A method of assigning binary indexes to codevectors in vector quantization (VQ)system, which is called pseudo-Gray coding, is presented in this paper by constructing a kind of Hopfield neural network. Pseudo-Gray codi...A method of assigning binary indexes to codevectors in vector quantization (VQ)system, which is called pseudo-Gray coding, is presented in this paper by constructing a kind of Hopfield neural network. Pseudo-Gray coding belongs to joint source/channel coding, which could provide a redundancy-free error protection scheme for VQ of analog signals when the binary indexes of signal codevectors are used as channel symbols on a discrete memoryless channel. Since pseudo-Gray coding is of combinatorial optimization problems which are NP-complete problems,globally optimal solutions are generally impossible. Thus, a kind of Hopfield neural network is used by constructing suitable energy function to get sub-optimal solutions. This kind of Hop field neural network is easily modified to solve simplified version of pseudo-Gray coding for single bit-error channel model. Simulating experimental results show that the method introduced here could offer good performances.展开更多
In order to emulate a skilled human operator determining weld penetration from feature sizes of weld pool,such us topside maximum width and half-length of weld pool, a CCD camera assisted with electronic shutter and c...In order to emulate a skilled human operator determining weld penetration from feature sizes of weld pool,such us topside maximum width and half-length of weld pool, a CCD camera assisted with electronic shutter and composed filter system is used to simultaneously capture topside and backside images of weld pool in the same frame. Neural networks are used to investigate the complicated relationships between the weld penedrion and different parameters, they are capabe of modeling complicated nonlinear functions. Bead-on-plate welding experiments and simulations show that a neural network model has adequate accuracy required for monitoring full penetration duringpulsed GTAW dynamic process.展开更多
隐藏社区检测有助于揭示网络深层次功能和结构特征,是一个具有挑战性的研究领域。隐藏社区由弱关系连接而成,受具有较强连接关系的显性社区影响,在网络中不易被检测到。当前的隐藏社区发现算法对节点属性信息和全局拓扑结构的综合利用...隐藏社区检测有助于揭示网络深层次功能和结构特征,是一个具有挑战性的研究领域。隐藏社区由弱关系连接而成,受具有较强连接关系的显性社区影响,在网络中不易被检测到。当前的隐藏社区发现算法对节点属性信息和全局拓扑结构的综合利用仍显不足,为解决这一问题,提出了一种基于双重图卷积神经网络(GCN)联合优化隐藏社区发现算法——HCDGCN(hidden community detection based on dual GCN)。HCDGCN融合节点局部和全局结构特征,通过两个GCN共同迭代优化一个损失函数,并逐步削弱权重,使得弱关系社区变得清晰可见,实现了隐藏社区发现。在真实数据集上的实验结果表明,HCDGCN在隐藏社区发现方面优于现有基准方法,实现了更快的收敛速度和更优的社区划分。展开更多
文摘A method of assigning binary indexes to codevectors in vector quantization (VQ)system, which is called pseudo-Gray coding, is presented in this paper by constructing a kind of Hopfield neural network. Pseudo-Gray coding belongs to joint source/channel coding, which could provide a redundancy-free error protection scheme for VQ of analog signals when the binary indexes of signal codevectors are used as channel symbols on a discrete memoryless channel. Since pseudo-Gray coding is of combinatorial optimization problems which are NP-complete problems,globally optimal solutions are generally impossible. Thus, a kind of Hopfield neural network is used by constructing suitable energy function to get sub-optimal solutions. This kind of Hop field neural network is easily modified to solve simplified version of pseudo-Gray coding for single bit-error channel model. Simulating experimental results show that the method introduced here could offer good performances.
文摘In order to emulate a skilled human operator determining weld penetration from feature sizes of weld pool,such us topside maximum width and half-length of weld pool, a CCD camera assisted with electronic shutter and composed filter system is used to simultaneously capture topside and backside images of weld pool in the same frame. Neural networks are used to investigate the complicated relationships between the weld penedrion and different parameters, they are capabe of modeling complicated nonlinear functions. Bead-on-plate welding experiments and simulations show that a neural network model has adequate accuracy required for monitoring full penetration duringpulsed GTAW dynamic process.
文摘隐藏社区检测有助于揭示网络深层次功能和结构特征,是一个具有挑战性的研究领域。隐藏社区由弱关系连接而成,受具有较强连接关系的显性社区影响,在网络中不易被检测到。当前的隐藏社区发现算法对节点属性信息和全局拓扑结构的综合利用仍显不足,为解决这一问题,提出了一种基于双重图卷积神经网络(GCN)联合优化隐藏社区发现算法——HCDGCN(hidden community detection based on dual GCN)。HCDGCN融合节点局部和全局结构特征,通过两个GCN共同迭代优化一个损失函数,并逐步削弱权重,使得弱关系社区变得清晰可见,实现了隐藏社区发现。在真实数据集上的实验结果表明,HCDGCN在隐藏社区发现方面优于现有基准方法,实现了更快的收敛速度和更优的社区划分。
