Threshold optimization for weighted voting classifiers

Weighted voting classifiers considered in this paper consist of N units each providing individual classification decisions. The entire system output is based on tallying the weighted votes for each decision and choosing the one which has total support weight exceeding a certain threshold. Each individual unit may abstain from voting. The entire system may also abstain from voting if no decision support weight exceeds the threshold. Existing methods of evaluating the reliability of weighted voting systems can be applied to limited special cases of these systems and impose some restrictions on their parameters. In this paper a universal generating function method is suggested which allows the reliability of weighted voting classifiers to be exactly evaluated without imposing constraints on unit weights. Based on this method, the classifier reliability is determined as a function of a threshold factor, and a procedure is suggested for finding the threshold which minimizes the cost of damage caused by classifier failures (misclassification and abstention may have different price.) Dynamic and static threshold voting rules are considered and compared. A method of analyzing the influence of units' availability on the entire classifier reliability is suggested, and illustrative examples are presented. © 2003 Wiley Periodicals, Inc. Naval Research Logistics 50: 322–344, 2003.     

现代水雷控制电路中开关器件可靠性分析及其应用

从现代水雷控制电路开关器件的可靠性出发,对有触点和无触点开关器件的特点进行了研究,特别是对功率三极管B772和双线圈自锁继电器DS2Y SL2 DC6V的性能及可靠性进行了深入的对比分析,得到了开关器件选择准则,给水雷开关控制电路设计提供了理论依据.结论是:当控制系统工作时间较长而开、关不是很频繁时,用自锁继电器比用功率三极管更合适.     

Systems composed of two types of nonidentical and dependent components

A coherent system of order n that consists two different types of dependent components is considered. The lifetimes of the components in each group are assumed to follow an exchangeable joint distribution, and the two random vectors, which represent the lifetimes of the components in each group are also assumed to be dependent. Under this particular form of dependence, all components are assumed to be dependent but they are categorized with respect to their reliability functions. Mixture representation is obtained for the survival function of the system's lifetime. Mixture representations are also obtained for the series and parallel systems consisting of disjoint modules such that all components of Type I are involved in one module (subsystem) and all components of Type II are placed in the other module. The theoretical results are illustrated with examples. © 2015 Wiley Periodicals, Inc. Naval Research Logistics 62: 388–394, 2015     

一种改进遗传算法在UCAV快速航迹规划中的应用

针对无人作战飞机(Unmanned Combat Aerial Vehicle,UCAV)航迹规划约束条件复杂、不确定因素多、实时性要求高的特点,提出了一种基于Voronoi图和改进遗传算法的快速航迹规划方法。该方法采取分层航迹规划的思想,首先根据Voronoi图生成初始航迹,并综合考虑约束条件,赋予各条航迹相应的权值;然后应用改进的遗传算法在生成的航迹空间中寻优,最终得到满意的航迹。该算法利用多处理机并行计算技术对传统遗传算法进行改进,大大缩短寻优时间。仿真结果表明基于Voronoi图和改进遗传算法的航迹规划提高了实时性,增强了UCAV的动态战场适应能力和突发威胁应对能力。     

考虑多性能参数的引信弹簧可靠性评估

弹簧作为引信中常用的储能源,是影响引信可靠性的重要零件,而引信失效会形成重大安全隐患。为了准确预估某引信弹簧贮存期间的可靠度变化,提出了一种基于修正Arrhenius模型的多元正态可靠性评估方法。以应力损失率和永久变形率作为性能参数,设计了恒定应力加速退化试验,获取弹簧在120℃、130℃、150℃和160℃下的退化数据,并采用Anderson-Darling统计量验证退化量的最优分布为正态分布。根据修正的Arrhenius方程,得到弹簧在贮存温度下的退化轨迹曲线。基于多元正态分布建立弹簧贮存可靠度模型,分析弹簧贮存期间的可靠度变化特点。通过与其他可靠度模型对比,该模型预估结果更准确,可为引信的视情维修提供依据。     

基于流程仿真的物资接收系统可靠性预计方法

针对船舶物资接收时间计算的问题,新增加了对设备发生故障的考虑,通过引入接收时间可靠性的概念,将其转换为船舶物资接收系统的可靠性预计问题。为了解决上述可靠性预计问题,提出了基于流程仿真的系统可靠性预计方法。分析了物资接收系统的工作流程,依据工作流程实现了仿真程序,用蒙特卡洛法对物资接收系统的可靠性进行了求解,并分析了设备不同的可靠性水平对物资接收系统可靠性的影响。仿真结果表明,增加了对设备故障的考虑后,对物资接收时间的估计更加接近实际;基于流程仿真的系统可靠性预计方法的模型更容易理解,所得结论更加具体。     

基于概率影响图的空战能力评估模型

基于空战指标间复杂的影响关系,引入概率影响图,并结合指标间重要程度的比较对飞机空战能力进行客观评估。利用空战信息流图,依据作战结果计算能力指标值与发生概率,构建空战模型的概率影响图;定性分析能力指标间的影响关系,定量计算综合影响权重;综合考虑比较权和影响权,计算空战能力值。结果证明,影响关系在空战能力评估中占有很大比重。     

基于改进GM(1,1)模型的导弹贮存可靠性预测方法

针对导弹系统技术复杂、贮存样本量受限、测试数据波动性较大等特点,结合装备的具体情况提出了基于改进GM(1,1)模型的导弹贮存可靠性预测方法。该方法首先利用"对数-幂函数变换"对导弹的历史可靠性数据进行处理,提高数据光滑度,然后依据GM(1,1)模型计算得到可靠性预测值和残差,再利用残差建立残差修正模型,得到残差修正值,减少残差对结果的影响,最后利用残差修正值修正可靠性预测值并还原,求得可靠性最终预测值。实例表明,该改进模型对导弹系统可靠性变化的描述比传统模型更加准确有效,预测结果精度更高,为导弹贮存可靠性预测分析提供了一种有效的改进方法,其算法设计推广性强,可作为其他装备寿命预估的重要工具。     

基于样块改进的图像修复算法

图像修复是指对图像破损区域进行填充或者将图像中多余物体进行移除。在Criminisi算法的基础上进行改进,在待修复块优先权的计算过程中,由于等照度线的曲率可以反映图像的局部特征,块与块之间的方差值可以反映图像的边缘信息,因此,将二者考虑进来,确保修复过程能够准确有序地进行。在寻找最佳匹配块时,将等照度线的曲率也作为一个因素增加进来,有效地提高了最佳匹配块搜索的精确性。经过仿真实验证明,改进后的算法不仅在PSNR值上比原算法有所提高,而且修复结果也比原算法更加准确可靠。     

改进IAHP-CIM模型的雷达组网探测能力评估方法

针对雷达组网探测能力的评估问题,采用鱼骨图法对影响雷达组网探测能力的多种因素进行梳理,得到结构层次清晰的指标评价体系。采用改进的区间层次分析—控制区间和记忆模型对该指标体系进行评估,具体方法是:运用区间层次分析法构造区间判断矩阵;利用蛙跳算法求解区间判断矩阵中满足最小一致性的确定性矩阵;利用控制区间和记忆模型来确定各指标的风险概率,实现指标体系的评估。以具体的案例为对象进行仿真实验,结果表明,所提评估方法有效,评估结论相对客观、可信,对雷达组网探测能力评估具有一定参考价值,从而为雷达组网的优化部署奠定良好基础。