The support vector machine （SVM） is a novel machine learning method, which has the ability to approximate nonlinear functions with arbitrary accuracy. Setting parameters well is very crucial for SVM learning results...The support vector machine （SVM） is a novel machine learning method, which has the ability to approximate nonlinear functions with arbitrary accuracy. Setting parameters well is very crucial for SVM learning results and generalization ability, and now there is no systematic, general method for parameter selection. In this article, the SVM parameter selection for function approximation is regarded as a compound optimization problem and a mutative scale chaos optimization algorithm is employed to search for optimal paraxneter values. The chaos optimization algorithm is an effective way for global optimal and the mutative scale chaos algorithm could improve the search efficiency and accuracy. Several simulation examples show the sensitivity of the SVM parameters and demonstrate the superiority of this proposed method for nonlinear function approximation.展开更多
Deficiencies of applying the traditional least squares support vector machine （LS-SVM） to time series online prediction were specified. According to the kernel function matrix＇s property and using the recursive cal...Deficiencies of applying the traditional least squares support vector machine （LS-SVM） to time series online prediction were specified. According to the kernel function matrix＇s property and using the recursive calculation of block matrix, a new time series online prediction algorithm based on improved LS-SVM was proposed. The historical training results were fully utilized and the computing speed of LS-SVM was enhanced. Then, the improved algorithm was applied to timc series online prediction. Based on the operational data provided by the Northwest Power Grid of China, the method was used in the transient stability prediction of electric power system. The results show that, compared with the calculation time of the traditional LS-SVM（75 1 600 ms）, that of the proposed method in different time windows is 40-60 ms, proposed method is above 0.8. So the improved method is online prediction. and the prediction accuracy（normalized root mean squared error） of the better than the traditional LS-SVM and more suitable for time series online prediction.展开更多
Geomechanical parameters are complex and uncertain.In order to take this complexity and uncertainty into account,a probabilistic back-analysis method combining the Bayesian probability with the least squares support v...Geomechanical parameters are complex and uncertain.In order to take this complexity and uncertainty into account,a probabilistic back-analysis method combining the Bayesian probability with the least squares support vector machine(LS-SVM) technique was proposed.The Bayesian probability was used to deal with the uncertainties in the geomechanical parameters,and an LS-SVM was utilized to establish the relationship between the displacement and the geomechanical parameters.The proposed approach was applied to the geomechanical parameter identification in a slope stability case study which was related to the permanent ship lock within the Three Gorges project in China.The results indicate that the proposed method presents the uncertainties in the geomechanical parameters reasonably well,and also improves the understanding that the monitored information is important in real projects.展开更多
As a new type of learning machine developed on the basis of statistics learning theory, support vector machine （SVM） plays an important role in knowledge discovering and knowledge updating by constructing non-linear...As a new type of learning machine developed on the basis of statistics learning theory, support vector machine （SVM） plays an important role in knowledge discovering and knowledge updating by constructing non-linear optimal classifter. However, realizing SVM requires resolving quadratic programming under constraints of inequality, which results in calculation difficulty while learning samples gets larger. Besides, standard SVM is incapable of tackling multi-classification. To overcome the bottleneck of populating SVM, with training algorithm presented, the problem of quadratic programming is converted into that of resolving a linear system of equations composed of a group of equation constraints by adopting the least square SVM（LS-SVM） and introducing a modifying variable which can change inequality constraints into equation constraints, which simplifies the calculation. With regard to multi-classification, an LS-SVM applicable in multi-dassiftcation is deduced. Finally, efficiency of the algorithm is checked by using universal Circle in square and twospirals to measure the performance of the classifier.展开更多
This paper provides an introduction to a support vector machine, a new kernel-based technique introduced in statistical learning theory and structural risk minimization, then presents a modeling-control framework base...This paper provides an introduction to a support vector machine, a new kernel-based technique introduced in statistical learning theory and structural risk minimization, then presents a modeling-control framework based on SVM. At last a numerical experiment is taken to demonstrate the proposed approach's correctness and effectiveness.展开更多
弹道中段目标为一个目标群,包括弹头、诱饵、碎片等,并且由于距离传感器较远,红外成像为点目标,可用信息较少,因此单一的红外传感器往往难以满足识别要求,需要融合多个传感器进行识别。针对红外多传感器的融合识别问题,本文提出了基于...弹道中段目标为一个目标群,包括弹头、诱饵、碎片等,并且由于距离传感器较远,红外成像为点目标,可用信息较少,因此单一的红外传感器往往难以满足识别要求,需要融合多个传感器进行识别。针对红外多传感器的融合识别问题,本文提出了基于增量支持向量机和D-S(increment support vector machine-Dempster-Shafer,ISVM-DS)证据理论的融合识别方法。首先,训练多个波段传感器红外特征的支持向量数据描述(support vector data description,SVDD)模型,生成壳向量并训练其ISVM模型;接着,采用ISVM模型的后验概率生成基本概率赋值(basic probability assignment,BPA);最后,利用D-S证据理论对多个证据的BPA进行融合,输出分类结果。实验结果表明,该方法能有效提高目标识别的准确性。展开更多
基金the National Nature Science Foundation of China (60775047, 60402024)
文摘The support vector machine （SVM） is a novel machine learning method, which has the ability to approximate nonlinear functions with arbitrary accuracy. Setting parameters well is very crucial for SVM learning results and generalization ability, and now there is no systematic, general method for parameter selection. In this article, the SVM parameter selection for function approximation is regarded as a compound optimization problem and a mutative scale chaos optimization algorithm is employed to search for optimal paraxneter values. The chaos optimization algorithm is an effective way for global optimal and the mutative scale chaos algorithm could improve the search efficiency and accuracy. Several simulation examples show the sensitivity of the SVM parameters and demonstrate the superiority of this proposed method for nonlinear function approximation.
基金Project (SGKJ[200301-16]) supported by the State Grid Cooperation of China
文摘Deficiencies of applying the traditional least squares support vector machine （LS-SVM） to time series online prediction were specified. According to the kernel function matrix＇s property and using the recursive calculation of block matrix, a new time series online prediction algorithm based on improved LS-SVM was proposed. The historical training results were fully utilized and the computing speed of LS-SVM was enhanced. Then, the improved algorithm was applied to timc series online prediction. Based on the operational data provided by the Northwest Power Grid of China, the method was used in the transient stability prediction of electric power system. The results show that, compared with the calculation time of the traditional LS-SVM（75 1 600 ms）, that of the proposed method in different time windows is 40-60 ms, proposed method is above 0.8. So the improved method is online prediction. and the prediction accuracy（normalized root mean squared error） of the better than the traditional LS-SVM and more suitable for time series online prediction.
基金Projects(2013BAB02B01,2013BAB02B03)supported by the National Key Technologies R&D Program of ChinaProjects(41072224,41272347)supported by the National Natural Science Foundation of China
文摘Geomechanical parameters are complex and uncertain.In order to take this complexity and uncertainty into account,a probabilistic back-analysis method combining the Bayesian probability with the least squares support vector machine(LS-SVM) technique was proposed.The Bayesian probability was used to deal with the uncertainties in the geomechanical parameters,and an LS-SVM was utilized to establish the relationship between the displacement and the geomechanical parameters.The proposed approach was applied to the geomechanical parameter identification in a slope stability case study which was related to the permanent ship lock within the Three Gorges project in China.The results indicate that the proposed method presents the uncertainties in the geomechanical parameters reasonably well,and also improves the understanding that the monitored information is important in real projects.
文摘As a new type of learning machine developed on the basis of statistics learning theory, support vector machine （SVM） plays an important role in knowledge discovering and knowledge updating by constructing non-linear optimal classifter. However, realizing SVM requires resolving quadratic programming under constraints of inequality, which results in calculation difficulty while learning samples gets larger. Besides, standard SVM is incapable of tackling multi-classification. To overcome the bottleneck of populating SVM, with training algorithm presented, the problem of quadratic programming is converted into that of resolving a linear system of equations composed of a group of equation constraints by adopting the least square SVM（LS-SVM） and introducing a modifying variable which can change inequality constraints into equation constraints, which simplifies the calculation. With regard to multi-classification, an LS-SVM applicable in multi-dassiftcation is deduced. Finally, efficiency of the algorithm is checked by using universal Circle in square and twospirals to measure the performance of the classifier.
文摘This paper provides an introduction to a support vector machine, a new kernel-based technique introduced in statistical learning theory and structural risk minimization, then presents a modeling-control framework based on SVM. At last a numerical experiment is taken to demonstrate the proposed approach's correctness and effectiveness.
文摘弹道中段目标为一个目标群,包括弹头、诱饵、碎片等,并且由于距离传感器较远,红外成像为点目标,可用信息较少,因此单一的红外传感器往往难以满足识别要求,需要融合多个传感器进行识别。针对红外多传感器的融合识别问题,本文提出了基于增量支持向量机和D-S(increment support vector machine-Dempster-Shafer,ISVM-DS)证据理论的融合识别方法。首先,训练多个波段传感器红外特征的支持向量数据描述(support vector data description,SVDD)模型,生成壳向量并训练其ISVM模型;接着,采用ISVM模型的后验概率生成基本概率赋值(basic probability assignment,BPA);最后,利用D-S证据理论对多个证据的BPA进行融合,输出分类结果。实验结果表明,该方法能有效提高目标识别的准确性。
