This paper explores the adaptive iterative learning control method in the control of fractional order systems for the first time. An adaptive iterative learning control(AILC) scheme is presented for a class of commens...This paper explores the adaptive iterative learning control method in the control of fractional order systems for the first time. An adaptive iterative learning control(AILC) scheme is presented for a class of commensurate high-order uncertain nonlinear fractional order systems in the presence of disturbance.To facilitate the controller design, a sliding mode surface of tracking errors is designed by using sufficient conditions of linear fractional order systems. To relax the assumption of the identical initial condition in iterative learning control(ILC), a new boundary layer function is proposed by employing MittagLeffler function. The uncertainty in the system is compensated for by utilizing radial basis function neural network. Fractional order differential type updating laws and difference type learning law are designed to estimate unknown constant parameters and time-varying parameter, respectively. The hyperbolic tangent function and a convergent series sequence are used to design robust control term for neural network approximation error and bounded disturbance, simultaneously guaranteeing the learning convergence along iteration. The system output is proved to converge to a small neighborhood of the desired trajectory by constructing Lyapnov-like composite energy function(CEF)containing new integral type Lyapunov function, while keeping all the closed-loop signals bounded. Finally, a simulation example is presented to verify the effectiveness of the proposed approach.展开更多
In the area of computer vision, deep learning has produced a variety of state-of-the-art models that rely on massive labeled data. However, collecting and annotating images from the real world is too demanding in term...In the area of computer vision, deep learning has produced a variety of state-of-the-art models that rely on massive labeled data. However, collecting and annotating images from the real world is too demanding in terms of labor and money investments, and is usually inflexible to build datasets with specific characteristics, such as small area of objects and high occlusion level. Under the framework of Parallel Vision, this paper presents a purposeful way to design artificial scenes and automatically generate virtual images with precise annotations.A virtual dataset named Parallel Eye is built, which can be used for several computer vision tasks. Then, by training the DPM(Deformable parts model) and Faster R-CNN detectors, we prove that the performance of models can be significantly improved by combining Parallel Eye with publicly available real-world datasets during the training phase. In addition, we investigate the potential of testing the trained models from a specific aspect using intentionally designed virtual datasets, in order to discover the flaws of trained models. From the experimental results, we conclude that our virtual dataset is viable to train and test the object detectors.展开更多
The purpose of this paper is to solve the problem of robust face recognition(FR) with single sample per person(SSPP). In the scenario of FR with SSPP, we present a novel model local robust sparse representation(LRSR) ...The purpose of this paper is to solve the problem of robust face recognition(FR) with single sample per person(SSPP). In the scenario of FR with SSPP, we present a novel model local robust sparse representation(LRSR) to tackle the problem of query images with various intra-class variations,e.g., expressions, illuminations, and occlusion. FR with SSPP is a very difficult challenge due to lacking of information to predict the possible intra-class variation of the query images.The key idea of the proposed method is to combine a local sparse representation model and a patch-based generic variation dictionary learning model to predict the possible facial intraclass variation of the query images. The experimental results on the AR database, Extended Yale B database, CMU-PIE database and LFW database show that the proposed method is robust to intra-class variations in FR with SSPP, and outperforms the state-of-art approaches.展开更多
The appearance and wide use of memory hardware bring significant changes to the conventional vertical memory hierarchy that fails to handle contentions for shared hardware resources and expensive data movements.To dea...The appearance and wide use of memory hardware bring significant changes to the conventional vertical memory hierarchy that fails to handle contentions for shared hardware resources and expensive data movements.To deal with these problems,existing schemes have to rely on inefficient scheduling strategies that also cause extra temporal,spatial and bandwidth overheads.Based on the insights that the shared hardware resources trend to be uniformly and hierarchically offered to the requests for co-located applications in memory systems,we present an efficient abstraction of memory hierarchies,called Label,which is used to establish the connection between the application layer and underlying hardware layer.Based on labels,our paper proposes LaMem,a labeled,resource-isolated and cross-tiered memory system by leveraging the way-based partitioning technique for shared resources to guarantee QoS demands of applications,while supporting fast and low-overhead cache repartitioning technique.Besides,we customize LaMem for the learned index that fundamentally replaces storage structures with computation models as a case study to verify the applicability of LaMem.Experimental results demonstrate the efficiency and efficacy of LaMem.展开更多
Smart grids are the developmental trend of power systems and they have attracted much attention all over the world.Due to their complexities,and the uncertainty of the smart grid and high volume of information being c...Smart grids are the developmental trend of power systems and they have attracted much attention all over the world.Due to their complexities,and the uncertainty of the smart grid and high volume of information being collected,artificial intelligence techniques represent some of the enabling technologies for its future development and success.Owing to the decreasing cost of computing power,the profusion of data,and better algorithms,AI has entered into its new develop-mental stage and AI 2.0 is developing rapidly.Deep learning(DL),reinforcement learning(RL)and their combination-deep reinforcement learning(DRL)are representative methods and relatively mature methods in the family of AI 2.0.This article introduces the concept and status quo of the above three methods,summarizes their potential for application in smart grids,and provides an overview of the research work on their application in smart grids.展开更多
The recently proposed learned index has higher query performance and space efficiency than the conventional B+-tree.However,the original learned index has the problems of insertion failure and unbounded query complexi...The recently proposed learned index has higher query performance and space efficiency than the conventional B+-tree.However,the original learned index has the problems of insertion failure and unbounded query complexity,meaning that it supports neither insertions nor bounded query complexity.Some variants of the learned index use an out-of-place strategy and a bottom-up build strategy to accelerate insertions and support bounded query complexity,but introduce additional query costs and frequent node splitting operations.Moreover,none of the existing learned indices are cache-friendly.In this paper,aiming to not only support efficient queries and insertions but also offer bounded query complexity,we propose a new learned index called COLIN(Cache-cOnscious Learned INdex).Unlike previous solutions using an out-of-place strategy,COLIN adopts an in-place approach to support insertions and reserves some empty slots in a node to optimize the node’s data placement.In particular,through model-based data placement and cache-conscious data layout,COLIN decouples the local-search boundary from the maximum error of the model.The experimental results on five workloads and three datasets show that COLIN achieves the best read/write performance among all compared indices and outperforms the second best index by 18.4%,6.2%,and 32.9%on the three datasets,respectively.展开更多
We propose an approach to underpin interactive visual exploration of large data volumes by training Learned Visualization Index(LVI).Knowing in advance the data,the aggregation functions that are used for visualizatio...We propose an approach to underpin interactive visual exploration of large data volumes by training Learned Visualization Index(LVI).Knowing in advance the data,the aggregation functions that are used for visualization,the visual encoding,and available interactive operations for data selection,LVI allows to avoid time-consuming data retrieval and processing of raw data in response to user’s interactions.Instead,LVI directly predicts aggregates of interest for the user’s data selection.We demonstrate the efficiency of the proposed approach in application to two use cases of spatio-temporal data at different scales.展开更多
基金supported by the National Natural Science Foundation of China(60674090)Shandong Natural Science Foundation(ZR2017QF016)
文摘This paper explores the adaptive iterative learning control method in the control of fractional order systems for the first time. An adaptive iterative learning control(AILC) scheme is presented for a class of commensurate high-order uncertain nonlinear fractional order systems in the presence of disturbance.To facilitate the controller design, a sliding mode surface of tracking errors is designed by using sufficient conditions of linear fractional order systems. To relax the assumption of the identical initial condition in iterative learning control(ILC), a new boundary layer function is proposed by employing MittagLeffler function. The uncertainty in the system is compensated for by utilizing radial basis function neural network. Fractional order differential type updating laws and difference type learning law are designed to estimate unknown constant parameters and time-varying parameter, respectively. The hyperbolic tangent function and a convergent series sequence are used to design robust control term for neural network approximation error and bounded disturbance, simultaneously guaranteeing the learning convergence along iteration. The system output is proved to converge to a small neighborhood of the desired trajectory by constructing Lyapnov-like composite energy function(CEF)containing new integral type Lyapunov function, while keeping all the closed-loop signals bounded. Finally, a simulation example is presented to verify the effectiveness of the proposed approach.
基金supported by the National Natural Science Foundation of China(61533019,71232006)
文摘In the area of computer vision, deep learning has produced a variety of state-of-the-art models that rely on massive labeled data. However, collecting and annotating images from the real world is too demanding in terms of labor and money investments, and is usually inflexible to build datasets with specific characteristics, such as small area of objects and high occlusion level. Under the framework of Parallel Vision, this paper presents a purposeful way to design artificial scenes and automatically generate virtual images with precise annotations.A virtual dataset named Parallel Eye is built, which can be used for several computer vision tasks. Then, by training the DPM(Deformable parts model) and Faster R-CNN detectors, we prove that the performance of models can be significantly improved by combining Parallel Eye with publicly available real-world datasets during the training phase. In addition, we investigate the potential of testing the trained models from a specific aspect using intentionally designed virtual datasets, in order to discover the flaws of trained models. From the experimental results, we conclude that our virtual dataset is viable to train and test the object detectors.
基金supported in part by the National Natural Science Foundation of China(61673402,61273270,60802069)the Natural Science Foundation of Guangdong Province(2017A030311029,2016B010109002,2015B090912001,2016B010123005,2017B090909005)+1 种基金the Science and Technology Program of Guangzhou of China(201704020180,201604020024)the Fundamental Research Funds for the Central Universities of China
文摘The purpose of this paper is to solve the problem of robust face recognition(FR) with single sample per person(SSPP). In the scenario of FR with SSPP, we present a novel model local robust sparse representation(LRSR) to tackle the problem of query images with various intra-class variations,e.g., expressions, illuminations, and occlusion. FR with SSPP is a very difficult challenge due to lacking of information to predict the possible intra-class variation of the query images.The key idea of the proposed method is to combine a local sparse representation model and a patch-based generic variation dictionary learning model to predict the possible facial intraclass variation of the query images. The experimental results on the AR database, Extended Yale B database, CMU-PIE database and LFW database show that the proposed method is robust to intra-class variations in FR with SSPP, and outperforms the state-of-art approaches.
基金supported in part by National Natural Science Foundation of China(62125202).
文摘The appearance and wide use of memory hardware bring significant changes to the conventional vertical memory hierarchy that fails to handle contentions for shared hardware resources and expensive data movements.To deal with these problems,existing schemes have to rely on inefficient scheduling strategies that also cause extra temporal,spatial and bandwidth overheads.Based on the insights that the shared hardware resources trend to be uniformly and hierarchically offered to the requests for co-located applications in memory systems,we present an efficient abstraction of memory hierarchies,called Label,which is used to establish the connection between the application layer and underlying hardware layer.Based on labels,our paper proposes LaMem,a labeled,resource-isolated and cross-tiered memory system by leveraging the way-based partitioning technique for shared resources to guarantee QoS demands of applications,while supporting fast and low-overhead cache repartitioning technique.Besides,we customize LaMem for the learned index that fundamentally replaces storage structures with computation models as a case study to verify the applicability of LaMem.Experimental results demonstrate the efficiency and efficacy of LaMem.
文摘Smart grids are the developmental trend of power systems and they have attracted much attention all over the world.Due to their complexities,and the uncertainty of the smart grid and high volume of information being collected,artificial intelligence techniques represent some of the enabling technologies for its future development and success.Owing to the decreasing cost of computing power,the profusion of data,and better algorithms,AI has entered into its new develop-mental stage and AI 2.0 is developing rapidly.Deep learning(DL),reinforcement learning(RL)and their combination-deep reinforcement learning(DRL)are representative methods and relatively mature methods in the family of AI 2.0.This article introduces the concept and status quo of the above three methods,summarizes their potential for application in smart grids,and provides an overview of the research work on their application in smart grids.
基金the National Natural Science Foundation of China under Grant No.62072419the Huawei-USTC Joint Innovation Project on Fundamental System Software。
文摘The recently proposed learned index has higher query performance and space efficiency than the conventional B+-tree.However,the original learned index has the problems of insertion failure and unbounded query complexity,meaning that it supports neither insertions nor bounded query complexity.Some variants of the learned index use an out-of-place strategy and a bottom-up build strategy to accelerate insertions and support bounded query complexity,but introduce additional query costs and frequent node splitting operations.Moreover,none of the existing learned indices are cache-friendly.In this paper,aiming to not only support efficient queries and insertions but also offer bounded query complexity,we propose a new learned index called COLIN(Cache-cOnscious Learned INdex).Unlike previous solutions using an out-of-place strategy,COLIN adopts an in-place approach to support insertions and reserves some empty slots in a node to optimize the node’s data placement.In particular,through model-based data placement and cache-conscious data layout,COLIN decouples the local-search boundary from the maximum error of the model.The experimental results on five workloads and three datasets show that COLIN achieves the best read/write performance among all compared indices and outperforms the second best index by 18.4%,6.2%,and 32.9%on the three datasets,respectively.
基金National Key R&D Program of China(2018YFC0831700)NSFC project(61972278)+1 种基金Natural Science Foundation of Tianjin(20JCQNJC01620)the Browser Project(CEIEC-2020-ZM02-0132).
文摘We propose an approach to underpin interactive visual exploration of large data volumes by training Learned Visualization Index(LVI).Knowing in advance the data,the aggregation functions that are used for visualization,the visual encoding,and available interactive operations for data selection,LVI allows to avoid time-consuming data retrieval and processing of raw data in response to user’s interactions.Instead,LVI directly predicts aggregates of interest for the user’s data selection.We demonstrate the efficiency of the proposed approach in application to two use cases of spatio-temporal data at different scales.
