一个基于机器学习的神经网络初始化方法

本文针对ＢＰ（ｂａｃｋｐｒｏｐａｇａｔｉｏｎ）前馈神经网络存在的训练时间长、容易陷入局部极小等问题，研究了一个基于机器学习的神经网络初始化方法．实验结果表明，用这种方法初始化神经网络，提高了神经网络的学习效率和泛化能力，并且可以有效地抑制陷入局部极小的可能性．

BP神经网络在空袭目标优选中的应用

空袭目标优选,应用改进的BP神经网络算法。即在空袭目标优选评估指标体系基础上,建立BP神经网络,通过定义学习代价函数、确定函数输出信号、修正函数信号。并通过网络初始化等改进BP算法,以激活函数敏感性,加速网络收敛。算例验证了该算法合理性,稳定性良好。

冲突避免的水声网络拓扑发现协议

当水声网络的所有节点完成在目标区域的部署后,每个节点除了自己的节点ID已知外,对新网络的信息一无所知,而这些信息是网络顺利运行的必要前提。因此,一个能够完成网络中所有节点和链路发现的网络拓扑发现协议是非常必要和重要的。水声拓扑发现协议完成的效率,往往依赖于信道接入策略的选择,但它不能完全使用已有的水声多路访问控制(multiple access control,MAC)协议,因为在网络建立的初始阶段拓扑未知,已有传统水声MAC协议不能完成拓扑发现,所以需要根据这一阶段的特殊状态来设计拓扑发现协议。基于此问题,提出了一种高效的冲突避免的水声网络拓扑发现(简称为CFVE)协议,该协议利用网络中节点ID的唯一性,在其特定时隙接入信道,节点无冲突地发现控制分组的交换,最终实现网络中所有链路和节点的发现。仿真结果表明,CFVE协议可以以较低的发现时延和能耗完成全网拓扑的发现,是一种适合于多跳水声网络的拓扑发现协议。

Real-time instance segmentation based on contour learning

Instance segmentation plays an important role in image processing.The Deep Snake algorithm based on contour iteration deforms an initial bounding box to an instance contour end-to-end,which can improve the performance of instance segmentation,but has defects such as slow segmentation speed and sub-optimal initial contour.To solve these problems,a real-time instance segmentation algorithm based on contour learning was proposed.Firstly,ShuffleNet V2 was used as backbone network,and the receptive field of the model was expanded by using a 5×5 convolution kernel.Secondly,a lightweight up-sampling module,multi-stage aggregation(MSA),performs residual fusion of multi-layer features,which not only improves segmentation speed,but also extracts effective features more comprehensively.Thirdly,a contour initialization method for network learning was designed,and a global contour feature aggregation mechanism was used to return a coarse contour,which solves the problem of excessive error between manually initialized contour and real contour.Finally,the Snake deformation module was used to iteratively optimize the coarse contour to obtain the final instance contour.The experimental results showed that the proposed method improved the instance segmentation accuracy on semantic boundaries dataset(SBD),Cityscapes and Kins datasets,and the average precision reached 55.8 on the SBD;Compared with Deep Snake,the model parameters were reduced by 87.2%,calculation amount was reduced by 78.3%,and segmentation speed reached 39.8 frame·s−1 when instance segmentation was performed on an image with a size of 512×512 pixels on a 2080Ti GPU.The proposed method can reduce resource consumption,realize instance segmentation tasks quickly and accurately,and therefore is more suitable for embedded platforms with limited resources.

优化神经网络在油石比预估中的应用

利用反传神经网络算法由沥青混合料级配等参数作为输入参数估计沥青混凝土最佳沥青含量,针对传统BP网络的缺陷,通过改进网络初始化、网络结构,采用动态的网络学习机制,提高了反传神经网络在最佳沥青含量预估中的稳定性和泛化性能。

802.16e系统周期测距的软件设计和实现

测距作为WiMAX上行链路调整时间偏置、功率信息和载波频率的一种方法,在系统接入和通信过程中起着重要作用。深入研究了基于ARM处理器的802.16e系统正交频分多址(orthogonal frequency division multiple ac-cess,OFDMA)物理层的周期测距的软件设计与实现,给出了802.16e系统OFDMA物理层的周期测距算法和流程、周期测距码的发射和检测原理以及周期测距模块的C语言设计。在搭建的测试平台上进行链路测试,结果表明此方案是可行的。

Seismic velocity inversion based on CNN-LSTM fusion deep neural network

Based on the CNN-LSTM fusion deep neural network,this paper proposes a seismic velocity model building method that can simultaneously estimate the root mean square(RMS)velocity and interval velocity from the common-midpoint(CMP)gather.In the proposed method,a convolutional neural network(CNN)Encoder and two long short-term memory networks(LSTMs)are used to extract spatial and temporal features from seismic signals,respectively,and a CNN Decoder is used to recover RMS velocity and interval velocity of underground media from various feature vectors.To address the problems of unstable gradients and easily fall into a local minimum in the deep neural network training process,we propose to use Kaiming normal initialization with zero negative slopes of rectifi ed units and to adjust the network learning process by optimizing the mean square error(MSE)loss function with the introduction of a freezing factor.The experiments on testing dataset show that CNN-LSTM fusion deep neural network can predict RMS velocity as well as interval velocity more accurately,and its inversion accuracy is superior to that of single neural network models.The predictions on the complex structures and Marmousi model are consistent with the true velocity variation trends,and the predictions on fi eld data can eff ectively correct the phase axis,improve the lateral continuity of phase axis and quality of stack section,indicating the eff ectiveness and decent generalization capability of the proposed method.

Distribution Network Reactive Power Optimization Based on Ant Colony Optimization and Differential Evolution Algorithm

Due to the inherent complexity, traditional ant colony optimization （ACO） algorithm is inadequate and insufficient to the reactive power optimization for distribution network. Therefore, firstly the ACO algorithm is improved in two aspects： pheromone mutation and re-initialization strategy. Then the thought of differential evolution （DE） algorithm is proposed to be merged into ACO, and by producing new individuals with random deviation disturbance of DE, pheromone quantity left by ants is disturbed appropriately, to search the optimal path, by which the ability of search having been improved. The proposed algorithm is tested on IEEE30-hus system and actual distribution network, and the reactive power optimization results are calculated to verify the feasibility and effectiveness of the improved algorithm.