In soft sensor field, just-in-time learning(JITL) is an effective approach to model nonlinear and time varying processes. However, most similarity criterions in JITL are computed in the input space only while ignoring...In soft sensor field, just-in-time learning(JITL) is an effective approach to model nonlinear and time varying processes. However, most similarity criterions in JITL are computed in the input space only while ignoring important output information, which may lead to inaccurate construction of relevant sample set. To solve this problem, we propose a novel supervised feature extraction method suitable for the regression problem called supervised local and non-local structure preserving projections(SLNSPP), in which both input and output information can be easily and effectively incorporated through a newly defined similarity index. The SLNSPP can not only retain the virtue of locality preserving projections but also prevent faraway points from nearing after projection,which endues SLNSPP with powerful discriminating ability. Such two good properties of SLNSPP are desirable for JITL as they are expected to enhance the accuracy of similar sample selection. Consequently, we present a SLNSPP-JITL framework for developing adaptive soft sensor, including a sparse learning strategy to limit the scale and update the frequency of database. Finally, two case studies are conducted with benchmark datasets to evaluate the performance of the proposed schemes. The results demonstrate the effectiveness of LNSPP and SLNSPP.展开更多
The concept of soft topological space was introduced by some authors. In the present paper, we investigate some basic notions of soft topological spaces by using new soft point concept. Later we give soft locally comp...The concept of soft topological space was introduced by some authors. In the present paper, we investigate some basic notions of soft topological spaces by using new soft point concept. Later we give soft locally compact space and the relationships between them are discussed in detail. Finally, we define soft paracompactness and explore some of its basic properties.展开更多
Chemical reactivity towards electron transfer is captured by the Fukui function.However,this is not well defined when the system or its ions have degenerate or pseudo-degenerate ground states.In such a case,the first-...Chemical reactivity towards electron transfer is captured by the Fukui function.However,this is not well defined when the system or its ions have degenerate or pseudo-degenerate ground states.In such a case,the first-order chemical response is not independent of the perturbation and the correct response has to be computed using the mathematical formalism of perturbation theory for degenerate states.Spatialpseudo-degeneracy is ubiquitous in nanostructures with high symmetry and totally extended systems.Given the size of these systems,using degenerate-state perturbation theory is impractical because it requires the calculation of many excited states.Here we present an alternative to compute the chemical response of extended systems using models of local softness in terms of the local density of states.The local softness is approximately equal to the density of states at the Fermi level.However,such approximation leaves out the contribution of inner states.In order to include and weight the contribution of the states around the Fermi level,a model inspired by the long-range behavior of the local softness is presented.Single wall capped carbon nanotubes(SWCCNT) illustrate the limitation of the frontier orbital theory in extended systems.Thus,we have used a C360 SWCCNT to test the proposed model and how it compares with available models based on the local density of states.Interestingly,a simple Hü ckel approximation captures the main features of chemical response of these systems.Our results suggest that density-of-states models of the softness along simple tight binding Hamiltonians could be used to explore the chemical reactivity of more complex system,such a surfaces and nanoparticles.展开更多
Inspired by the tremendous achievements of meta-learning in various fields,this paper proposes the local quadratic embedding learning(LQEL)algorithm for regression problems based on metric learning and neural networks...Inspired by the tremendous achievements of meta-learning in various fields,this paper proposes the local quadratic embedding learning(LQEL)algorithm for regression problems based on metric learning and neural networks(NNs).First,Mahalanobis metric learning is improved by optimizing the global consistency of the metrics between instances in the input and output space.Then,we further prove that the improved metric learning problem is equivalent to a convex programming problem by relaxing the constraints.Based on the hypothesis of local quadratic interpolation,the algorithm introduces two lightweight NNs;one is used to learn the coefficient matrix in the local quadratic model,and the other is implemented for weight assignment for the prediction results obtained from different local neighbors.Finally,the two sub-mod els are embedded in a unified regression framework,and the parameters are learned by means of a stochastic gradient descent(SGD)algorithm.The proposed algorithm can make full use of the information implied in target labels to find more reliable reference instances.Moreover,it prevents the model degradation caused by sensor drift and unmeasurable variables by modeling variable differences with the LQEL algorithm.Simulation results on multiple benchmark datasets and two practical industrial applications show that the proposed method outperforms several popular regression methods.展开更多
Existing unsupervised person re-identification approaches fail to fully capture thefine-grained features of local regions,which can result in people with similar appearances and different identities being assigned the...Existing unsupervised person re-identification approaches fail to fully capture thefine-grained features of local regions,which can result in people with similar appearances and different identities being assigned the same label after clustering.The identity-independent information contained in different local regions leads to different levels of local noise.To address these challenges,joint training with local soft attention and dual cross-neighbor label smoothing(DCLS)is proposed in this study.First,the joint training is divided into global and local parts,whereby a soft attention mechanism is proposed for the local branch to accurately capture the subtle differences in local regions,which improves the ability of the re-identification model in identifying a person’s local significant features.Second,DCLS is designed to progressively mitigate label noise in different local regions.The DCLS uses global and local similarity metrics to semantically align the global and local regions of the person and further determines the proximity association between local regions through the cross information of neighboring regions,thereby achieving label smoothing of the global and local regions throughout the training process.In extensive experiments,the proposed method outperformed existing methods under unsupervised settings on several standard person re-identification datasets.展开更多
Local learning based soft sensing methods succeed in coping with time-varying characteristics of processes as well as nonlinearities in industrial plants. In this paper, a local partial least squares based soft sensin...Local learning based soft sensing methods succeed in coping with time-varying characteristics of processes as well as nonlinearities in industrial plants. In this paper, a local partial least squares based soft sensing method for multi-output processes is proposed to accomplish process states division and local model adaptation,which are two key steps in development of local learning based soft sensors. An adaptive way of partitioning process states without redundancy is proposed based on F-test, where unique local time regions are extracted.Subsequently, a novel anti-over-fitting criterion is proposed for online local model adaptation which simultaneously considers the relationship between process variables and the information in labeled and unlabeled samples. Case study is carried out on two chemical processes and simulation results illustrate the superiorities of the proposed method from several aspects.展开更多
In order to solve the problem that the existing meshless models are of high computational complexity and are difficult to express the biomechanical characteristics of real soft tissue, a local high-resolution deformat...In order to solve the problem that the existing meshless models are of high computational complexity and are difficult to express the biomechanical characteristics of real soft tissue, a local high-resolution deformation model of soft tissue based on element-free Galerkin method is proposed. The proposed model applies an element-free Galerkin method to establish the model, and integrates Kelvin viscoelastic model and adjustment function to simulate nonlinear viscoelasticity of soft tissue. Meanwhile, a local high-resolution algorithm is applied to sample and render the deformed region of the model to reduce the computational complexity. To verify the effectiveness of the model,liver and brain tumor deformation simulation experiments are carried out. The experimental results show that compared with the existing meshless models, the proposed model well reflects the biomechanical characteristics of soft tissue, and is of high authenticity, which can provide better visual feedback to users while reducing computational cost.展开更多
针对软刚臂系泊系统铰节点在服役过程中出现的疲劳损伤问题,提出一种基于原型监测和局部密度双向聚类算法(Bidirectional Clustering Algorithm based on Local Density,BCALoD)的疲劳寿命计算方法。采用BCALoD算法对获得的船体六自由...针对软刚臂系泊系统铰节点在服役过程中出现的疲劳损伤问题,提出一种基于原型监测和局部密度双向聚类算法(Bidirectional Clustering Algorithm based on Local Density,BCALoD)的疲劳寿命计算方法。采用BCALoD算法对获得的船体六自由度进行工况分类,运用多体动力学将运动数据转算为受力时程,将其作为铰节点疲劳寿命分析的载荷谱。采用Abaqus软件建立各铰节点有限元模型以计算热点应力,结合Miner线性疲劳累积损伤理论和雨流计数方法计算疲劳寿命。进一步分析评估基于实测数据的铰节点疲劳设计指标,指出该FPSO软刚臂上铰节点的疲劳寿命不足以支持其完成服役,且各铰节点难以统一维护和更换。本研究可为在役软刚臂系泊系统的疲劳寿命计算提供一种新的载荷处理方法,为未来海洋平台的设计提供参考。展开更多
基金Supported by the National Natural Science Foundation of China(61273160)the Fundamental Research Funds for the Central Universities(14CX06067A,13CX05021A)
文摘In soft sensor field, just-in-time learning(JITL) is an effective approach to model nonlinear and time varying processes. However, most similarity criterions in JITL are computed in the input space only while ignoring important output information, which may lead to inaccurate construction of relevant sample set. To solve this problem, we propose a novel supervised feature extraction method suitable for the regression problem called supervised local and non-local structure preserving projections(SLNSPP), in which both input and output information can be easily and effectively incorporated through a newly defined similarity index. The SLNSPP can not only retain the virtue of locality preserving projections but also prevent faraway points from nearing after projection,which endues SLNSPP with powerful discriminating ability. Such two good properties of SLNSPP are desirable for JITL as they are expected to enhance the accuracy of similar sample selection. Consequently, we present a SLNSPP-JITL framework for developing adaptive soft sensor, including a sparse learning strategy to limit the scale and update the frequency of database. Finally, two case studies are conducted with benchmark datasets to evaluate the performance of the proposed schemes. The results demonstrate the effectiveness of LNSPP and SLNSPP.
文摘The concept of soft topological space was introduced by some authors. In the present paper, we investigate some basic notions of soft topological spaces by using new soft point concept. Later we give soft locally compact space and the relationships between them are discussed in detail. Finally, we define soft paracompactness and explore some of its basic properties.
基金This work has been supported by FONDECYT grants 1140313 and 11150164. CC and PF acknowledge support by Financiamiento Basal para Centros Cientificos y Tecnologicos de Excelencia-FB0807, and project RC-130006 CILIS, granted by the Fondo de Innovacion para
文摘Chemical reactivity towards electron transfer is captured by the Fukui function.However,this is not well defined when the system or its ions have degenerate or pseudo-degenerate ground states.In such a case,the first-order chemical response is not independent of the perturbation and the correct response has to be computed using the mathematical formalism of perturbation theory for degenerate states.Spatialpseudo-degeneracy is ubiquitous in nanostructures with high symmetry and totally extended systems.Given the size of these systems,using degenerate-state perturbation theory is impractical because it requires the calculation of many excited states.Here we present an alternative to compute the chemical response of extended systems using models of local softness in terms of the local density of states.The local softness is approximately equal to the density of states at the Fermi level.However,such approximation leaves out the contribution of inner states.In order to include and weight the contribution of the states around the Fermi level,a model inspired by the long-range behavior of the local softness is presented.Single wall capped carbon nanotubes(SWCCNT) illustrate the limitation of the frontier orbital theory in extended systems.Thus,we have used a C360 SWCCNT to test the proposed model and how it compares with available models based on the local density of states.Interestingly,a simple Hü ckel approximation captures the main features of chemical response of these systems.Our results suggest that density-of-states models of the softness along simple tight binding Hamiltonians could be used to explore the chemical reactivity of more complex system,such a surfaces and nanoparticles.
基金supported by the National Key Research and Development Program of China(2016YFB0303401)the International(Regional)Cooperation and Exchange Project(61720106008)+1 种基金the National Science Fund for Distinguished Young Scholars(61725301)the Shanghai AI Lab。
文摘Inspired by the tremendous achievements of meta-learning in various fields,this paper proposes the local quadratic embedding learning(LQEL)algorithm for regression problems based on metric learning and neural networks(NNs).First,Mahalanobis metric learning is improved by optimizing the global consistency of the metrics between instances in the input and output space.Then,we further prove that the improved metric learning problem is equivalent to a convex programming problem by relaxing the constraints.Based on the hypothesis of local quadratic interpolation,the algorithm introduces two lightweight NNs;one is used to learn the coefficient matrix in the local quadratic model,and the other is implemented for weight assignment for the prediction results obtained from different local neighbors.Finally,the two sub-mod els are embedded in a unified regression framework,and the parameters are learned by means of a stochastic gradient descent(SGD)algorithm.The proposed algorithm can make full use of the information implied in target labels to find more reliable reference instances.Moreover,it prevents the model degradation caused by sensor drift and unmeasurable variables by modeling variable differences with the LQEL algorithm.Simulation results on multiple benchmark datasets and two practical industrial applications show that the proposed method outperforms several popular regression methods.
基金supported by the National Natural Science Foundation of China under Grant Nos.62076117 and 62166026the Jiangxi Key Laboratory of Smart City under Grant No.20192BCD40002Jiangxi Provincial Natural Science Foundation under Grant No.20224BAB212011.
文摘Existing unsupervised person re-identification approaches fail to fully capture thefine-grained features of local regions,which can result in people with similar appearances and different identities being assigned the same label after clustering.The identity-independent information contained in different local regions leads to different levels of local noise.To address these challenges,joint training with local soft attention and dual cross-neighbor label smoothing(DCLS)is proposed in this study.First,the joint training is divided into global and local parts,whereby a soft attention mechanism is proposed for the local branch to accurately capture the subtle differences in local regions,which improves the ability of the re-identification model in identifying a person’s local significant features.Second,DCLS is designed to progressively mitigate label noise in different local regions.The DCLS uses global and local similarity metrics to semantically align the global and local regions of the person and further determines the proximity association between local regions through the cross information of neighboring regions,thereby achieving label smoothing of the global and local regions throughout the training process.In extensive experiments,the proposed method outperformed existing methods under unsupervised settings on several standard person re-identification datasets.
基金Supported by the National Natural Science Foundation of China(61273160)the Fundamental Research Funds for the Central Universities(14CX06067A,13CX05021A)
文摘Local learning based soft sensing methods succeed in coping with time-varying characteristics of processes as well as nonlinearities in industrial plants. In this paper, a local partial least squares based soft sensing method for multi-output processes is proposed to accomplish process states division and local model adaptation,which are two key steps in development of local learning based soft sensors. An adaptive way of partitioning process states without redundancy is proposed based on F-test, where unique local time regions are extracted.Subsequently, a novel anti-over-fitting criterion is proposed for online local model adaptation which simultaneously considers the relationship between process variables and the information in labeled and unlabeled samples. Case study is carried out on two chemical processes and simulation results illustrate the superiorities of the proposed method from several aspects.
基金Supported by the National Natural Science Foundation of China(No.61502240,61502096,61304205,61773219)Natural Science Foundation of Jiangsu Province(No.BK20141002,BK20150634)
文摘In order to solve the problem that the existing meshless models are of high computational complexity and are difficult to express the biomechanical characteristics of real soft tissue, a local high-resolution deformation model of soft tissue based on element-free Galerkin method is proposed. The proposed model applies an element-free Galerkin method to establish the model, and integrates Kelvin viscoelastic model and adjustment function to simulate nonlinear viscoelasticity of soft tissue. Meanwhile, a local high-resolution algorithm is applied to sample and render the deformed region of the model to reduce the computational complexity. To verify the effectiveness of the model,liver and brain tumor deformation simulation experiments are carried out. The experimental results show that compared with the existing meshless models, the proposed model well reflects the biomechanical characteristics of soft tissue, and is of high authenticity, which can provide better visual feedback to users while reducing computational cost.
文摘针对软刚臂系泊系统铰节点在服役过程中出现的疲劳损伤问题,提出一种基于原型监测和局部密度双向聚类算法(Bidirectional Clustering Algorithm based on Local Density,BCALoD)的疲劳寿命计算方法。采用BCALoD算法对获得的船体六自由度进行工况分类,运用多体动力学将运动数据转算为受力时程,将其作为铰节点疲劳寿命分析的载荷谱。采用Abaqus软件建立各铰节点有限元模型以计算热点应力,结合Miner线性疲劳累积损伤理论和雨流计数方法计算疲劳寿命。进一步分析评估基于实测数据的铰节点疲劳设计指标,指出该FPSO软刚臂上铰节点的疲劳寿命不足以支持其完成服役,且各铰节点难以统一维护和更换。本研究可为在役软刚臂系泊系统的疲劳寿命计算提供一种新的载荷处理方法,为未来海洋平台的设计提供参考。
