-linear methods in predicting SPAD values of oilseed rape leaves. It is concluded that LS-SVM regression method is a promising technique for chemometrics in the field of quantitative prediction.
2007-12-14
教育部博士点基金（20040335034 ）
Zhejiang University,Zhejiang University,Zhejiang University,Zhejiang University
#Agronomy#
2005-02-05
不可分的问题转换成在高维特征空间中线性可分的问题，用最小二乘支持向量机方法构建一种新的水质综合评价模型。该模型经过训练和检验，并用于实际的地下水水质综合评价，其结果较客观和科学，可以推广到相关的
北京大学环境科学系
#环境科学技术#
In the research of the nonlinear time series prediction, we apply the least squares support vector machine (LS-SVM) to use. In order to improve the precision LS-SVM has been discussed in the following aspects. First, the parameterγand multi-step prediction capabilities of the LS-SVM network are investigated. Then we employ clustering method in the model to prune the number of the support values. The learning rate and the capabilities of filtering noise for LS-SVM are all greatly improved.
2005-01-13
Department of Physics, Nankai University,Department of Physics, Nankai University
#Physics#
2016-02-01
在啤酒发酵过程中，为了建立精准的传感器温度故障诊断模型，在标准支持向量机(SVM)的基础上提出了分段加权最小二乘支持向量机的方法，该方法首先利用模糊C聚类(FCM)对样本进行聚类分析，达到划分
黑龙江省自然科学基金（F201222）
哈尔滨理工大学自动化学院 ，哈尔滨，150080,哈尔滨理工大学自动化学院，哈尔滨，150080
本文收录在中国科技论文在线精品论文，2016，9（10）：1048-1054.
2011-08-25
针对传统GPS高程异常反演方法中存在的不足，本文采用遗传算法优化最小二乘支持向量机参数反演GPS高程异常。实验表明，在有限样本的情况下，GA-LSSVM模型不仅发挥了LSSVM处理小样本数据的能力
2009-07-06
虽然支持向量机具有非线性拟合、泛化能力强、训练收敛速度快等显著特点，但当处理海量电力负荷数据时，支持向量机的训练效率降低，针对解决这一问题提出的最小二乘支持向量机被引入电力短期负荷预测中。当负荷样本
2009-12-30
，限制了该算法的应用。为此提出基于线性最小二乘支持向量机的N-FINDR改进算法，该算法无需降维预处理，且采用低复杂度的距离尺度代替复杂的体积尺度来加速算法。此外还提出对野值点施加有效控制以赋予算法鲁棒性
国家自然科学基金（60802059）
教育部博士点基金（200802171003）
国家自然科学基金（0）
哈尔滨工程大学信息与通信工程学院,哈尔滨工程大学信息与通信工程学院,哈尔滨工程大学信息与通信工程学院
#测绘科学技术#
SI Gangquan,SHI Jianquan,Guo Zhang
To solve the sparseness problem of least squares support vector machine (LSSVM) in learning process, a training algorithm of LSSVM based on active learning is investigated. In the first stage of the algorithm, in order to solve the problem of a large number of similar training data samples, we select support samples by K-means clustering method. The second stage, we obtain a model using LSSVM and conduct function estimation of the all samples, calculating the error of the estimation values and the original samples, sorting support samples and selecting the best sample. Then the selected sample is added into training set to obtain new model. And the processes are repeated until the predetermined performance requirements are achieved, thus the sparse LSSVM model is obtained. The simulation on sinc function indicates that the proposed method performs more effectively than Suykens standard sparse method for removing the redundant support vector with better sparseness and robustness. The experiments on motorcycle dataset of the UCI indicate that the proposed algorithm can solve the problem of heteroscedasticity in some degree.
2014-03-19
the Specialized Research Fund for Doctoral Program of Higher Education of China （Grant No:20130201120011）
State Key Laboratory of Electrical Insulation and Power Equipment, School of Electrical Engineering, Xi'an Jiaotong University, Xi’an, Shaanxi Province, 710049 ,State Key Laboratory of Electrical Insulation and Power Equipment, School of Electrical Engineering, Xi'an Jiaotong University, Xi’an, Shaanxi Province, 710049,State Key Laboratory of Electrical Insulation and Power Equipment, School of Electrical Engineering, Xi'an Jiaotong University, Xi’an, Shaanxi Province, 710049
提示
