How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classif...How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classification due to the powerful feature representation ability and better performance. However,the training and testing of CNN mainly rely on single machine.Single machine has its natural limitation and bottleneck in processing RSIs due to limited hardware resources and huge time consuming. Besides, overfitting is a challenge for the CNN model due to the unbalance between RSIs data and the model structure.When a model is complex or the training data is relatively small,overfitting occurs and leads to a poor predictive performance. To address these problems, a distributed CNN architecture for RSIs target classification is proposed, which dramatically increases the training speed of CNN and system scalability. It improves the storage ability and processing efficiency of RSIs. Furthermore,Bayesian regularization approach is utilized in order to initialize the weights of the CNN extractor, which increases the robustness and flexibility of the CNN model. It helps prevent the overfitting and avoid the local optima caused by limited RSI training images or the inappropriate CNN structure. In addition, considering the efficiency of the Na¨?ve Bayes classifier, a distributed Na¨?ve Bayes classifier is designed to reduce the training cost. Compared with other algorithms, the proposed system and method perform the best and increase the recognition accuracy. The results show that the distributed system framework and the proposed algorithms are suitable for RSIs target classification tasks.展开更多
Build a general software development platform for industrial process supervisor and management system by combining the technology of industrial configuration and Client/Server model, and introduce the architecture and...Build a general software development platform for industrial process supervisor and management system by combining the technology of industrial configuration and Client/Server model, and introduce the architecture and topological application of this platform. It puts forward a solution to the real time problem in the industrial distributed supervisor system.展开更多
With the evolution of application system, there are t wo different system architectures. One is the traditional application system suc h as MIS and Business Software. Along with its extension, the traditional applic a...With the evolution of application system, there are t wo different system architectures. One is the traditional application system suc h as MIS and Business Software. Along with its extension, the traditional applic ation system transforms from file-based structure to C/S and then CSS model. At the same time, following the prevalence of Internet/Intranet, Web application s ystem based on browser comes into being. In early time, Web application only pro vided functions of looking over or querying static data on browser. But with the development of Internet/Intranet widely, it’s expected that more and more trad itional applications can be performed on browser, or even E-Business trades and other complicated application systems such as MIS, ERP and CRM and so on. In or der to satisfy both traditional application and Web application, reduce the cost of developing system repeatedly, increase the repeated use of application syste m and take advantage of the functions of OOA/OOD sufficiently, a new distributed architecture structure (system solution based on repeated components) comes for th. In this article, this distributed architecture structure will be discuss ed in detail. Firstly, the evolution of traditional application system and Web application sys tem will be talked over, especially the advantages and disadvantages of these tw o architectures. Secondly, the distributed architecture (system solution based o n repeated components) will be described particular. Several prevalent technolog y of component, such as COM+, CORBA and EJB, will also be illustrate d in this part. Thirdly, the practice of the technology of repeated component wi ll be discussed by analysing and designing the management system of Science & Te chnology Articles. Lastly, the latest distributed techonlogy of E-business(Web service based on xml/soap) will be discussed. In the end, Based on summing-up o f the distributed technology of E-Business, the future distributed tenchnology of E-Business will be expected.展开更多
基金supported by the National Natural Science Foundation of China(U1435220)
文摘How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classification due to the powerful feature representation ability and better performance. However,the training and testing of CNN mainly rely on single machine.Single machine has its natural limitation and bottleneck in processing RSIs due to limited hardware resources and huge time consuming. Besides, overfitting is a challenge for the CNN model due to the unbalance between RSIs data and the model structure.When a model is complex or the training data is relatively small,overfitting occurs and leads to a poor predictive performance. To address these problems, a distributed CNN architecture for RSIs target classification is proposed, which dramatically increases the training speed of CNN and system scalability. It improves the storage ability and processing efficiency of RSIs. Furthermore,Bayesian regularization approach is utilized in order to initialize the weights of the CNN extractor, which increases the robustness and flexibility of the CNN model. It helps prevent the overfitting and avoid the local optima caused by limited RSI training images or the inappropriate CNN structure. In addition, considering the efficiency of the Na¨?ve Bayes classifier, a distributed Na¨?ve Bayes classifier is designed to reduce the training cost. Compared with other algorithms, the proposed system and method perform the best and increase the recognition accuracy. The results show that the distributed system framework and the proposed algorithms are suitable for RSIs target classification tasks.
基金The Natural Science Foundation of Hunan Province!(No.96 10 1 3 0 )
文摘Build a general software development platform for industrial process supervisor and management system by combining the technology of industrial configuration and Client/Server model, and introduce the architecture and topological application of this platform. It puts forward a solution to the real time problem in the industrial distributed supervisor system.
文摘With the evolution of application system, there are t wo different system architectures. One is the traditional application system suc h as MIS and Business Software. Along with its extension, the traditional applic ation system transforms from file-based structure to C/S and then CSS model. At the same time, following the prevalence of Internet/Intranet, Web application s ystem based on browser comes into being. In early time, Web application only pro vided functions of looking over or querying static data on browser. But with the development of Internet/Intranet widely, it’s expected that more and more trad itional applications can be performed on browser, or even E-Business trades and other complicated application systems such as MIS, ERP and CRM and so on. In or der to satisfy both traditional application and Web application, reduce the cost of developing system repeatedly, increase the repeated use of application syste m and take advantage of the functions of OOA/OOD sufficiently, a new distributed architecture structure (system solution based on repeated components) comes for th. In this article, this distributed architecture structure will be discuss ed in detail. Firstly, the evolution of traditional application system and Web application sys tem will be talked over, especially the advantages and disadvantages of these tw o architectures. Secondly, the distributed architecture (system solution based o n repeated components) will be described particular. Several prevalent technolog y of component, such as COM+, CORBA and EJB, will also be illustrate d in this part. Thirdly, the practice of the technology of repeated component wi ll be discussed by analysing and designing the management system of Science & Te chnology Articles. Lastly, the latest distributed techonlogy of E-business(Web service based on xml/soap) will be discussed. In the end, Based on summing-up o f the distributed technology of E-Business, the future distributed tenchnology of E-Business will be expected.
