GPU上高光谱快速ICA降维并行算法

高光谱影像降维快速独立成分分析过程包含大规模矩阵运算和大量迭代计算。通过分析算法热点,设计协方差矩阵计算、白化处理、ICA迭代和IC变换等关键热点的图像处理单元映射方案,提出并实现一种G-Fast ICA并行算法,并基于GPU架构研究算法优化策略。实验结果显示:在处理高光谱影像降维时,CPU/GPU异构系统能获得比CPU更高效的性能,G-Fast ICA算法比串行最高可获得72倍加速比,比16核CPU并行处理快4~6.5倍。     

改进蚁群算法在P2P网络资源搜索中的应用

针对P2P网络搜索算法中冗余查询消息过多,资源搜索效率低的问题,提出了基于改进蚁群算法的P2P资源搜索算法,算法中在选择邻节点查询时,综合考虑到本地资源情况、邻节点资源情况、邻节点资源相似度等因素,尽量避开了资源搜索中的恶意节点,并改进了基本蚁群算法的状态转移规则,从而避免了查询消息的盲目发送。仿真实验表明,与传统资源搜索算法K-radom-walks和Flooding相比,该算法在搜索命中率和带宽利用率方面有明显提高。     

搜索路径给定时的搜索对策问题及其应用

搜索路径给定时的最优搜索方案问题,也可以理解为是关于搜索者和目标的二人对策问题,主要讨论了当搜索路径给定时的单个搜索者和单个目标的搜索对策问题。首先根据问题的特点,利用动态规划和迭代的方法,确定关于目标逃逸路径混合策略的最优分区,证明该分区是多面体凸集;针对目标不同逃逸路径的分区,求出搜索者的最大期望收益,再将问题转化为二人有限零和对策,计算出搜索者的支付矩阵,确定最优搜索策略。最后结合海军护航行动,对我舰载直升机搜索小型海盗船进行分析和计算,说明搜索路径给定时的最优搜索对策对于双方的资源分配和提高搜索效率具有一定的应用价值。     

The SSA-BP-based potential threat prediction for aerial target considering commander emotion

The target's threat prediction is an essential procedure for the situation analysis in an aerial defense system. However, the traditional threat prediction methods mostly ignore the effect of commander's emotion. They only predict a target's present threat from the target's features itself, which leads to their poor ability in a complex situation. To aerial targets, this paper proposes a method for its potential threat prediction considering commander emotion (PTP-CE) that uses the Bi-directional LSTM (BiLSTM) network and the backpropagation neural network (BP) optimized by the sparrow search algorithm (SSA). Furthermore, we use the BiLSTM to predict the target's future state from real-time series data, and then adopt the SSA-BP to combine the target's state with the commander's emotion to establish a threat prediction model. Therefore, the target's potential threat level can be obtained by this threat prediction model from the predicted future state and the recognized emotion. The experimental results show that the PTP-CE is efficient for aerial target's state prediction and threat prediction, regardless of commander's emotional effect.     

反潜机采用阿基米德螺旋线搜潜问题研究

反潜机是重要的反潜力量,根据反潜机搜潜情况,建立了反潜飞机采用阿基米德螺旋线样式搜潜的数学模型和目标运动模型,讨论了螺旋线采用的三种轨迹间隔,通过仿真验证,确立了反潜机搜潜最优轨迹间隔,以达到提高发现目标潜艇概率、优化反潜效能的目的,为反潜飞机采用阿基米德巡逻线搜潜样式搜潜时提供战术参考。     

基于依赖矩阵的Web服务组合故障诊断

为了保证指挥信息系统在动态环境下能够提供持续可靠的组合服务,提出一种利用依赖矩阵对Web服务组合故障原因进行诊断的模型,对依赖矩阵的建立进行了详细说明。然后,基于构造的依赖矩阵,提出改进的贪心算法对失效情况进行探测,并设计了基于二分查找的故障定位算法。实验模拟表明,提出的模型能够利用少量探测就能监测整个服务组合流程的运行情况,并定位找到错误源。     

New results on rendezvous search on the interval

In a rendezvous search problem, two players are placed in a network and must try to meet each other in the least possible expected time. We look at rendezvous search on a discrete interval in which the players are initially placed using independent draws (usually assumed to be from the same distribution). Some optimal solutions are known if this distribution is uniform, and also for certain other special types of distribution. In this article, we present two new results. First, we characterize the complete set of solutions for the uniform case, showing that all optimal strategies must have two specific properties (namely, of being swept and strictly geodesic). Second, we relate search strategies on the interval to proper binary trees, and use this correspondence to derive a recurrence relation for solutions to the symmetric rendezvous problem for any initial distribution. This relation allows us to solve any such problem computationally by dynamic programming. Finally, some ideas for future research are discussed. © Wiley Periodicals, Inc. Naval Research Logistics 60: 454–467, 2013     

高速互联线的高频串扰仿真研究

为了研究PCB板上高速互联线之间的串扰,基于传输线分布参数节点导纳方程和快速傅里叶逆变换技术,仿真研究了PCB板布线间的串扰电压响应,分析了分布参数、线长度及端接阻抗对串扰强弱的影响,提出了减少串扰的措施。仿真结果表明：串扰电压值随分布电感的增加而减小,随分布电容的增加变化不明显;串扰电压值随线长增加而减小;串扰电压值随干扰线端接阻抗的增加而减小,随受扰线端接阻抗的增大而增大。     

微结构阵列超精密车床快刀伺服装置及试验研究

各种微结构阵列在LED照明、液晶显示、光学仪器等领域得到了广泛的应用,但其结构细微复杂且形状表面质量要求高,其加工工艺技术研究引起了广泛的关注。本文提出压电陶瓷驱动结合柔性铰链作为刀架的快刀伺服装置,建立快刀伺服系统的机电耦合模型,研究各系统参数对系统性能的影响规律,基于有限元仿真对铰链结构参数进行优化;通过激光位移传感器测试刀具输出位移的线性度;利用研制的快刀系统和超精密车床在红铜材质的圆柱面上进行正弦网格微结构加工,加工结果表明所设计的快刀系统能够准确有效地加工出结构复杂的微结构阵列。     

Multi-scale traffic vehicle detection based on faster R-CNN with NAS optimization and feature enrichment

It well known that vehicle detection is an important component of the field of object detection. However, the environment of vehicle detection is particularly sophisticated in practical processes. It is compara-tively difficult to detect vehicles of various scales in traffic scene images, because the vehicles partially obscured by green belts, roadblocks or other vehicles, as well as influence of some low illumination weather. In this paper, we present a model based on Faster R-CNN with NAS optimization and feature enrichment to realize the effective detection of multi-scale vehicle targets in traffic scenes. First, we proposed a Retinex-based image adaptive correction algorithm (RIAC) to enhance the traffic images in the dataset to reduce the influence of shadow and illumination, and improve the image quality. Second, in order to improve the feature expression of the backbone network, we conducted Neural Architecture Search (NAS) on the backbone network used for feature extraction of Faster R-CNN to generate the optimal cross-layer connection to extract multi-layer features more effectively. Third, we used the object Feature Enrichment that combines the multi-layer feature information and the context information of the last layer after cross-layer connection to enrich the information of vehicle targets, and improve the robustness of the model for challenging targets such as small scale and severe occlusion. In the imple-mentation of the model, K-means clustering algorithm was used to select the suitable anchor size for our dataset to improve the convergence speed of the model. Our model has been trained and tested on the UN-DETRAC dataset, and the obtained results indicate that our method has art-of-state detection performance.