基于改进的圆投影向量的背景补偿方法

针对传统运动背景补偿算法难以适应大角度旋转的应用场合,提出了一种改进的圆投影向量的背景补偿方法。该算法首先利用图像熵自动选择合适的图像参考块,以增强算法的实用性;其次对传统的圆投影向量进行了改进,增加了相位向量以获取背景的旋转参量,并采用核函数定义各像素点的距离权值,从而可以获得更加准确的结果。最后给出了算法步骤,并利用实测数据进行验证。通过仿真实验证明了该算法在各种场景、各种运动情况下的有效性以及对噪声、光照等因素具有鲁棒性。     

模糊检索系统研究

模糊性是人类思维和客观事物普遍具有的属性之一。为了克服现行计算机信息系统的局限性 ,模糊检索应运而生。运用模糊技术开发的计算机信息系统既允许用户用自然语言进行信息查询 ,又能给出输出信号项与用户查询的关联度 ,协助用户完成信息处理任务 ,因而具有一定的人脑进行模糊信息处理的能力。简要讨论了模糊检索系统的结构 ,模糊知识库及其管理 ,模糊数据库的组织等。     

含区间参数的战场资源动态调度模型及算法

战场资源调度是作战指挥领域研究的热点.首先描述了战场资源调度问题,分析了战场资源动态调度需求,在此基础上建立了包含区间参数的战场资源动态调度模型.然后设计了三种不同的贪心策略,分别为基本贪心策略、双重贪心策略和一致贪心策略,提出了模型求解的混合贪心算法.最后结合联合作战算例进行了仿真验证,结果表明本文方法可行优越,能应用于不确定性的战场环境中.     

舰船装备维修费单项预测集对分析与组合建模

根据集对分析的基本原理,结合基于误差大小的集对分析组合预测,给出了基于误差方向的集对分析组合预测和基于模型性能的集对分析组合预测;针对基于误差大小的集对分析组合预测建模过程中,从关联度的确定到组合权重的计算过程相对复杂、难以理解,推导简化了组合预测权重计算过程;针对集对分析中同一度为0时导致组合预测模型信息丢失的问题,提出了一种基于折扣的同一度、差异度、对立度转换处理方法。最后算例说明了该方法的有效性。     

准循环LDPC好码设计

现有准循环(QC)LDPC码的设计未考虑避免短环问题与校验矩阵的行相关问题.第一个问题使准循环LDPC码的误码率性能远低于随机LDPC码,第二个问题使得构造生成矩阵非常困难.为解决第一个问题,提出避免短环的准循环LDPC码的设计约束条件,根据四、六环检验结果调整校验矩阵中循环子矩阵的维数和移位因子.为解决第二个问题,提出一种不规则准循环LDPC码的设计方法,该方法将校验矩阵中的特定位置的子矩阵用零矩阵和循环矩阵置换,获得一非奇异方阵,用于构造生成矩阵.虽然在校验矩阵中采用双对角线子矩阵可解决校验矩阵的行相关问题,但是会产生低码重的码字,导致误码率性能不能随码长增加而提高.计算机仿真结果表明,设计的准循环LDPC码具有良好的误码率性能.     

Robust H∞ filtering for discrete-time systems with Markovian switching and time-delays

The robust H∞ filtering problem for uncertain discrete-time Markovian jump linear systems with modedependent time-delays is investigated. Attention is focused on designing a Markovian jump linear filter that ensures robust stochastic stability while achieving a prescribed H∞ performance level of the resulting filtering error system, for all admissible uncertainties. The key features of the approach include the introduction of a new type of stochastic Lyapunov functional and some free weighting matrix variables. Sufficient conditions for the solvability of this problem are obtained in terms of a set of linear matrix inequalities. Numerical examples are provided to demonstrate the reduced conservatism of the proposed approach.     

Portfolio Selection with Different Borrowing-Lending Rates: Utility Maximization Model based on Mean and VaR

This article investigates a portfolio selection problem with different borrowing–lending rates and with Value-at-Risk (VaR) as the measure of risk. The problem is formulated as a utility maximization model with a general utility function that is a function of only the mean and the VaR of portfolio return. Several properties of the efficient frontier of the mean-VaR model are first obtained and then used to give some existence conditions and characterizations of the optimal solution to the utility maximization model. Further, a solution method and a numerical algorithm for solving the optimal solution are proposed. Finally, a numerical example using the real data of Chinese stock market is given to show the validity and the practicability of these results.     

分数布朗运动下欧式汇率期权的定价

应用风险偏好和均衡定价方法,考虑了标的资产服从分数布朗运动下的汇率期权定价问题.首先利用条件期望构建了条件过 程的联合密度函数, 然后,基于历史有限信息推导出分数欧式汇率期权的闭式解. 为了理解定价模型,进一步分析了赫斯特指数对定价 结果的影响. 最后,给出了基于GBP/USD期权的实证研究.不同模型的结果说明了汇率市场具有分形特性.     

基于D2D通信的蜂窝数据分流补偿机制设计

设备到设备(device to device,D2D)通信允许邻近用户使用蜂窝网络频段直接通信,既能分流部分蜂窝数据,减轻基站负担,又能提升服务质量。但由于信息不对称,蜂窝网络不知道用户的类型参数,无法准确提供合理补偿,以激励用户参与数据分流。基于契约理论设计了一种分流补偿机制,首先设计蜂窝网络收益函数和分流用户代价函数及其二者的效用;然后基于用户类型参数服从均匀分布设计补偿机制,验证了该机制能满足个人理性和激励相容条件,分析了该机制的最优性能;最后与正比例补偿机制和完全信息补偿机制进行对比仿真,结果表明,本文设计的分流补偿机制既能保证用户愿意参与数据分流,也鼓励用户报告自身真实的类型参数,还能获得接近于完全信息补偿机制下的效用和性能。     

Multi-label dimensionality reduction and classification with extreme learning machines

In the need of some real applications, such as text categorization and image classification, the multi-label learning gradually becomes a hot research point in recent years. Much attention has been paid to the research of multi-label classification algorithms. Considering the fact that the high dimensionality of the multi-label datasets may cause the curse of dimensionality and wil hamper the classification process, a dimensionality reduction algorithm, named multi-label kernel discriminant analysis （MLKDA）, is proposed to reduce the dimensionality of multi-label datasets. MLKDA, with the kernel trick, processes the multi-label integrally and realizes the nonlinear dimensionality reduction with the idea similar with linear discriminant analysis （LDA）. In the classification process of multi-label data, the extreme learning machine （ELM） is an efficient algorithm in the premise of good accuracy. MLKDA, combined with ELM, shows a good performance in multi-label learning experiments with several datasets. The experiments on both static data and data stream show that MLKDA outperforms multi-label dimensionality reduction via dependence maximization （MDDM） and multi-label linear discriminant analysis （MLDA） in cases of balanced datasets and stronger correlation between tags, and ELM is also a good choice for multi-label classification.