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
Aim To study the identification and control of nonlinear systems using neural networks. Methods A new type of neural network in which the dynamical error feedback is used to modify the inputs of the network was empl...Aim To study the identification and control of nonlinear systems using neural networks. Methods A new type of neural network in which the dynamical error feedback is used to modify the inputs of the network was employed to reduce the inherent network approximation error. Results A new identification model constructed by the proposed network and stable filters was derived for continuous time nonlinear systems, and a stable adaptive control scheme based on the proposed networks was developed. Conclusion Theory and simulation results show that the modified neural network is feasible to control a class of nonlinear systems.展开更多
We propose a novel approach called adaptive fuzzy ant-based routing (AFAR), where a group of intelligent agents (or ants) builds paths between a pair of nodes, exploring the network concurrently and exchanging obtaine...We propose a novel approach called adaptive fuzzy ant-based routing (AFAR), where a group of intelligent agents (or ants) builds paths between a pair of nodes, exploring the network concurrently and exchanging obtained information to up-date the routing tables. Routing decisions can be made by the fuzzy logic technique based on local information about the current network state and the knowledge constructed by a previous set of behaviors of other agents. The fuzzy logic technique allows multiple constraints such as path delay and path utilization to be considered in a simple and intuitive way. Simulation tests show that AFAR outperforms OSPF, AntNet and ASR, three of the currently most important state-of-the-art algorithms, in terms of end-to-end delay, packet delivery, and packet drop ratio. AFAR is a promising alternative for routing of data in next generation networks.展开更多
In this paper, we study delay-induced firing behavior and transitions in adaptive Newman-Watts networks of thermosensitive neurons with electrical or chemical synapses. It is found that electrical and chemical synapse...In this paper, we study delay-induced firing behavior and transitions in adaptive Newman-Watts networks of thermosensitive neurons with electrical or chemical synapses. It is found that electrical and chemical synapse time delay-induced firing behavior and transitions differ significantly. In the case of electrical synapses, the bursts for a fixed delay involve equal number of spikes in each burst, and for certain time delays the firing can be inhibited. However, in the case of chemical synapses the bursts for a fixed delay involve different numbers of spikes in each burst, and no firing inhibition is observed. It is also shown that larger growth rates of adaptive coupling strength or larger network randomness can enhance the synchronization of bursting in the case of electrical synapses but reduce it in the case of chemical synapses. These results show that electrical and chemical synapses have different effects on delay-induced firing behavior and dynamical evolution. Compared to electrical synapses, chemical synapses might be more beneficial to the generation of firing and abundant firing transitions in adaptive and delayed neuronal networks. These findings can help to better understand different firing behaviors in neuronal networks with electrical and chemical synapses.展开更多
By introducing a deadwzone scheme, a new neural network based adaptive iterative learning control （ILC） （NN-AILC） scheme is presented for nonlinear discrete-time systems, where the NN weights are time-varying. The...By introducing a deadwzone scheme, a new neural network based adaptive iterative learning control （ILC） （NN-AILC） scheme is presented for nonlinear discrete-time systems, where the NN weights are time-varying. The most distinct contribution of the proposed NN-AILC is the relaxation of the identical conditions of initial state and reference trajectory, which are common requirements in traditional ILC problems. Convergence analysis indicates that the tracking error converges to a bounded ball, whose size is determined by the dead-zone nonlinearity. Computer simulations verify the theoretical results.展开更多
Hybrid wavelength-division-multiplexing(WDM)/time-division-multiplexing(TDM) ethernet passive optical networks(EPONs) can achieve low per-subscriber cost and scalability to increase the number of subscribers. This pap...Hybrid wavelength-division-multiplexing(WDM)/time-division-multiplexing(TDM) ethernet passive optical networks(EPONs) can achieve low per-subscriber cost and scalability to increase the number of subscribers. This paper discusses dynamic wavelength and bandwidth allocation(DWBA) algorithm in hybrid WDM/TDM EPONs.Based on the correlation structure of the variable bit rate(VBR) video traffic,we propose a quality-ofservice (QoS) supported DWBA using adaptive linear traffic prediction.Wavelength and timeslot are allocated dynamically by optical line terminal(OLT) to all optical network units(ONUs) based on the bandwidth requests and the guaranteed service level agreements(SLA) of all ONUs.Mean square error of the predicted average arriving rate of compound video traffic during waiting period is minimized through Wiener-Hopf equation.Simulation results show that the DWBA-adaptive-linear-prediction(DWBA-ALP) algorithm can significantly improve the QoS performances in terms of low delay and high bandwidth utilization.展开更多
In this paper,we study lag synchronization between two coupled networks and apply two types of control schemes,including the open-plus-closed-loop(OPCL) and adaptive controls.We then design the corresponding control a...In this paper,we study lag synchronization between two coupled networks and apply two types of control schemes,including the open-plus-closed-loop(OPCL) and adaptive controls.We then design the corresponding control algorithms according to the OPCL and adaptive feedback schemes.With the designed controllers,we obtain two theorems on the lag synchronization based on Lyapunov stability theory and Barbalat's lemma.Finally we provide numerical examples to show the effectiveness of the obtained controllers and see that the adaptive control is stronger than the OPCL control when realizing the lag synchronization between two coupled networks with different coupling structures.展开更多
基金国家自然科学基金(the National Natural Science Foundation of China under Grant No.60534020)国家教育部新世纪人才支持计划(the New Century Excellent Talent Foundation from MOE of China under Grant No.NCET- 04- 415)+1 种基金教育部科技创新工程重大项目培育资金项目(No.706024)上海市国际科技合作基金项目(No.061307041)
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.
文摘Aim To study the identification and control of nonlinear systems using neural networks. Methods A new type of neural network in which the dynamical error feedback is used to modify the inputs of the network was employed to reduce the inherent network approximation error. Results A new identification model constructed by the proposed network and stable filters was derived for continuous time nonlinear systems, and a stable adaptive control scheme based on the proposed networks was developed. Conclusion Theory and simulation results show that the modified neural network is feasible to control a class of nonlinear systems.
基金Project supported by the Iranian Telecommunication Research Center
文摘We propose a novel approach called adaptive fuzzy ant-based routing (AFAR), where a group of intelligent agents (or ants) builds paths between a pair of nodes, exploring the network concurrently and exchanging obtained information to up-date the routing tables. Routing decisions can be made by the fuzzy logic technique based on local information about the current network state and the knowledge constructed by a previous set of behaviors of other agents. The fuzzy logic technique allows multiple constraints such as path delay and path utilization to be considered in a simple and intuitive way. Simulation tests show that AFAR outperforms OSPF, AntNet and ASR, three of the currently most important state-of-the-art algorithms, in terms of end-to-end delay, packet delivery, and packet drop ratio. AFAR is a promising alternative for routing of data in next generation networks.
文摘In this paper, we study delay-induced firing behavior and transitions in adaptive Newman-Watts networks of thermosensitive neurons with electrical or chemical synapses. It is found that electrical and chemical synapse time delay-induced firing behavior and transitions differ significantly. In the case of electrical synapses, the bursts for a fixed delay involve equal number of spikes in each burst, and for certain time delays the firing can be inhibited. However, in the case of chemical synapses the bursts for a fixed delay involve different numbers of spikes in each burst, and no firing inhibition is observed. It is also shown that larger growth rates of adaptive coupling strength or larger network randomness can enhance the synchronization of bursting in the case of electrical synapses but reduce it in the case of chemical synapses. These results show that electrical and chemical synapses have different effects on delay-induced firing behavior and dynamical evolution. Compared to electrical synapses, chemical synapses might be more beneficial to the generation of firing and abundant firing transitions in adaptive and delayed neuronal networks. These findings can help to better understand different firing behaviors in neuronal networks with electrical and chemical synapses.
基金supported by General Program (60774022)State Key Program (60834001) of National Natural Science Foundation of ChinaDoctoral Foundation of Qingdao University of Science & Technology (0022324)
文摘By introducing a deadwzone scheme, a new neural network based adaptive iterative learning control （ILC） （NN-AILC） scheme is presented for nonlinear discrete-time systems, where the NN weights are time-varying. The most distinct contribution of the proposed NN-AILC is the relaxation of the identical conditions of initial state and reference trajectory, which are common requirements in traditional ILC problems. Convergence analysis indicates that the tracking error converges to a bounded ball, whose size is determined by the dead-zone nonlinearity. Computer simulations verify the theoretical results.
文摘Hybrid wavelength-division-multiplexing(WDM)/time-division-multiplexing(TDM) ethernet passive optical networks(EPONs) can achieve low per-subscriber cost and scalability to increase the number of subscribers. This paper discusses dynamic wavelength and bandwidth allocation(DWBA) algorithm in hybrid WDM/TDM EPONs.Based on the correlation structure of the variable bit rate(VBR) video traffic,we propose a quality-ofservice (QoS) supported DWBA using adaptive linear traffic prediction.Wavelength and timeslot are allocated dynamically by optical line terminal(OLT) to all optical network units(ONUs) based on the bandwidth requests and the guaranteed service level agreements(SLA) of all ONUs.Mean square error of the predicted average arriving rate of compound video traffic during waiting period is minimized through Wiener-Hopf equation.Simulation results show that the DWBA-adaptive-linear-prediction(DWBA-ALP) algorithm can significantly improve the QoS performances in terms of low delay and high bandwidth utilization.
基金Supported by the National Natural Science Foundation of China under Grant No.61304173Foundation of Liaoning Educational Committee(No.13-1069)and Hangzhou Polytechnic(No.KZYZ-2009-2)
文摘In this paper,we study lag synchronization between two coupled networks and apply two types of control schemes,including the open-plus-closed-loop(OPCL) and adaptive controls.We then design the corresponding control algorithms according to the OPCL and adaptive feedback schemes.With the designed controllers,we obtain two theorems on the lag synchronization based on Lyapunov stability theory and Barbalat's lemma.Finally we provide numerical examples to show the effectiveness of the obtained controllers and see that the adaptive control is stronger than the OPCL control when realizing the lag synchronization between two coupled networks with different coupling structures.
