一种基于Q-R矩阵分解的自适应滤波算法

由于计算误差等因素的影响,致使滤波协方差阵不对称或负定,从而导致滤波器发散,影响滤波算法的收敛速度和稳定性。在机动加速度"当前"统计自适应卡尔曼滤波算法的基础上,引入了基于Q-R矩阵分解的自适应卡尔曼滤波算法。将协方差阵分解为两个矩阵的乘积,来保证协方差矩阵的正定性。仿真结果表明,该算法可以较好地跟踪机动目标,具有精度高、稳定好、收敛快等特点。     

克服多路径效应的自适应偏轴跟踪方法

在已有的偏轴跟踪方法的基础上,利用海情、目标距离、正交分量的误差电压及其变化,自适应地进行偏轴跟踪,以达到用普通单脉冲雷达精确地跟踪超低空飞行海上目标的目的.     

卫星导航弱信号的变维卡尔曼滤波跟踪算法

复杂环境下的多普勒频移变化及信号功率衰减均会造成载波跟踪偏差较大甚至失锁,针对标准卡尔曼滤波算法跟踪机动目标时不能同时满足高动态及高灵敏度要求的问题,提出一种基于变维卡尔曼滤波的载波跟踪算法。引入机动和非机动两种载波跟踪模型,通过机动检测因子监视载波动态变化,实时高效地切换载波跟踪模型,从而实现对载波机动和非机动状态的自适应跟踪,抑制机动改变引起的较大误差突跳。理论分析和仿真结果表明,该算法在低至30d BHz弱信号环境下,相比基于标准卡尔曼滤波的跟踪算法,其在目标动态突变时相位跟踪误差减小约37.5%,频率跟踪误差减小约77%。     

神经网络架构搜索研究进展与展望

神经网络架构搜索旨在针对不同任务,自动化地搜索得到性能最优的神经网络结构,是深度学习、计算机视觉技术结合当前现实需求应运而生的一大重要科学问题。对近年来神经网络架构搜索研究进行梳理、归类和评述;阐述神经网络架构搜索的定义和意义,全方位剖析当前研究所面临的难点与挑战;以此为基础,对主流的搜索策略进行阐述和归纳;探讨研究潜在的问题及未来颇具潜力的研究方向,以期推动该领域的进一步发展。     

非均匀光强对曲率型自适应光学系统的影响

在高斯光强和光强存在正态随机起伏情况下,研究了一种37单元的曲率型自适应光学系统对低阶Zernike像差的校正效果,并和均匀光强时的校正效果进行了比较.光强为高斯分布时,光强的不均匀性对Zernike像差的校正带来了一定的影响,对于曲率为零的Zernike像差影响较小,对曲率不为零的Zernike像差影响较大.光强存在正态随机起伏时,对各阶Zernike像差的校正影响较小,曲率为零的Zernike像差的校正效果好于曲率不为零的Zernike像差的校正效果.结果表明在光强起伏不严重的情况下,该37单元曲率型自适应光学系统对低阶Zernike像差可以较好地校正.     

Averaging frameworks for simulation optimization with applications to simulated annealing

We present two frameworks for designing random search methods for discrete simulation optimization. One of our frameworks is very broad (in that it includes many random search methods), whereas the other one considers a special class of random search methods called point‐based methods, that move iteratively between points within the feasible region. Our frameworks involve averaging, in that all decisions that require estimates of the objective function values at various feasible solutions are based on the averages of all observations collected at these solutions so far. Also, the methods are adaptive in that they can use information gathered in previous iterations to decide how simulation effort is expended in the current iteration. We show that the methods within our frameworks are almost surely globally convergent under mild conditions. Thus, the generality of our frameworks and associated convergence guarantees makes the frameworks useful to algorithm developers wishing to design efficient and rigorous procedures for simulation optimization. We also present two variants of the simulated annealing (SA) algorithm and provide their convergence analysis as example application of our point‐based framework. Finally, we provide numerical results that demonstrate the empirical effectiveness of averaging and adaptivity in the context of SA. © 2012 Wiley Periodicals, Inc. Naval Research Logistics, 2012     

无源北斗组合导航算法对载体机动的适应性

研究了自适应滤波定位算法,以便减小大机动时组合导航系统的定位误差。首先,在仿真分析组合导航算法的基础上,提出了模糊逻辑自适应滤波方案。然后,通过仿真获取系统知识,建立模糊逻辑算法调整滤波器驱动噪声方差,实现滤波定位模型对用户机动的适应性。最后,通过仿真验证,模糊逻辑自适应滤波算法能够根据用户机动情况实时调整卡尔曼滤波器的驱动噪声方差参数,并能有效提高组合导航系统机动时的定位精度。     

基于核函数的自适应聚类背景提取

随着目标的检测与跟踪的广泛应用,移动物体分割问题成为研究热点,而解决这类问题的关键需为对图像背景的更新和提取。通过对目前已有的背景提取方法的研究,提出了一种新的基于核函数的背景提取方法:进行预处理,制定删选法则来自适应获取所需处理的视频序列;定义核函数来衡量模式间相似性,对2类聚类中心进行初始化;利用最小距离准则来灰度归并,采取实时的自适应阈值选择;最后通过比较满足条件的像素总数,获取所需背景。实验证明,该方法有效。     

A cooperative interference resource allocation method based on improved firefly algorithm

To deal with the radio frequency threat posed by modern complex radar networks to aircraft, we researched the unmanned aerial vehicle (UAV) formations radar countermeasures, aiming at the solution of radar jamming resource allocation under system countermeasures. A jamming resource allocation method based on an improved firefly algorithm (FA) is proposed. Firstly, the comprehensive factors affecting the level of threat and interference efficiency of radiation source are quantified by a fuzzy comprehensive evaluation. Besides, the interference efficiency matrix and the objective function of the allocation model are determined to establish the interference resource allocation model. Finally, A mutation operator and an adaptive heuristic are integtated into the FA algorithm, which searches an interference resource allocation scheme. The simulation results show that the improved FA algorithm can compensate for the deficiencies of the FA algorithm. The improved FA algorithm provides a more sci-entific and reasonable decision-making plan for aircraft mission allocation and can effectively deal with the battlefield threats of the enemy radar network. Moreover, in terms of convergence accuracy and speed as well as algorithm stability, the improved FA algorithm is superior to the simulated annealing algorithm (SA), the niche genetic algorithm (NGA), the improved discrete cuckoo algorithm (IDCS), the mutant firefly algorithm (MFA), the cuckoo search and fireflies algorithm (CSFA), and the best neighbor firefly algorithm (BNFA).