The conventional X-ray gray weighted image fusion method based on variable energy cannot characterize the phys- ical properties of complicated objects correctly, therefore, the gray correction method of X-ray fusion i...The conventional X-ray gray weighted image fusion method based on variable energy cannot characterize the phys- ical properties of complicated objects correctly, therefore, the gray correction method of X-ray fusion image based on neural network is proposed. The conventional method acquires 12 bit images on variable energy, and then fuses the images in a tra- ditional way. While the new method takes the fusion image as the input of neural network simulation system and takes the acquired 16 bit image as the output of neural network. The X-ray image physical characteristic model based on neural net- work is obtained through training. And then it takes steel ladder block as the test object to verify the feasibility of the mod- el. In the end, the gray curve of output image is compared with the gray curve of 16 bit real image. The experiment results show that this method can fit the nonlinear relationship between the fusion image and the real image, and also can expand the scope of application of low dynamic image acquisition equipment.展开更多
In this study, a Multi-Layer BP neural network(MLBP) with dynamic thresholds is employed to build a classifier model.As to the design of the neural network structure, theoretical guidance and plentiful experiments are...In this study, a Multi-Layer BP neural network(MLBP) with dynamic thresholds is employed to build a classifier model.As to the design of the neural network structure, theoretical guidance and plentiful experiments are combined to optimize the hidden layers' parameters which include the number of hidden layers and their node numbers.The classifier with dynamic thresholds is used to standardize the output for the first time, and it improves the robustness of the model to a high level.Finally, the classifier is applied to forecast box office revenue of a movie before its theatrical release.The comparison results with the MLP method show that the MLBP classifier model achieves more satisfactory results, and it is more reliable and effective to solve the problem.展开更多
As a key technology to realize smart services of Internet of Things(IoT), network virtualization technology can support the network diversification and ubiquity, and improve the utilization rate of network resources...As a key technology to realize smart services of Internet of Things(IoT), network virtualization technology can support the network diversification and ubiquity, and improve the utilization rate of network resources. This paper studies the service-ori- ented network virtualization architecture for loT services. Firstly the semantic description method for loT services is proposed, then the resource representation model and resource management model in the environment of network virtualization are presented. Based on the above models, the service-oriented virtual network architecture for loT is established. Finally, a smart campus system is designed and deployed based on the service-oriented virtual network architecture. Moreover, the proposed architecture and models are verified in experiments.展开更多
Based on an integrate-and-fire mechanism, we investigate self-organized criticality of a simple neuron model on a modified BA scale-free network with aging nodes. In our model, we find that the distribution of avalanc...Based on an integrate-and-fire mechanism, we investigate self-organized criticality of a simple neuron model on a modified BA scale-free network with aging nodes. In our model, we find that the distribution of avalanche size follows power-law behavior. The critical exponent τ depends on the aging exponent α. The structures of the network with aging of nodes change with an increase of α. The different topological structures lead to different behaviors in models of integrate-and-fire neurons.展开更多
In order to analyze the influence rule of experimental parameters on the energy-absorption characteristics and effectively forecast energy-absorption characteristic of thin-walled structure, the forecast model of GA-B...In order to analyze the influence rule of experimental parameters on the energy-absorption characteristics and effectively forecast energy-absorption characteristic of thin-walled structure, the forecast model of GA-BP hybrid algorithm was presented by uniting respective applicability of back-propagation artificial neural network (BP-ANN) and genetic algorithm (GA). The detailed process was as follows. Firstly, the GA trained the best weights and thresholds as the initial values of BP-ANN to initialize the neural network. Then, the BP-ANN after initialization was trained until the errors converged to the required precision. Finally, the network model, which met the requirements after being examined by the test samples, was applied to energy-absorption forecast of thin-walled cylindrical structure impacting. After example analysis, the GA-BP network model was trained until getting the desired network error only by 46 steps, while the single BP-ANN model achieved the same network error by 992 steps, which obviously shows that the GA-BP hybrid algorithm has faster convergence rate. The average relative forecast error (ARE) of the SEA predictive results obtained by GA-BP hybrid algorithm is 1.543%, while the ARE of the SEA predictive results obtained by BP-ANN is 2.950%, which clearly indicates that the forecast precision of the GA-BP hybrid algorithm is higher than that of the BP-ANN.展开更多
The effects of blend composition and micro-phase structure on the mechanical behavior of A/B polymer blend film are studied by coupling the Monte Carlo(MC) simulation of morphology with the lattice spring model(LSM) o...The effects of blend composition and micro-phase structure on the mechanical behavior of A/B polymer blend film are studied by coupling the Monte Carlo(MC) simulation of morphology with the lattice spring model(LSM) of micro mechanics of materials.The MC method with bond length fluctuation and cavity diffusion algorithm on cubic lattice is adopted to simulate the micro-phase structure of A/B polymer blend.The information of morphology and structure is then inputted to the LSM composed of a three-dimensional network of springs to obtain the mechanical properties of polymer blend film.Simulated results show that the mechanical response is mainly affected by the density and the composition of polymer blend film through the morphology transition.When a force is applied on the outer boundary of polymer blend film,the vicinity of the inner cavities experiences higher stresses and strains responsible for the onset of crack propagation and the premature failure of the entire system.展开更多
In the past decades, many cleanslate future network architectures have gained limited deployment in current Internet, due to the stability and rigidity of TCP/IP, the narrow waist of the Internet. We first propose thr...In the past decades, many cleanslate future network architectures have gained limited deployment in current Internet, due to the stability and rigidity of TCP/IP, the narrow waist of the Internet. We first propose three principles that the future Internet architecture should obey to be well-defined network architecture, i.e. supporting service innovation and enabling evolvability. By abstracting different modes from TCP/IP network and SDN technology, we argue that the centric-distributed-centric(CDC) mode has great potential for the well-defined future network architecture in which diverse network architectures could be incrementally deployed and coexist with each other. Prototype system regulated by CDC mode was developed. Experimental results reveal that CDC can support diverse architectures to coexist in the current Internet and thus enables the Internet to evolve.展开更多
Due to the enormous harm of virus propagation,research regarding virus immunizations still absolutely necessary.In comparison to current researches,a new virus immunization method the hierarchical virus immunization m...Due to the enormous harm of virus propagation,research regarding virus immunizations still absolutely necessary.In comparison to current researches,a new virus immunization method the hierarchical virus immunization method(HVIM) for community networks is proposed.Based on the virus transmission dynamic model SusceptibleInfectious-Removed and SusceptibleRemoved(SIRSR),HVIM considered the influence of external factors on the spread of viruses and only needs a portion of the network structure to be able to carry out immunization.Another pro for HVIM is that it is scalable and suitable for parallel computing which is a requirement in the big data era.Finally,a simulation dataset and a real dataset were used to run experiments,and the results of simulation showed that HVIM obviously is superior to others on the aspect of immunity.展开更多
In view of the problems of multi-scale changes of segmentation targets,noise interference,rough segmentation results and slow training process faced by medical image semantic segmentation,a multi-scale residual aggreg...In view of the problems of multi-scale changes of segmentation targets,noise interference,rough segmentation results and slow training process faced by medical image semantic segmentation,a multi-scale residual aggregation U-shaped attention network structure of MAAUNet(MultiRes aggregation attention UNet)is proposed based on MultiResUNet.Firstly,aggregate connection is introduced from the original feature aggregation at the same level.Skip connection is redesigned to aggregate features of different semantic scales at the decoder subnet,and the problem of semantic gaps is further solved that may exist between skip connections.Secondly,after the multi-scale convolution module,a convolution block attention module is added to focus and integrate features in the two attention directions of channel and space to adaptively optimize the intermediate feature map.Finally,the original convolution block is improved.The convolution channels are expanded with a series convolution structure to complement each other and extract richer spatial features.Residual connections are retained and the convolution block is turned into a multi-channel convolution block.The model is made to extract multi-scale spatial features.The experimental results show that MAAUNet has strong competitiveness in challenging datasets,and shows good segmentation performance and stability in dealing with multi-scale input and noise interference.展开更多
基金National Natural Science Foundation of China(No.61302159,61227003,61301259)Natural Science Foundation of Shanxi Province(No.2012021011-2)+2 种基金Specialized Research Fund for the Doctoral Program of Higher Education,China(No.20121420110006)Top Science and Technology Innovation Teams of Higher Learning Institutions of Shanxi Province,ChinaProject Sponsored by Scientific Research for the Returned Overseas Chinese Scholars,Shanxi Province(No.2013-083)
文摘The conventional X-ray gray weighted image fusion method based on variable energy cannot characterize the phys- ical properties of complicated objects correctly, therefore, the gray correction method of X-ray fusion image based on neural network is proposed. The conventional method acquires 12 bit images on variable energy, and then fuses the images in a tra- ditional way. While the new method takes the fusion image as the input of neural network simulation system and takes the acquired 16 bit image as the output of neural network. The X-ray image physical characteristic model based on neural net- work is obtained through training. And then it takes steel ladder block as the test object to verify the feasibility of the mod- el. In the end, the gray curve of output image is compared with the gray curve of 16 bit real image. The experiment results show that this method can fit the nonlinear relationship between the fusion image and the real image, and also can expand the scope of application of low dynamic image acquisition equipment.
基金Supported by National Natural Science Foundation of China (No. 60573172)
文摘In this study, a Multi-Layer BP neural network(MLBP) with dynamic thresholds is employed to build a classifier model.As to the design of the neural network structure, theoretical guidance and plentiful experiments are combined to optimize the hidden layers' parameters which include the number of hidden layers and their node numbers.The classifier with dynamic thresholds is used to standardize the output for the first time, and it improves the robustness of the model to a high level.Finally, the classifier is applied to forecast box office revenue of a movie before its theatrical release.The comparison results with the MLP method show that the MLBP classifier model achieves more satisfactory results, and it is more reliable and effective to solve the problem.
基金supported by the national 973 project of China under Grants 2013CB329104the Natural Science Foundation of China under Grants 61372124,61427801,61271237,61271236Jiangsu Collaborative Innovation Center for Technology and Application of Internet of Things under Grants SJ213003
文摘As a key technology to realize smart services of Internet of Things(IoT), network virtualization technology can support the network diversification and ubiquity, and improve the utilization rate of network resources. This paper studies the service-ori- ented network virtualization architecture for loT services. Firstly the semantic description method for loT services is proposed, then the resource representation model and resource management model in the environment of network virtualization are presented. Based on the above models, the service-oriented virtual network architecture for loT is established. Finally, a smart campus system is designed and deployed based on the service-oriented virtual network architecture. Moreover, the proposed architecture and models are verified in experiments.
基金The project supported by National Natural Science Foundation of China under Grant No. 10675060 and the Doctoral Foundation of Ministry of Education of China
文摘Based on an integrate-and-fire mechanism, we investigate self-organized criticality of a simple neuron model on a modified BA scale-free network with aging nodes. In our model, we find that the distribution of avalanche size follows power-law behavior. The critical exponent τ depends on the aging exponent α. The structures of the network with aging of nodes change with an increase of α. The different topological structures lead to different behaviors in models of integrate-and-fire neurons.
基金Project(50175110) supported by the National Natural Science Foundation of ChinaProject(2009bsxt019) supported by the Graduate Degree Thesis Innovation Foundation of Central South University, China
文摘In order to analyze the influence rule of experimental parameters on the energy-absorption characteristics and effectively forecast energy-absorption characteristic of thin-walled structure, the forecast model of GA-BP hybrid algorithm was presented by uniting respective applicability of back-propagation artificial neural network (BP-ANN) and genetic algorithm (GA). The detailed process was as follows. Firstly, the GA trained the best weights and thresholds as the initial values of BP-ANN to initialize the neural network. Then, the BP-ANN after initialization was trained until the errors converged to the required precision. Finally, the network model, which met the requirements after being examined by the test samples, was applied to energy-absorption forecast of thin-walled cylindrical structure impacting. After example analysis, the GA-BP network model was trained until getting the desired network error only by 46 steps, while the single BP-ANN model achieved the same network error by 992 steps, which obviously shows that the GA-BP hybrid algorithm has faster convergence rate. The average relative forecast error (ARE) of the SEA predictive results obtained by GA-BP hybrid algorithm is 1.543%, while the ARE of the SEA predictive results obtained by BP-ANN is 2.950%, which clearly indicates that the forecast precision of the GA-BP hybrid algorithm is higher than that of the BP-ANN.
基金Supported by the National Natural Science Foundation of China (20976044 20736002)
文摘The effects of blend composition and micro-phase structure on the mechanical behavior of A/B polymer blend film are studied by coupling the Monte Carlo(MC) simulation of morphology with the lattice spring model(LSM) of micro mechanics of materials.The MC method with bond length fluctuation and cavity diffusion algorithm on cubic lattice is adopted to simulate the micro-phase structure of A/B polymer blend.The information of morphology and structure is then inputted to the LSM composed of a three-dimensional network of springs to obtain the mechanical properties of polymer blend film.Simulated results show that the mechanical response is mainly affected by the density and the composition of polymer blend film through the morphology transition.When a force is applied on the outer boundary of polymer blend film,the vicinity of the inner cavities experiences higher stresses and strains responsible for the onset of crack propagation and the premature failure of the entire system.
基金supported in part by the National Natural Science Foundation of China under Grant No.61402521Jiangsu Province Natural Science Foundation of China under Grant No.BK20140068the China Post Doctoral Science Foundation under Grant No.2017M610286
文摘In the past decades, many cleanslate future network architectures have gained limited deployment in current Internet, due to the stability and rigidity of TCP/IP, the narrow waist of the Internet. We first propose three principles that the future Internet architecture should obey to be well-defined network architecture, i.e. supporting service innovation and enabling evolvability. By abstracting different modes from TCP/IP network and SDN technology, we argue that the centric-distributed-centric(CDC) mode has great potential for the well-defined future network architecture in which diverse network architectures could be incrementally deployed and coexist with each other. Prototype system regulated by CDC mode was developed. Experimental results reveal that CDC can support diverse architectures to coexist in the current Internet and thus enables the Internet to evolve.
基金supported by China 973 Program (2014CB340600)NSF(60903175,61272405, 61272033,and 61272451)University Innovation Foundation(2013TS102 and 2013TS106)
文摘Due to the enormous harm of virus propagation,research regarding virus immunizations still absolutely necessary.In comparison to current researches,a new virus immunization method the hierarchical virus immunization method(HVIM) for community networks is proposed.Based on the virus transmission dynamic model SusceptibleInfectious-Removed and SusceptibleRemoved(SIRSR),HVIM considered the influence of external factors on the spread of viruses and only needs a portion of the network structure to be able to carry out immunization.Another pro for HVIM is that it is scalable and suitable for parallel computing which is a requirement in the big data era.Finally,a simulation dataset and a real dataset were used to run experiments,and the results of simulation showed that HVIM obviously is superior to others on the aspect of immunity.
基金National Natural Science Foundation of China(No.61806006)Jiangsu University Superior Discipline Construction Project。
文摘In view of the problems of multi-scale changes of segmentation targets,noise interference,rough segmentation results and slow training process faced by medical image semantic segmentation,a multi-scale residual aggregation U-shaped attention network structure of MAAUNet(MultiRes aggregation attention UNet)is proposed based on MultiResUNet.Firstly,aggregate connection is introduced from the original feature aggregation at the same level.Skip connection is redesigned to aggregate features of different semantic scales at the decoder subnet,and the problem of semantic gaps is further solved that may exist between skip connections.Secondly,after the multi-scale convolution module,a convolution block attention module is added to focus and integrate features in the two attention directions of channel and space to adaptively optimize the intermediate feature map.Finally,the original convolution block is improved.The convolution channels are expanded with a series convolution structure to complement each other and extract richer spatial features.Residual connections are retained and the convolution block is turned into a multi-channel convolution block.The model is made to extract multi-scale spatial features.The experimental results show that MAAUNet has strong competitiveness in challenging datasets,and shows good segmentation performance and stability in dealing with multi-scale input and noise interference.