Semantic image annotation based on GMM and random walk model

Automatic image annotation has been an active topic of research in computer vision and patternrecognition for decades.A two stage automatic image annotation method based on Gaussian mixturemodel (GMM) and random walk model (abbreviated as GMM-RW) is presented.To start with,GMM fitted by the rival penalized expectation maximization (RPEM) algorithm is employed to estimatethe posterior probabilities of each annotation keyword.Subsequently, a random walk processover the constructed label similarity graph is implemented to further mine the potential correlations ofthe candidate annotations so as to capture the refining results, which plays a crucial role in semanticbased image retrieval.The contributions exhibited in this work are multifold.First, GMM is exploitedto capture the initial semantic annotations, especially the RPEM algorithm is utilized to train themodel that can determine the number of components in GMM automatically.Second, a label similaritygraph is constructed by a weighted linear combination of label similarity and visual similarity ofimages associated with the corresponding labels, which is able to avoid the phenomena of polysemyand synonym efficiently during the image annotation process.Third, the random walk is implementedover the constructed label graph to further refine the candidate set of annotations generated byGMM.Conducted experiments on the standard Corel5k demonstrate that GMM-RW is significantlymore effective than several state-of-the-arts regarding their effectiveness and efficiency in the task of automatic image annotation.     

Ho∞-based fault detection for nonlinear networked systems with random packet dropout and probabilistic interval delay

The fault detection problem for the nonlinear networked control system (NCS) with packet dropout and delay is investigated.A nonlinear stochastic system model is proposed to account for the NCS with random packet dropout and networkinduced non-uniformly distributed time-varying delay in both from sensor to controller (S/C) and from controller to actuator (C/A).Based on the obtained NCS model,employing an observer-based fault detection filter as the residual generator,the addressed fault detection problem is converted into an auxiliary nonlinear H∞ control problem.Then,with the help of Lyapunov functional approach,a sufficient condition for the desired fault detection filter is constructed in terms of certain linear matrix inequalities,which depend on not only the delay interval but also the delay interval occurrence rate and successful packet communication rate.Especially,a trade-off phenomenon between the maximum allowable delay bound and successful data packet transmission rate is found,which is typically resulted from the limited bandwidth of communication networks.The effectiveness of the proposed method is demonstrated by a simulation example.     

门诊到住院过程中病床负荷公平性的病人路由策略

在调研分析住院病人历史数据和医院业务流程基础上,建立了病人流路由分配的单排队多服务台队列倒V模型.以病房工作负荷公平性为目标,分析了RMI(randomized most-idle)随机路由分配策略的马尔科夫过程在倒V模型中的应用,得到了系统的阻塞概率及病床占用率等相关性能指标参数,从理论上分析了RMI路由分配策略的公平性.对比了两服务台队列占用率、单位时间内服务的病人数量,结果验证了RMI策略的公平性.     

古典概型问题的数学模型

在古典概型问题中引入了n次随机试验,n维样本点,n维随机事件和n维样本空间等概念,对解决古典概型的应用问题提供了相应的数学模型.     

H_∞-based fault detection for nonlinear networked systems with random packet dropout and probabilistic interval delay

The fault detection problem for the nonlinear networked control system(NCS) with packet dropout and delay is investigated.A nonlinear stochastic system model is proposed to account for the NCS with random packet dropout and networkinduced non-uniformly distributed time-varying delay in both from sensor to controller(S/C) and from controller to actuator(C/A).Based on the obtained NCS model,employing an observer-based fault detection filter as the residual generator,the addressed fault detection problem is converted into an auxiliary nonlinear H∞ control problem.Then,with the help of Lyapunov functional approach,a sufficient condition for the desired fault detection filter is constructed in terms of certain linear matrix inequalities,which depend on not only the delay interval but also the delay interval occurrence rate and successful packet communication rate.Especially,a trade-off phenomenon between the maximum allowable delay bound and successful data packet transmission rate is found,which is typically resulted from the limited bandwidth of communication networks.The effectiveness of the proposed method is demonstrated by a simulation example.     

内燃机配气机构传动链脱节概率

以某型发动机配气机构传动链为研究对象,应用随机摄动和概率可靠性等分析方法,建立了配气机构脱节概率可靠性数学模型.当配气机构基本随机变量为正态分布时,提出了传动链脱节的可靠性分析方法.通过算例分析获得了凸轮在不同运动阶段的传动链脱节概率,以及在不同转速下的脱节失效概率,并且随着转速升高传动链发生脱节的概率也会升高,与实际情况相符合,进一步表明了所提方法的正确性.此外,通过分析脱节的原因,提出了为降低脱节概率而应采取的方法,为今后内燃机配气机构传动链的可靠性设计提供了理论依据.     

无双线性对的无证书签密方案分析与改进

对高键鑫等人提出的一种无双线性对运算的无证书签密方案进行密码分析,指出方案的不可伪造性证明存在漏洞,致使方案不安全,并提出了一个改进的签密方案.安全性能方面,为了抵抗不诚实用户发起的公钥替换攻击,改进方案在签密运算的指数部分加入用户生成的部分公钥的哈希函数值,并在随机预言模型下证明了改进方案对自适应选择消息和身份攻击是存在性不可伪造的,改进方案没有使用计算耗时的对运算,具有较高的运算效率.     

EHGFs方向可控滤波压制地震勘探随机噪声

为有效提取地震信号同相轴信息, 解决以哈密特-高斯函数(HGFs: Hemite-Gauss Functions)为核函数的方向可控滤波器因无方向性而导致同相轴被降频的问题, 引入以拉伸哈密特-高斯函数(EHGFs: Elongated Hemite-Gauss Functions)为核的方向可控滤波去噪方法。该方法考虑有效信号与随机噪声在方向性上的差异,
通过近似拟合方法构造EHGFs 方向可控滤波器, 借助EHGFs 具有明确的方向性, 滤波时沿着轴向进行滤波,提高线性度, 减少平滑作用, 取得方向滤波数据后再根据数据局部数字特征进行数据重组, 达到去噪效果。实验结果表明, 该方法具有明显压制随机噪声、恢复有效信号的效果。     

企业战略风险的模糊评价模型

基于战略风险管理的基本概念与内容,从战略风险评价角度出发,提出了一类企业战略风险的模糊评价方法.即通过分析比较传统概率风险测度的不足,将模糊评价方法用于战略风险的评价,以更能准确地反映和把握企业战略的风险程度.     

带有控制结构约束的次优状态反馈律的研究

研究了带有约束机制的次优状态反馈律,主要对终端时间tf=∞系统建立次优状态反馈的数学模型.通过简单控制结构约束的引入,消除状态变量不完全可测所造成的障碍,从而得到了带控制结构约束的次优必要条件及改进后的迭代算法.