结构正则化多视图非负矩阵分解

现存非负矩阵分解（non-negative matrix factorization,NMF）研究多考虑单一视图分解数据,忽略了数据信息的全面性。此外,NMF限制其获取数据的内在几何结构。针对以上问题,提出一个结构正则化多视图非负矩阵分解算法（structure regularized multi-view nonnegative matrix factorization,SRMNMF）。首先,通过主成分分析来对数据进行全局结构的判别式学习;其次,利用流形学习来捕获数据的局部结构;然后,通过利用多视图数据的多样性和差异性来学习表征。模型提升了算法聚类的整体性能,更加有效地挖掘数据的结构信息。此外,采用高效的交替迭代算法优化目标函数得到最优的因子矩阵。在六个数据集上与现存的代表性方法比较,所提出的SRMNMF的准确率、NMI和Purity分别最大提高4.4%、6.1%和4.05%。     

改进的非负稀疏编码神经网络模型及其应用

提出了一种改进的基于NIG（Normal Inverse Gaussian）密度和稳健主成分分析（PCA）的非负稀疏编码（NNSC）神经网络模型,该模型实质上实现了一个二阶段的学习过程。并利用这个模型成功地建模了视觉感知系统V1区的感受野。该NNSC模型具有很强的自适应于自然数据统计特性的能力。另外,利用类似小波收缩法去噪原理,该模型能够有效地去除图像中的高斯加性噪声,对自然图像编码的仿真实验也表明了该模型在生物学上的合理性和可行性。     

Profit-oriented partial disassembly line design: dealing with hazardous parts and task processing times uncertainty

This paper addresses the problem of profit-oriented disassembly line design and balancing considering partial disassembly, presence of hazardous parts and uncertainty of task processing times. Few papers have studied the stochastic disassembly line balancing problem and existing approaches have focused on heuristic and metaheuristic methods. Most existing work has concentrated on complete disassembly where task times are assumed to be normal random variables and where AND/OR graphs are not considered. The objective of this paper is the design of a serial line that obtains the maximum revenue and then balances the workload under uncertainty. The processing time of a disassembly task is assumed to be a random variable with any known probability distribution. An AND/OR graph is used to model the precedence relationships among tasks. Stochastic programming models and exact-based solution approaches combining the L-shaped algorithm and Monte Carlo sampling techniques are proposed. The relevance and applicability of the proposed models and solution methods are shown by solving efficiently a set of disassembly problem instances from the literature.     

Stability criteria for neutral systems with time‐varying delays and nonlinear uncertainties

Abstract

The asymptotic stability problem for a class of neutral systems with time‐varying delays and nonlinear uncertainties is investigated in this paper. LMI‐based delay‐dependent criteria are proposed to guarantee the asymptotic stability of the considered systems. New Lyapunov‐Krasovskii functional and Leibniz‐Newton formulae are used to find the delay‐dependent stability results. Finally, some numerical examples are illustrated to show the improved results from using this method.     

新安江模型参数有效优化及不确定性评估

应用新安江模型进行水文模拟时,由于模型本身的不足及参数多、信息量少等原因,会出现率定的最优参数组不唯一、不稳定等问题。考虑到以往的参数优选,都只得出一个参数组,不能反映出其不确定性状况。提出应用基于马尔可夫链蒙特卡罗(MCMC)理论的SCEM-UA算法,通过双牌流域以1 h为时段间隔的36场典型洪水数据对新安江模型参数进行优选和不确定性评估。结果表明,该算法能很好地推出新安江模型参数的后验概率分布;率定和检验结果分析也表明,应用SCEM-UA算法对新安江模型进行优选和不确定评估是有效和可行的。     

基于Markov理论的改进灰色GM(1,1)预测模型研究

在灰色预测的基础上,引入马尔可夫链预测理论,建立了灰色马尔可夫预测模型.它是将灰色预测模型与马尔可夫预测方法优化组合,用灰色预测模型预测随机时间序列数据的总体发展趋势,而用马尔可夫链模型预测各数据在总体趋势下的随机波动性变化,得到随机时间序列趋势预测模型的解.通过公路运输实际数据进行了验证,结果表明:灰色马尔可夫预测模...     

Backward Inference in Bayesian Networks for Distributed Systems Management

The growing complexity of distributed systems in terms of hardware components, operating system, communication and application software and the huge amount of dependencies among them have caused an increase in demand for distributed management systems. An efficient distributed management system needs to work effectively even in face of incomplete management information, uncertain situations, and dynamic changes. In this paper, Bayesian networks are proposed to model dependencies between managed objects in distributed systems. The strongest dependency route (SDR) algorithm is developed for backward inference in Bayesian networks. The SDR algorithm can track the strongest causes and trace the strongest routes between particular effects and its causes, the strongest dependency of causes can be also achieved by the algorithm. Thus, the backward inference provides an efficient mechanism in fault locating, and is beneficial for performance management.     

气相色谱-质谱法测定葡萄中苯醚甲环唑的不确定度评定

目的：评定气相色谱-质谱法测定葡萄中苯醚甲环唑时的不确定度。方法：根据GB 23200.8—2016 《食品安全国家标准 水果和蔬菜中500种农药及相关化学品残留量的测定 气相色谱-质谱法》建立模型,根据JJF 1059.1—2012《测量不确定评定和表示》对不确定度来源进行分析量化。结果：本方法测定苯醚甲环唑的合成不确定度为2.258%,扩展不确定度为0.0451,葡萄中苯醚甲环唑测定结果为（0.06047±0.00273）mg/kg,k=2。结论：本方法不确定度主要来源为标准溶液配制及其曲线拟合,重复性测定对实验结果准确性影响较小。     

一种基于响应面的翼型鲁棒优化设计方法

针对不确定因素引起的翼型气动性能波动现象,探讨了翼型几何形状随机不确定波动对翼型气动特性的影响,并进行了减小此影响的鲁棒优化设计。引入类别形状函数变换(CST)方法可以大大降低设计变量自由度数目,以NACA0012翼型为例,进行了考虑翼型几何形状随机扰动的气动不确定性分析,发现几何形状的微小波动对升力特性影响很小。发展了一种基于响应面和遗传算法的鲁棒优化设计方法,能够高效的减小阻力及其波动的影响。计算结果显示尽管相对于确定性优化结果鲁棒优化阻力略有增加,但波动更小,气动性能具有更好的鲁 棒性。     

弱非线性和不确定性对结构动力学分析的影响

局部连接引起的弱非线性和加工制造公差引起的参数变化不确定性是许多工程结构的常见现象。针对弱非线性和参数变化不确定性对结构动力学分析的影响进行了讨论,提出了一种通过恒位移和恒速度响应的振动试验进行非线性建模,并用统计分析来处理不确定性,建立尽可能精确的数学模型进行结构动力学分析的处理方法。仿真实例是在对美国Sandia国家实验室2006年提出的"结构动力学问题的模型确认挑战"研究的基础上,建立的具有非线性刚度和非线性阻尼以及参数变化不确定性的三自由度集中质量模型,仿真结果验证了方法的有效性。