The morphological and functional characteristics of neurons are quite varied and complex. There is a need for a comprehensive approach for distinguishing and classifying neurons. Similar to the biological species clas...The morphological and functional characteristics of neurons are quite varied and complex. There is a need for a comprehensive approach for distinguishing and classifying neurons. Similar to the biological species classification system, this study proposes a morphological classification system for neurons based on principal component analysis. Based on four principal components of neuronal morphology derived from principal component analysis, a nomenclature system for neurons was obtained. This system can accurately distinguish between the same type of neuron from different species.展开更多
云机器人通过动态"卸载"任务到云端高效处理,极大提高了节点的智能水平。然而,由于云端应用的实时性差异和负载的不可预知,对网络传输的服务质量(quality of service,QoS)需求不尽相同。从控制角度研究网络传输的服务质量问题...云机器人通过动态"卸载"任务到云端高效处理,极大提高了节点的智能水平。然而,由于云端应用的实时性差异和负载的不可预知,对网络传输的服务质量(quality of service,QoS)需求不尽相同。从控制角度研究网络传输的服务质量问题,提出并实现了一种基于BP神经网络的双闭环接入控制方法(BPFD-MAC),在最大化能量利用率的同时,实现绝对服务质量和相对服务质量保证。通过反馈控制结构,将绝对QoS约束和相对QoS约束解耦为2个独立闭环:活动时间闭环根据高优先级的延迟控制节点活动时间,满足绝对约束;退避窗口闭环根据不同优先级的延迟比,调整退避时间的初始上限,保持相对延迟比例关系恒定,满足相对约束。并采用BP神经网络方法进行参数自适应校正和控制器设计。最后,基于ZigBit 900的硬件实验表明,相对于FD-MAC,BPFD-MAC不仅能够在负载动态变化时提供绝对和相对QoS保证,并且在网络高负载下,具有更高的吞吐量和能量利用率;在网络低负载下,具有更低的能耗。展开更多
The back propagation (BP)-based artificial neural nets (ANN) can identify complicated relationships among dissolved gas contents in transformer oil and corresponding fault types, using the highly nonlinear mapping nat...The back propagation (BP)-based artificial neural nets (ANN) can identify complicated relationships among dissolved gas contents in transformer oil and corresponding fault types, using the highly nonlinear mapping nature of the neural nets. An efficient BP-ALM (BP with Adaptive Learning Rate and Momentum coefficient) algorithm is proposed to reduce the training time and avoid being trapped into local minima, where the learning rate and the momentum coefficient are altered at iterations. We developed a system of transformer fault diagnosis based on Dissolved Gases Analysis (DGA) with a BP-ALM algorithm. Training patterns were selected from the results of a Refined Three-Ratio method (RTR). Test results show that the system has a better ability of quick learning and global convergence than other methods and a superior performance in fault diagnosis compared to convectional BP-based neural networks and RTR.展开更多
基金the National Natural Science Foundation of China, No. 10872069
文摘The morphological and functional characteristics of neurons are quite varied and complex. There is a need for a comprehensive approach for distinguishing and classifying neurons. Similar to the biological species classification system, this study proposes a morphological classification system for neurons based on principal component analysis. Based on four principal components of neuronal morphology derived from principal component analysis, a nomenclature system for neurons was obtained. This system can accurately distinguish between the same type of neuron from different species.
文摘云机器人通过动态"卸载"任务到云端高效处理,极大提高了节点的智能水平。然而,由于云端应用的实时性差异和负载的不可预知,对网络传输的服务质量(quality of service,QoS)需求不尽相同。从控制角度研究网络传输的服务质量问题,提出并实现了一种基于BP神经网络的双闭环接入控制方法(BPFD-MAC),在最大化能量利用率的同时,实现绝对服务质量和相对服务质量保证。通过反馈控制结构,将绝对QoS约束和相对QoS约束解耦为2个独立闭环:活动时间闭环根据高优先级的延迟控制节点活动时间,满足绝对约束;退避窗口闭环根据不同优先级的延迟比,调整退避时间的初始上限,保持相对延迟比例关系恒定,满足相对约束。并采用BP神经网络方法进行参数自适应校正和控制器设计。最后,基于ZigBit 900的硬件实验表明,相对于FD-MAC,BPFD-MAC不仅能够在负载动态变化时提供绝对和相对QoS保证,并且在网络高负载下,具有更高的吞吐量和能量利用率;在网络低负载下,具有更低的能耗。
文摘The back propagation (BP)-based artificial neural nets (ANN) can identify complicated relationships among dissolved gas contents in transformer oil and corresponding fault types, using the highly nonlinear mapping nature of the neural nets. An efficient BP-ALM (BP with Adaptive Learning Rate and Momentum coefficient) algorithm is proposed to reduce the training time and avoid being trapped into local minima, where the learning rate and the momentum coefficient are altered at iterations. We developed a system of transformer fault diagnosis based on Dissolved Gases Analysis (DGA) with a BP-ALM algorithm. Training patterns were selected from the results of a Refined Three-Ratio method (RTR). Test results show that the system has a better ability of quick learning and global convergence than other methods and a superior performance in fault diagnosis compared to convectional BP-based neural networks and RTR.
