[Objective] To analyze the key factor in agricultural technology diffusion- technology support, and to explore the method to quicken the diffusion of agricultural technology. [Method] The technology acquisition advant...[Objective] To analyze the key factor in agricultural technology diffusion- technology support, and to explore the method to quicken the diffusion of agricultural technology. [Method] The technology acquisition advantage of social network was il- lustrated by summarizing the status and characteristics of agricultural technology and technology supporting types in the process of agriculture technology diffusion. [Result] The multi-layer, complex, persistence, systematization features of agricultural technol- ogy require support and help of technology from surrounding social network to ulti- mately internalize the technology. [Conclusion] Using social networks for the technol- ogy support will be a powerful supplement to the system of agricultural technology diffusion.展开更多
The threat of malware in wireless sensor network has stimulated some activities to model and analyze the malware prevalence.To understand the dynamics of malware propagation in wireless sensor network,we propose a nov...The threat of malware in wireless sensor network has stimulated some activities to model and analyze the malware prevalence.To understand the dynamics of malware propagation in wireless sensor network,we propose a novel epidemic model named as e-SEIR(susceptible-exposed-infectious-recovered)model,which is a set of delayed differential equations,in this paper.The model has taken into account the following two factors:1 Multi-state antivirus measures;2 Temporary immune period.Then,the stability and Hopf bifurcation at the equilibria of linearized model are carefully analyzed by considering the distribution of eigenvalues of characteristic equations.Both mathematical analysis and numerical simulations show that the dynamical features of the proposed model rely on the basic reproduction number R0 and time delayτ.This novel model can help us to better understand and predict the propagation behaviors of malware in wireless sensor networks.展开更多
To cope with the constraint problem of power consumption and transmission delay in the virtual backbone of wireless sensor network, a distributed connected dominating set （CDS） algorithm with （α,β）-constraints i...To cope with the constraint problem of power consumption and transmission delay in the virtual backbone of wireless sensor network, a distributed connected dominating set （CDS） algorithm with （α,β）-constraints is proposed. Based on the （α, β）-tree concept, a new connected dominating tree with bounded transmission delay problem（CDTT） is defined and a corresponding algorithm is designed to construct a CDT-tree which can trade off limited total power and bounded transmission delay from source to destination nodes. The CDT algorithm consists of two phases： The first phase constructs a maximum independent set（MIS）in a unit disk graph model. The second phase estimates the distance and calculates the transmission power to construct a spanning tree in an undirected graph with different weights for MST and SPF, respectively. The theoretical analysis and simulation results show that the CDT algorithm gives a correct solution to the CDTF problem and forms a virtual backbone with（ α,β）-constraints balancing the requirements of power consumption and transmission delay.展开更多
A novel adaptive support vector regression neural network （SVR-NN） is proposed, which combines respectively merits of support vector machines and a neural network. First, a support vector regression approach is appl...A novel adaptive support vector regression neural network （SVR-NN） is proposed, which combines respectively merits of support vector machines and a neural network. First, a support vector regression approach is applied to determine the initial structure and initial weights of the SVR-NN so that the network architecture is easily determined and the hidden nodes can adaptively be constructed based on support vectors. Furthermore, an annealing robust learning algorithm is presented to adjust these hidden node parameters as well as the weights of the SVR-NN. To test the validity of the proposed method, it is demonstrated that the adaptive SVR-NN can be used effectively for the identification of nonlinear dynamic systems. Simulation results show that the identification schemes based on the SVR-NN give considerably better performance and show faster learning in comparison to the previous neural network method.展开更多
Effective fault detection techniques can help flotation plant reduce reagents consumption,increase mineral recovery,and reduce labor intensity.Traditional,online fault detection methods during flotation processes have...Effective fault detection techniques can help flotation plant reduce reagents consumption,increase mineral recovery,and reduce labor intensity.Traditional,online fault detection methods during flotation processes have concentrated on extracting a specific froth feature for segmentation,like color,shape,size and texture,always leading to undesirable accuracy and efficiency since the same segmentation algorithm could not be applied to every case.In this work,a new integrated method based on convolution neural network(CNN)combined with transfer learning approach and support vector machine(SVM)is proposed to automatically recognize the flotation condition.To be more specific,CNN function as a trainable feature extractor to process the froth images and SVM is used as a recognizer to implement fault detection.As compared with the existed recognition methods,it turns out that the CNN-SVM model can automatically retrieve features from the raw froth images and perform fault detection with high accuracy.Hence,a CNN-SVM based,real-time flotation monitoring system is proposed for application in an antimony flotation plant in China.展开更多
基金Supported by the National Social Science Foundation of China:the Sociological Study on the Technology Adoption Behaviors of Farmers(08BSH049)~~
文摘[Objective] To analyze the key factor in agricultural technology diffusion- technology support, and to explore the method to quicken the diffusion of agricultural technology. [Method] The technology acquisition advantage of social network was il- lustrated by summarizing the status and characteristics of agricultural technology and technology supporting types in the process of agriculture technology diffusion. [Result] The multi-layer, complex, persistence, systematization features of agricultural technol- ogy require support and help of technology from surrounding social network to ulti- mately internalize the technology. [Conclusion] Using social networks for the technol- ogy support will be a powerful supplement to the system of agricultural technology diffusion.
基金National Natural Science Foundation of China(No.61379125)
文摘The threat of malware in wireless sensor network has stimulated some activities to model and analyze the malware prevalence.To understand the dynamics of malware propagation in wireless sensor network,we propose a novel epidemic model named as e-SEIR(susceptible-exposed-infectious-recovered)model,which is a set of delayed differential equations,in this paper.The model has taken into account the following two factors:1 Multi-state antivirus measures;2 Temporary immune period.Then,the stability and Hopf bifurcation at the equilibria of linearized model are carefully analyzed by considering the distribution of eigenvalues of characteristic equations.Both mathematical analysis and numerical simulations show that the dynamical features of the proposed model rely on the basic reproduction number R0 and time delayτ.This novel model can help us to better understand and predict the propagation behaviors of malware in wireless sensor networks.
基金Major Program of the National Natural Science Foundation of China (No.70533050)High Technology Research Program ofJiangsu Province(No.BG2007012)+1 种基金China Postdoctoral Science Foundation(No.20070411065)Science Foundation of China University of Mining andTechnology(No.OC080303)
文摘To cope with the constraint problem of power consumption and transmission delay in the virtual backbone of wireless sensor network, a distributed connected dominating set （CDS） algorithm with （α,β）-constraints is proposed. Based on the （α, β）-tree concept, a new connected dominating tree with bounded transmission delay problem（CDTT） is defined and a corresponding algorithm is designed to construct a CDT-tree which can trade off limited total power and bounded transmission delay from source to destination nodes. The CDT algorithm consists of two phases： The first phase constructs a maximum independent set（MIS）in a unit disk graph model. The second phase estimates the distance and calculates the transmission power to construct a spanning tree in an undirected graph with different weights for MST and SPF, respectively. The theoretical analysis and simulation results show that the CDT algorithm gives a correct solution to the CDTF problem and forms a virtual backbone with（ α,β）-constraints balancing the requirements of power consumption and transmission delay.
文摘A novel adaptive support vector regression neural network （SVR-NN） is proposed, which combines respectively merits of support vector machines and a neural network. First, a support vector regression approach is applied to determine the initial structure and initial weights of the SVR-NN so that the network architecture is easily determined and the hidden nodes can adaptively be constructed based on support vectors. Furthermore, an annealing robust learning algorithm is presented to adjust these hidden node parameters as well as the weights of the SVR-NN. To test the validity of the proposed method, it is demonstrated that the adaptive SVR-NN can be used effectively for the identification of nonlinear dynamic systems. Simulation results show that the identification schemes based on the SVR-NN give considerably better performance and show faster learning in comparison to the previous neural network method.
基金Projects(61621062,61563015)supported by the National Natural Science Foundation of ChinaProject(2016zzts056)supported by the Central South University Graduate Independent Exploration Innovation Program,China
文摘Effective fault detection techniques can help flotation plant reduce reagents consumption,increase mineral recovery,and reduce labor intensity.Traditional,online fault detection methods during flotation processes have concentrated on extracting a specific froth feature for segmentation,like color,shape,size and texture,always leading to undesirable accuracy and efficiency since the same segmentation algorithm could not be applied to every case.In this work,a new integrated method based on convolution neural network(CNN)combined with transfer learning approach and support vector machine(SVM)is proposed to automatically recognize the flotation condition.To be more specific,CNN function as a trainable feature extractor to process the froth images and SVM is used as a recognizer to implement fault detection.As compared with the existed recognition methods,it turns out that the CNN-SVM model can automatically retrieve features from the raw froth images and perform fault detection with high accuracy.Hence,a CNN-SVM based,real-time flotation monitoring system is proposed for application in an antimony flotation plant in China.
