Network virtualization is an enabling technology of running multiple virtual networks on a shared substrate network. It aims to deal with the ossification of current network architecture. As a crucial component of net...Network virtualization is an enabling technology of running multiple virtual networks on a shared substrate network. It aims to deal with the ossification of current network architecture. As a crucial component of network virtualization, virtual network embedding(VNE) can efficiently and effectively allocates the substrate resource to proposed virtual network requests. According to the optimization strategy, VNE approaches can be classified into three categories: exact, heuristic and meta-heuristic solution. The VNE exact solution is the foundation of its corresponding heuristic and meta-heuristic solutions. This paper presents a survey of existing typical VNE exact solutions, and open problems for the future research of VNE exact solutions are proposed.展开更多
In this paper,we propose a systemic architecture of network selection based on context-awareness services,which gathers contextual information that includes such network information,user information and local informat...In this paper,we propose a systemic architecture of network selection based on context-awareness services,which gathers contextual information that includes such network information,user information and local information.This network selection strategy considers the Quality of Service(QoS) and user preferences.Also,it perceives contexts such as speed,coverage percentage and location,etc.,and it eventually performs network selection decision making and network execution based on multiple factors.From the perspective of network decision,it presents two network selection algorithms,namely the fuzzy mathematics evaluation method and multiple attribute decision making using the TOPSIS evaluation method.System simulations suggest that network selection based on the mathematics evaluation method is much faster than the TOPSIS evaluation method.However,the TOPSIS evaluation method is practically more efficient.The network selection method based on context-awareness provides an effective and flexible network vertical handover strategy,and ensures a good accuracy and efficiency.展开更多
A multilayer perceptron neural network system is established to support the diagnosis for five most common heart diseases (coronary heart disease, rheumatic valvular heart disease, hypertension, chronic cor pulmonale ...A multilayer perceptron neural network system is established to support the diagnosis for five most common heart diseases (coronary heart disease, rheumatic valvular heart disease, hypertension, chronic cor pulmonale and congenital heart disease). Momentum term, adaptive learning rate, the forgetting mechanics, and conjugate gradients method are introduced to improve the basic BP algorithm aiming to speed up the convergence of the BP algorithm and enhance the accuracy for diagnosis. A heart disease database consisting of 352 samples is applied to the training and testing courses of the system. The performance of the system is assessed by cross-validation method. It is found that as the basic BP algorithm is improved step by step, the convergence speed and the classification accuracy of the network are enhanced, and the system has great application prospect in supporting heart diseases diagnosis.展开更多
基金supported by the National Basic Research Program of China(973 Program)under Grant 2013CB329104the National Natural Science Foundation of China under Grants 61372124 and 61427801the Key Projects of Natural Science Foundation of Jiangsu University under Grant 11KJA510001
文摘Network virtualization is an enabling technology of running multiple virtual networks on a shared substrate network. It aims to deal with the ossification of current network architecture. As a crucial component of network virtualization, virtual network embedding(VNE) can efficiently and effectively allocates the substrate resource to proposed virtual network requests. According to the optimization strategy, VNE approaches can be classified into three categories: exact, heuristic and meta-heuristic solution. The VNE exact solution is the foundation of its corresponding heuristic and meta-heuristic solutions. This paper presents a survey of existing typical VNE exact solutions, and open problems for the future research of VNE exact solutions are proposed.
基金supported by the National Basic Research Program of China(973 Program)under Grant No.2012CB315805supported by the National Natural Science Foundation of China under Grants No.71172135,No.71231002,No.71201011,No.71271099the Ministry of Education of the People's Republic of China under Grant No.20120005120001
文摘In this paper,we propose a systemic architecture of network selection based on context-awareness services,which gathers contextual information that includes such network information,user information and local information.This network selection strategy considers the Quality of Service(QoS) and user preferences.Also,it perceives contexts such as speed,coverage percentage and location,etc.,and it eventually performs network selection decision making and network execution based on multiple factors.From the perspective of network decision,it presents two network selection algorithms,namely the fuzzy mathematics evaluation method and multiple attribute decision making using the TOPSIS evaluation method.System simulations suggest that network selection based on the mathematics evaluation method is much faster than the TOPSIS evaluation method.However,the TOPSIS evaluation method is practically more efficient.The network selection method based on context-awareness provides an effective and flexible network vertical handover strategy,and ensures a good accuracy and efficiency.
基金the Natural Science Foundation of China (No. 30070211).
文摘A multilayer perceptron neural network system is established to support the diagnosis for five most common heart diseases (coronary heart disease, rheumatic valvular heart disease, hypertension, chronic cor pulmonale and congenital heart disease). Momentum term, adaptive learning rate, the forgetting mechanics, and conjugate gradients method are introduced to improve the basic BP algorithm aiming to speed up the convergence of the BP algorithm and enhance the accuracy for diagnosis. A heart disease database consisting of 352 samples is applied to the training and testing courses of the system. The performance of the system is assessed by cross-validation method. It is found that as the basic BP algorithm is improved step by step, the convergence speed and the classification accuracy of the network are enhanced, and the system has great application prospect in supporting heart diseases diagnosis.
