Inference for longitudinal data with nonignorable nonmonotone missing responses

For the analysis of longitudinal data with nonignorable and nonmonotone missing responses, a full likelihood method often requires intensive computation, especially when there are many follow-up times. The authors propose and explore a Monte Carlo method, based on importance sampling, for approximating the maximum likelihood estimators. The finite-sample properties of the proposed estimators are studied using simulations. An application of the proposed method is also provided using longitudinal data on peptide intensities obtained from a proteomics experiment of trauma patients.     

Fast cross-validation of high-breakdown resampling methods for PCA

Cross-validation (CV) is a very popular technique for model selection and model validation. The general procedure of leave-one-out CV (LOO-CV) is to exclude one observation from the data set, to construct the fit of the remaining observations and to evaluate that fit on the item that was left out. In classical procedures such as least-squares regression or kernel density estimation, easy formulas can be derived to compute this CV fit or the residuals of the removed observations. However, when high-breakdown resampling algorithms are used, it is no longer possible to derive such closed-form expressions. High-breakdown methods are developed to obtain estimates that can withstand the effects of outlying observations. Fast algorithms are presented for LOO-CV when using a high-breakdown method based on resampling, in the context of robust covariance estimation by means of the MCD estimator and robust principal component analysis. A robust PRESS curve is introduced as an exploratory tool to select the number of principal components. Simulation results and applications on real data show the accuracy and the gain in computation time of these fast CV algorithms.     

Stochastic sampling design using a multi-objective genetic algorithm and adaptive neural networks

This paper presents a novel multi-objective genetic algorithm (MOGA) based on the NSGA-II algorithm, which uses metamodels to determine optimal sampling locations for installing pressure loggers in a water distribution system (WDS) when parameter uncertainty is considered. The new algorithm combines the multi-objective genetic algorithm with adaptive neural networks (MOGA–ANN) to locate pressure loggers. The purpose of pressure logger installation is to collect data for hydraulic model calibration. Sampling design is formulated as a two-objective optimization problem in this study. The objectives are to maximize the calibrated model accuracy and to minimize the number of sampling devices as a surrogate of sampling design cost. Calibrated model accuracy is defined as the average of normalized traces of model prediction covariance matrices, each of which is constructed from a randomly generated sampling set of calibration parameter values. This method of calculating model accuracy is called the ‘full’ fitness model. Within the genetic algorithm search process, the full fitness model is progressively replaced with the periodically (re)trained adaptive neural network metamodel where (re)training is done using the data collected by calling the full model. The methodology was first tested on a hypothetical (benchmark) problem to configure the setting requirement. Then the model was applied to a real case study. The results show that significant computational savings can be achieved by using the MOGA–ANN when compared to the approach where MOGA is linked to the full fitness model. When applied to the real case study, optimal solutions identified by MOGA–ANN are obtained 25 times faster than those identified by the full model without significant decrease in the accuracy of the final solution.     

Fast neural networks without multipliers

Multilayer perceptrons (MLPs) with weight values restricted to powers of two or sums of powers of two are introduced. In a digital implementation, these neural networks do not need multipliers but only shift registers when computing in forward mode, thus saving chip area and computation time. A learning procedure, based on backpropagation, is presented for such neural networks. This learning procedure requires full real arithmetic and therefore must be performed offline. Some test cases are presented, concerning MLPs with hidden layers of different sizes, on pattern recognition problems. Such tests demonstrate the validity and the generalization capability of the method and give some insight into the behavior of the learning algorithm     

基于在线社交网络的JPS跳跃并行顶点采样方法

针对现有在线社交网络（OSNs）采样方法无法有效地应用于低连通性的社交网络，且采集的样本顶点平均度严重偏离原始社交网络、顶点过度采样等问题，本文基于蒙特卡罗随机游走（MHRW）采样方法，引入双重跳跃策略、并行机制和顶点缓存区，提出一种跳跃无偏并行顶点（JPS）采样方法。将在线社交网络数据集建模为包含顶点和边的社交图进行模拟采样，利用Python/Matplotlib绘图库绘制采集的样本顶点属性图。实验结果表明,该采样方法更有效地应用于不同连通强度的社交图，提高了采样过程中的顶点更新率，降低了样本顶点的平均度偏差且能够更快速地收敛。     

基于运动空间相关性和时间连续性的运动估算快速算法

运动估算是视频信号的帧间预测编码中的一个重要环节,其效率和精度直接影响到编码器的性能。由于全搜索算法搜索速度较低,而很少采用,故目前普遍采用三步法、交叉法等各种快速近似算法,但是这些算法匹配精度较低,而且某些情况下应用效果不好。为解决上述算法存在的问题,在对视频编码中运动物体的空间相关性和时间连续性进行分析的基础上,给出了一种利用运动物体的空间相关性和时间连续性来进行运动估算的快速算法。实验结果表明,该算法计算每个宏块运动矢量所需的平均搜索次数低于三步法,而匹配精度则非常接近于全搜索算法,并且采用该算法的编码器,其总的编码输出位数少于采用全搜索算法的编码器。     

基于CUDA的GMM模型快速训练方法及应用

由于能够很好地近似描述任何分布,混合高斯模型(GMM)在模式在识别领域得到了广泛的应用.GMM模型参数通常使用迭代的期望最大化(EM)算法训练获得,当训练数据量非常庞大及模型混合数很大时,需要花费很长的训练时间.NVIDIA公司推出的统一计算设备架构(Computed unified device architecture,CUDA)技术通过在图形处理单元(GPU)并发执行多个线程能够实现大规模并行快速计算.本文提出一种基于CUDA,适用于特大数据量的GMM模型快速训练方法,包括用于模型初始化的K-means算法的快速实现方法,以及用于模型参数估计的EM算法的快速实现方法.文中还将这种训练方法应用到语种GMM模型训练中.实验结果表明,与Intel DualCore PentiumⅣ3.0 GHz CPU的一个单核相比,在NVIDIA GTS250 GPU上语种GMM模型训练速度提高了26倍左右.     

A Fast Procedure for Calculating Importance Weights in Bootstrap Sampling

Importance sampling is an efficient strategy for reducing the variance of certain bootstrap estimates. It has found wide applications in bootstrap quantile estimation, proportional hazards regression, bootstrap confidence interval estimation, and other problems. Although estimation of the optimal sampling weights is a special case of convex programming, generic optimization methods are frustratingly slow on problems with large numbers of observations. For instance, interior point and adaptive barrier methods must cope with forming, storing, and inverting the Hessian of the objective function. In this paper, we present an efficient procedure for calculating the optimal importance weights and compare its performance to standard optimization methods on a representative data set. The procedure combines several potent ideas for large-scale optimization.     

A computation-efficient on-line training algorithm for neurofuzzy networks

Neurofuzzy networks are often used to model linear or nonlinear processes, as they can provide some insights into the underlying processes and can be trained using experimental data. As the training of the networks involves intensive computation, it is often performed off line. However, it is well known that neurofuzzy networks trained off line may not be able to cope successully with time-varying processes. To overcome this problem, the weights of the networks are trained on line. In this paper, an on-line training algorithm with a computation time that is linear in the number of weights is derived by making full use of the local change property of neurofuzzy networks. It is shown that the estimated weights converge to that obtained from the least-squares method, and that the range of the input domain can be extended without retraining the network. Furthermore, it has a better ability in tracking time-varying systems than the recursive least-squares method, since in the proposed algorithm a positive definite submatrix is added to the relevant part of the covariance matrix. The performance of the proposed algorithm is illustrated by simulation examples and compared with that obtained using the recursive least-squares method.     

传感器网络中的分布式滚动时域状态估计

利用分布式滚动时域方法对无线传感器网络的状态估计问题进行研究,给出了基于量化测量值的滚动时域估计算法。在无线传感器网络的环境下处理分布式状态估计问题时,减少通信的成本是非常重要的一个环节,需要将观测值量化后再传送。以往的滚动时域估计方法无法处理量化观测值的状态估计问题,而本文的方法考虑了最严格的观测值量化情况即传感器只发送一个比特至融合中心的状态估计问题。与其它传感器网络中的状态估计方法相比,该方法减少了每一步的计算量。仿真结果验证了该算法的有效性。     

On sampling controlled stochastic approximation

The authors examine a novel class of stochastic approximation procedures which are based on carefully controlling the number of observations or measurements taken before each computational iteration. This method, referred to as sampling controlled stochastic approximation, has advantages over standard stochastic approximation such as requiring less computation and the ability to handle bias in estimation. The authors address the growth rate required of the number of samples and prove a general convergence theorem for the proposed stochastic approximation method. In addition, they present applications to optimize and also derive a sampling controlled version of the classic Robbins-Munro algorithm     

基于Bootstrap采样粒子滤波的WirelessHART时间同步算法﹡

针对无线HART传感器网络时间同步精度较低、能耗过大等问题,提出了一种基于Bootstrap采样的粒子滤波时间同步算法。在未知网络延迟分布的情况下,为了减少观测次数,对发送端和接收端的时间戳观测值进行Bootstrap采样,采用混合粒子滤波算法,获得精确的时钟偏移,从而不仅降低了无线HART传感网络时间同步误差,而且使能耗减小。最后,实验表明,对于无线HART网状分层网络,当观测量达到10以上时,粒子滤波算法获得的时间偏差的均方误差约是最大似然估计算法的50%,而基于Bootstrap采样的粒子滤波算法获得的时间偏差的均方误差约是最大似然估计算法的35%,仿真的结果验证了该方法的可行性和有效性。     

Input Disturbance Estimation For Linear Systems in The Bounded Noise Context

A method is presented for constructing input disturbance estimates for a linear system using noisy observations. The input disturbance of the dynamic system and the observation noise are assumed to be unknown but bounded. In addition, the structural characteristics of the input disturbance are given in the form of the maximum possible change of its magnitude per sampling time. The input disturbance represents a wide category of system uncertainties. A recursive procedure for obtaining disturbance set estimates is derived. The procedure is easy to implement and is a competitive technique comparative to the classical estimation schemes. Simulation results demonstrate the performance of the given techniques.     

基于均值漂移和联合粒子滤波的移动节点定位算法

针对无线传感器网络移动节点定位面临的高精度和实时性要求,把均值漂移算法引入联合粒子滤波(Joint ParticleFilter)框架.提出了基于均值漂移和联合粒子滤波的移动节点定位算法.它使用均值漂移算法构建粒子滤波的建议分布,通过有效利用最新观测信息,提高粒子状态估计的准确性,使得采样粒子的状态分布与后验概率分布更接近,减少了状态估计必需的粒子数目.该算法还提出了基于虚拟海明距离和交互势的权重计算方式,减少相邻移动节点间的干扰.仿真实验结果表明,基于均值漂移算法和联合粒子滤波的移动节点定位,可获得比基本粒子滤波更高的定位精度,其定位精度与无味粒子滤波(Uscented Particle Filter)相当,而计算开销比无味粒子滤波减小至少50%.     

Know by a handful the whole sack: efficient sampling for top-k influential user identification in large graphs

Influence Maximization aims to find the top-K influential individuals to maximize the influence spread within a social network, which remains an important yet challenging problem. Most existing greedy algorithms mainly focus on computing the exact influence spread, leading to low computational efficiency and limiting their application to real-world social networks. While in this paper we show that through supervised sampling, we can efficiently estimate the influence spread at only negligible cost of precision, thus significantly reducing the execution time. Motivated by this, we propose ESMCE, a power-law exponent supervised Monte Carlo estimation method. In particular, ESMCE exploits the power-law exponent of the social network to guide the sampling, and employs multiple iterative steps to guarantee the estimation accuracy. Moreover, ESMCE shows excellent scalability and well suits large-scale social networks. Extensive experiments on six real-world social networks demonstrate that, compared with state-of-the-art greedy algorithms, ESMCE is able to achieve almost two orders of magnitude speedup in execution time with only negligible error (2.21 % on average) in influence spread.     

在大型数据集中挖掘相关关系的算法

为了挖掘对象间的相关关系,建立对象间的相关关系网,该文提出了一种基于传递闭包聚类法挖掘相关关系的方法。为使方法高效、实用,对方法中相似阵及等价阵的计算,文章给出了计算等价阵的一种贪心算法-最大树法、计算相似阵的嵌套循环算法(RNL)及渐进式嵌套循环算法(IRNL)。RNL算法有效减少了大型数据库的I/O开销。当数据库中的数据增加时,使用IRNL算法能够充分利用原来的挖掘结果,避免了原有对象间相关度的重复计算,从而提高了整个挖掘过程的效率。     

Simulation for passage times in closed, multiclass networks of queues with unrestricted priorities

Regenerative simulation for passage times in networks of queues with priorities among job classes (and one or more job types) can be based on observation of a fully augmented job stack process which maintains the position of each of the jobs in a linear ‘job stack’, an enumeration of the jobs by service center and job class. In this paper we develop an estimation procedure for passage times through a subnetwork of queues. Observed passage times for all the jobs enter into the construction of point and interval estimates. The confidence intervals obtained using this estimation procedure are shorter than those obtained from simulation using a marked job.     

基于事件捕获的无线传感网络节点能耗实时估计

无线传感网络节点能耗的动态估计对于延长网络的寿命非常关键。针对无线传感网络节点的实时能耗估计,以运行TinyOS的MICAz节点作为目标平台,对TinyOS进行了功能扩展,用nesC语言设计了一个基于事件捕获的能耗估计模块。采用数据采集卡对各硬件模块的功耗模型进行了标定,实验结果表明该方法的时间和空间开销较小,估计精度约为4%。     

Event-triggered nonlinear consensus in directed multi-agent systems with combinational state measurements

Event-triggered sampling control is motivated by the applications of embedded microprocessors equipped in the agents with limited computation and storage resources. This paper studied global consensus in multi-agent systems with inherent nonlinear dynamics on general directed networks using decentralised event-triggered strategy. For each agent, the controller updates are event-based and only triggered at its own event times by only utilising the locally current sampling data. A high-performance sampling event that only needs local neighbours’ states at their own discrete time instants is presented. Furthermore, we introduce two kinds of general algebraic connectivity for strongly connected networks and strongly connected components of the directed network containing a spanning tree so as to describe the system's ability for reaching consensus. A detailed theoretical analysis on consensus is performed and two criteria are derived by virtue of algebraic graph theory, matrix theory and Lyapunov control approach. It is shown that the Zeno behaviour of triggering time sequence is excluded during the system's whole working process. A numerical simulation is given to show the effectiveness of the theoretical results.     

State Dependent Parameter metamodelling and sensitivity analysis

In this paper we propose a general framework to deal with model approximation and analysis. We present a unified procedure which exploits sampling, screening and model approximation techniques in order to optimally fulfill basic requirements in terms of general applicability and flexibility, efficiency of estimation and simplicity of implementation. The sampling procedure applies Sobol' quasi-Monte Carlo sequences, which display optimal characteristics when linked to a screening procedure, such as the elementary effect test. The latter method is used to reduce the dimensionality of the problem and allows for a preliminary sorting of the factors in terms of their relative importance. Then we apply State Dependent Parameter (SDP) modelling (a model estimation approach, based on recursive filtering and smoothing estimation) to build an approximation of the computational model under analysis and to estimate the variance based sensitivity indices. The method is conceptually simple and very efficient, leading to a significant reduction in the cost of the analysis. All measures of interest are computed using a single set of quasi-Monte Carlo runs. The approach is flexible because, in principle, it can be applied with any available type of Monte Carlo sample.