基于混合改进鸟群算法的贝叶斯网络结构学习

针对贝叶斯网络结构学习中寻优效率低下、易陷入局部最优的缺陷,提出了一种基于混合改进鸟群算法的贝叶斯网络结构学习算法.首先,通过互信息约束算法迭代初始网络;其次,改进鸟群算法,在经典鸟群算法中加入自适应惯性权重,随着迭代次数的增加动态调整搜索空间、改变收敛速度;最后,将改进的鸟群算法作为搜索策略,进行贝叶斯网络结构寻优.实验结果表明:改进的算法在寻优过程中不仅有较好的准确率和较快的收敛速度,而且具有良好的全局寻优能力.     

基于博弈策略的双无人机冲突解脱方法

针对无人机在空域飞行时完成冲突解脱所存在的消耗时间长、绕飞距离严重、机动次数多等问题,在2架无人机发生冲突的条件下,基于博弈论的知识,提出一种双无人机冲突解脱方法。首先,依据2架无人机的运动模型建立冲突探测模型,求出达到最小距离的时间公式,根据此公式反解出2架无人机改变的速度或航向值;其次,将鹰鸽博弈与贝叶斯博弈结合,以期望效用分析适合双方的解脱策略;最后,完成解脱后为减小航迹偏离等情况,无人机执行恢复策略恢复至初始状态。结果表明,与单机解脱相比,在解脱时间、绕飞距离、总飞行时间及总飞行距离方面的效果都有所改善。改进后的探测模型不仅能迅速计算出解脱策略改变值,而且在引入博弈策略后冲突双方可根据自身最大效益选择解脱策略,解决冲突解脱问题的方法简单有效,可以保证无人机在空域内发生冲突时能快速解脱。     

财务困境概率贝叶斯估计

通过财务困境概率估计模型建立一套企业财务风险预测系统,具有降低企业经营风险、投资风险以及防范金融危机的重要意义。现有的预测模型主要有:多元识别分析模型、Logit和Probit等统计回归模型以及人工神经网络预测模型。但以上模型均忽略了决策者个人经验、智慧以及信息优势对财务困境预测的重要作用。本文利用贝叶斯分析方法建立的概率估计模型,可以较好地解决这个问题,提高预测的针对性和准确性。     

TWO-STAGE ORDERING DECISION FOR A SHORT-LIFE-CYCLE PRODUCT

1. Introduction Recent years have seen scores of retail and manufacturing companies exploring innovative ordering or production modes in an effort to improve their operations and ultimately the bottom lines. So, more and more scholars and managers have investigated stochastic inventory problems. Uncertain demand is the cause of higher inventory costs for short-life-cycle products, such as style fashions, perishable products, and even IT-type products. For short-life-cycle products, most schol…     

Research on the self-defence electronic jamming decision-making based on the discrete dynamic Bayesian network

The manner and conditions of running the decision-making system with self-defense electronic jamming are given.After proposing the scenario of applying discrete dynamic Bayesian network to the decision making with self-defense electronic jamming,a decision-making model with self-defense electronic jamming based on the discrete dynamic Bayesian network is established.Then jamming decision inferences by the aid of the algorithm of discrete dynamic Bayesian network are carried on.The simulating result shows that this method is able to synthesize different targets which are not predominant.In this way,various features at the same time,as well as the same feature appearing at different time complement mutually;in addition,the accuracy and reliability of electronic jamming decision making are enhanced significantly.     

目标检测中的传感器管理方法研究

基于假设检验的方法,研究了目标检测与定位中的传感器管理方法,给出了一种最大后验概率法,讨论了另外两种基于贝叶斯推理的最大正确检测概率法和最小代价函数法。通过仿真改进了最大正确检测概率法,对三种不同方法的检测正确率和平均采样次数进行了比较,分析了各种方法的适用场合。     

对数正态分布环境因子的统计推断

为了对不同环境下的试验数据进行折算与综合，本文在失效机理不变的前提下，系统地讨论了对数正态分布环境因子的定义；给出了判别两种环境下产品失效机理是否发生了显著变化的统计检验方法；并推导了对数正态分布环境因子的极大似然估计（ＭＬＥ）以及经典的Ｂａｙｅｓｉａｎ与Ｆｉｄｕｃｉａｌ区间估计。最后用数值例说明了这些方法。结果表明该定义及这些方法是恰当的。     

A bayesian forecasting model for sequential bidding

In this paper we consider the problem facing a company in selecting the values of bids to submit on a sequence of contracts put out to tender. A simple-to-implement Bayesian forecasting model is presented, based on a steady Dirichlet process whose states are indexed by the possible bid decisions open to the company. The model gives an explicit algorithm for calculating the state probabilities, needing only data on the lowest bid made by the company's competitors. The flexibility of the basic model makes it a potentially powerful forecasting system for use by companies bidding for contracts.     

匹配于进化种群的局部网络图度量

为了分析匹配于进化种群的贝叶斯网络结构 ,给出了用于刻画局部贝叶斯网络度量的有关表示。依据贝叶斯狄利克雷度量 ,对于贝叶斯网络图中的 3个顶点 (对应于染色体的某 3个基因位置 ) ,研究了 3个顶点无连接、其中只有两个顶点存在有向连接、及 3个顶点存在两条有向边时的度量值关系。揭示了局部贝叶斯网络结构的固有特性 ,为进一步研究进化算法的种群结构提供了一条可行的途径。     

贝叶斯决策的影响图分析方法

对一般的贝叶斯决策问题, 常用的求解手段是决策树分析方法。本文则用影响图分析方法对贝叶斯决策问题进行表征和求解, 并将两个方法作了比较。另外, 本文给出了关于影响图变换运算的两个新结果。