This paper proposes a Back Propagation (BP) neural network with momentum enhancement aiming to achieving the smooth convergence for aggregate volumetric estimation purpose. Network inputs are first selected by optical...This paper proposes a Back Propagation (BP) neural network with momentum enhancement aiming to achieving the smooth convergence for aggregate volumetric estimation purpose. Network inputs are first selected by optically measuring the eight geometry-related parameters from the given particle image. To simplify the network structure, principal component analysis technique is applied to reduce the input dimension. The specific network structure is finalized based on both empirical expertise and analysis on selecting the appropriate number of neurons in hidden layer. The network is trained using the finite number of randomly-picked particles. The training and test results suggest that, compared to the generic BP network, the training duration of the proposed neural network is greatly attenuated, the complexity of the network structure is largely reduced, and the estimation precision is within 2%, being sufficiently up to technical satisfaction.展开更多
This paper proposes a simple and efficient distributed algorithm for calculating minimal dominating set in wireless sensor network. This method can avoid maintaining the connectivities between backbone hosts. Consider...This paper proposes a simple and efficient distributed algorithm for calculating minimal dominating set in wireless sensor network. This method can avoid maintaining the connectivities between backbone hosts. Considering that the hosts in mobile networks have different characteristics, this paper proposes a method of calculating minimal dominating set with weight. The nodes can be chosen to form a minimal dominating set when the network topology changes. For the host switch on/off operation, the updating algorithm was provided. The change in the status of a hostaffects only the status of hosts in the restricted vicinity. Simulation results show that the proposed method can ensure fewer dominators but with higher weight to form the minimal dominating set and the nodes can be adaptive to the changes of network topology.展开更多
基金Funded by Ningbo Natural Science Foundation (No. 2006A610016)Foundation of National Education Ministry for Returned Overseas Chinese Students & Scholars (SRF for ROCS, SEM. No.2006699)
文摘This paper proposes a Back Propagation (BP) neural network with momentum enhancement aiming to achieving the smooth convergence for aggregate volumetric estimation purpose. Network inputs are first selected by optically measuring the eight geometry-related parameters from the given particle image. To simplify the network structure, principal component analysis technique is applied to reduce the input dimension. The specific network structure is finalized based on both empirical expertise and analysis on selecting the appropriate number of neurons in hidden layer. The network is trained using the finite number of randomly-picked particles. The training and test results suggest that, compared to the generic BP network, the training duration of the proposed neural network is greatly attenuated, the complexity of the network structure is largely reduced, and the estimation precision is within 2%, being sufficiently up to technical satisfaction.
基金Supported by National Natural Science Foundation of China (No.60973141)Natural Science Foundation of Tianjin (No.09JCYBJC00300)
文摘This paper proposes a simple and efficient distributed algorithm for calculating minimal dominating set in wireless sensor network. This method can avoid maintaining the connectivities between backbone hosts. Considering that the hosts in mobile networks have different characteristics, this paper proposes a method of calculating minimal dominating set with weight. The nodes can be chosen to form a minimal dominating set when the network topology changes. For the host switch on/off operation, the updating algorithm was provided. The change in the status of a hostaffects only the status of hosts in the restricted vicinity. Simulation results show that the proposed method can ensure fewer dominators but with higher weight to form the minimal dominating set and the nodes can be adaptive to the changes of network topology.
