A sparse approximation algorithm based on projection is presented in this paper in order to overcome the limitation of the non-sparsity of least squares support vector machines （LS-SVM）. The new inputs are projected...A sparse approximation algorithm based on projection is presented in this paper in order to overcome the limitation of the non-sparsity of least squares support vector machines （LS-SVM）. The new inputs are projected into the subspace spanned by previous basis vectors （BV） and those inputs whose squared distance from the subspace is higher than a threshold are added in the BV set, while others are rejected. This consequently results in the sparse approximation. In addition, a recursive approach to deleting an exiting vector in the BV set is proposed. Then the online LS-SVM, sparse approximation and BV removal are combined to produce the sparse online LS-SVM algorithm that can control the size of memory irrespective of the processed data size. The suggested algorithm is applied in the online modeling of a pH neutralizing process and the isomerization plant of a refinery, respectively. The detailed comparison of computing time and precision is also given between the suggested algorithm and the nonsparse one. The results show that the proposed algorithm greatly improves the sparsity just with little cost of precision.展开更多
Least squares projection twin support vector machine(LSPTSVM)has faster computing speed than classical least squares support vector machine(LSSVM).However,LSPTSVM is sensitive to outliers and its solution lacks sparsi...Least squares projection twin support vector machine(LSPTSVM)has faster computing speed than classical least squares support vector machine(LSSVM).However,LSPTSVM is sensitive to outliers and its solution lacks sparsity.Therefore,it is difficult for LSPTSVM to process large-scale datasets with outliers.In this paper,we propose a robust LSPTSVM model(called R-LSPTSVM)by applying truncated least squares loss function.The robustness of R-LSPTSVM is proved from a weighted perspective.Furthermore,we obtain the sparse solution of R-LSPTSVM by using the pivoting Cholesky factorization method in primal space.Finally,the sparse R-LSPTSVM algorithm(SR-LSPTSVM)is proposed.Experimental results show that SR-LSPTSVM is insensitive to outliers and can deal with large-scale datasets fastly.展开更多
Based on analysis of the supporting object of bulking soft rock and comparing the supporting difficulty of the repairing projects with that of the newly excavated projects, this paper proposes a method to determine re...Based on analysis of the supporting object of bulking soft rock and comparing the supporting difficulty of the repairing projects with that of the newly excavated projects, this paper proposes a method to determine reasonable supporting parameters for soft rock project repairing. This method has been verified to be reasonable and economical in an industrial test.展开更多
The rapid development of China’s economic construction following the opening to the outside world calls for more foreign funds. Undertaking the task to raise funds abroad for many years, the Bank of China (BOC) has f...The rapid development of China’s economic construction following the opening to the outside world calls for more foreign funds. Undertaking the task to raise funds abroad for many years, the Bank of China (BOC) has furnished substantial foreign funds for a large number of key state projects. Since 1993 the BOC has issued bonds in Tokyo on three occasions, totalling Japanese yen 45 billion. It reentered the European capital展开更多
Checked by Henan Province Development and Relbrm Commission and Henan Province MunicipalFinance （）ffice, the “R ＆ I） and Industrialization of High Performance Functional Refractories for Metallurgy New Technology...Checked by Henan Province Development and Relbrm Commission and Henan Province MunicipalFinance （）ffice, the “R ＆ I） and Industrialization of High Performance Functional Refractories for Metallurgy New Technology” project declared by 1,1RR gained a special fund support on self-renovation and products structure adjustment. The project will realize the technology integration and industriali-zation of key refractories including purging component, metering nozzle and toil and belt continuous casting nozzle, etc. through building high performance functional refractories production lines for metallurgy new technology.展开更多
Development of the global economy makes modem enterprises confront challenges of efficient managements for large projects and complex processes. Projects are typically managed in rather special manners. On the contrar...Development of the global economy makes modem enterprises confront challenges of efficient managements for large projects and complex processes. Projects are typically managed in rather special manners. On the contrary, there exist many methodologies for product process management to achieve consistency and continuance. However, processes often lack flexibility offered by projects. This paper dis~ the relationship of conceptual characteristics between process and project, gives low-level details to tackle the difference between them, and proposes an enterprise process modeling method for project management. An integrated environment is designed to support the method from which both project management and process management can receive benefits and conform to the limitations.展开更多
Based on the features of the non-standard equipment executing work, a project management and decision support system oriented to the non-standard equipment is developed, and the information model, function model as we...Based on the features of the non-standard equipment executing work, a project management and decision support system oriented to the non-standard equipment is developed, and the information model, function model as well as the structure framework of the system are also introduced in this paper.展开更多
为解决传统数字滤波器在有限精度实现时因有限字长(Finite Word Length,FWL)效应导致滤波器性能下降的问题,提出一种L_(2)灵敏度最小化的数字滤波器状态空间实现稀疏化方法.推导前向差分算子数字滤波器结构传输函数及其等效状态空间实现...为解决传统数字滤波器在有限精度实现时因有限字长(Finite Word Length,FWL)效应导致滤波器性能下降的问题,提出一种L_(2)灵敏度最小化的数字滤波器状态空间实现稀疏化方法.推导前向差分算子数字滤波器结构传输函数及其等效状态空间实现,根据可控及可观格莱姆矩阵得到基于相似变换矩阵的L_(2)灵敏度表达式,并进行稀疏化校准,将L_(2)灵敏度最小化问题转换为凸函数求最值问题,求导得到L_(2)灵敏度最小化表达式,代回即得前向差分算子数字滤波器的稀疏化状态空间实现.仿真结果表明,所提方法设计的数字滤波器具有更好的抗FWL效应.展开更多
针对天基信息支援体系效能评估中存在的主观性强与复杂性高的问题,提出一种基于投影梯度神经网络的天基信息支援体系效能评估方法。首先,基于国防部体系框架(Department of Defense Architecture Framework,DoDAF)视图产品与包以德循环(...针对天基信息支援体系效能评估中存在的主观性强与复杂性高的问题,提出一种基于投影梯度神经网络的天基信息支援体系效能评估方法。首先,基于国防部体系框架(Department of Defense Architecture Framework,DoDAF)视图产品与包以德循环(observation,orientation,decision,action,OODA)梳理体系作战流程,进而建立评估指标体系,并基于离散事件仿真生成效能评估数据样本。然后,基于Rosen-反向传播(back propagation,BP)神经网络构建效能评估代理模型,并通过对权重参数的限制来解决在效益型指标下评估模型难以解释的问题。最后,对仿真样本进行评估模型验证试验,结果表明所提方法在天基信息支援体系效能评估中相较于传统BP神经网络计算性能提升超过50%,能够为天基信息支援体系效能评估提供技术支撑。展开更多
基金supported by the National Creative Research Groups Science Foundation of China (NCRGSFC:60721062)National Basic Research Program of China (973 Program) (No.2007CB714000)
文摘A sparse approximation algorithm based on projection is presented in this paper in order to overcome the limitation of the non-sparsity of least squares support vector machines （LS-SVM）. The new inputs are projected into the subspace spanned by previous basis vectors （BV） and those inputs whose squared distance from the subspace is higher than a threshold are added in the BV set, while others are rejected. This consequently results in the sparse approximation. In addition, a recursive approach to deleting an exiting vector in the BV set is proposed. Then the online LS-SVM, sparse approximation and BV removal are combined to produce the sparse online LS-SVM algorithm that can control the size of memory irrespective of the processed data size. The suggested algorithm is applied in the online modeling of a pH neutralizing process and the isomerization plant of a refinery, respectively. The detailed comparison of computing time and precision is also given between the suggested algorithm and the nonsparse one. The results show that the proposed algorithm greatly improves the sparsity just with little cost of precision.
基金supported by the National Natural Science Foundation of China(6177202062202433+4 种基金621723716227242262036010)the Natural Science Foundation of Henan Province(22100002)the Postdoctoral Research Grant in Henan Province(202103111)。
文摘Least squares projection twin support vector machine(LSPTSVM)has faster computing speed than classical least squares support vector machine(LSSVM).However,LSPTSVM is sensitive to outliers and its solution lacks sparsity.Therefore,it is difficult for LSPTSVM to process large-scale datasets with outliers.In this paper,we propose a robust LSPTSVM model(called R-LSPTSVM)by applying truncated least squares loss function.The robustness of R-LSPTSVM is proved from a weighted perspective.Furthermore,we obtain the sparse solution of R-LSPTSVM by using the pivoting Cholesky factorization method in primal space.Finally,the sparse R-LSPTSVM algorithm(SR-LSPTSVM)is proposed.Experimental results show that SR-LSPTSVM is insensitive to outliers and can deal with large-scale datasets fastly.
文摘Based on analysis of the supporting object of bulking soft rock and comparing the supporting difficulty of the repairing projects with that of the newly excavated projects, this paper proposes a method to determine reasonable supporting parameters for soft rock project repairing. This method has been verified to be reasonable and economical in an industrial test.
文摘The rapid development of China’s economic construction following the opening to the outside world calls for more foreign funds. Undertaking the task to raise funds abroad for many years, the Bank of China (BOC) has furnished substantial foreign funds for a large number of key state projects. Since 1993 the BOC has issued bonds in Tokyo on three occasions, totalling Japanese yen 45 billion. It reentered the European capital
文摘Checked by Henan Province Development and Relbrm Commission and Henan Province MunicipalFinance （）ffice, the “R ＆ I） and Industrialization of High Performance Functional Refractories for Metallurgy New Technology” project declared by 1,1RR gained a special fund support on self-renovation and products structure adjustment. The project will realize the technology integration and industriali-zation of key refractories including purging component, metering nozzle and toil and belt continuous casting nozzle, etc. through building high performance functional refractories production lines for metallurgy new technology.
基金Project supported by Aviation Basic Science Fundation( GrantNo .00F51058)
文摘Development of the global economy makes modem enterprises confront challenges of efficient managements for large projects and complex processes. Projects are typically managed in rather special manners. On the contrary, there exist many methodologies for product process management to achieve consistency and continuance. However, processes often lack flexibility offered by projects. This paper dis~ the relationship of conceptual characteristics between process and project, gives low-level details to tackle the difference between them, and proposes an enterprise process modeling method for project management. An integrated environment is designed to support the method from which both project management and process management can receive benefits and conform to the limitations.
文摘Based on the features of the non-standard equipment executing work, a project management and decision support system oriented to the non-standard equipment is developed, and the information model, function model as well as the structure framework of the system are also introduced in this paper.
文摘为解决传统数字滤波器在有限精度实现时因有限字长(Finite Word Length,FWL)效应导致滤波器性能下降的问题,提出一种L_(2)灵敏度最小化的数字滤波器状态空间实现稀疏化方法.推导前向差分算子数字滤波器结构传输函数及其等效状态空间实现,根据可控及可观格莱姆矩阵得到基于相似变换矩阵的L_(2)灵敏度表达式,并进行稀疏化校准,将L_(2)灵敏度最小化问题转换为凸函数求最值问题,求导得到L_(2)灵敏度最小化表达式,代回即得前向差分算子数字滤波器的稀疏化状态空间实现.仿真结果表明,所提方法设计的数字滤波器具有更好的抗FWL效应.
