检索结果-内蒙古大学图书馆

BIOMETRIKA 2017年第3期104卷 649-663页

作者： Srivastava, Sanvesh Engelhardt, Barbara E. Dunson, David B. Univ Iowa Dept Stat & Actuarial Sci 241 Schaeffer Hall20 East Washington St Iowa City IA 52242 USA Princeton Univ Dept Comp Sci Ctr Stat & Machine Learning 35 Olden St Princeton NJ 08540 USA Duke Univ Dept Stat Sci Box 90251 Durham NC 27708 USA

Bayesian sparse factor models have proven useful for characterizing dependence in multivariate data, but scaling computation to large numbers of samples and dimensions is problematic. We propose expandable factor analysis for scalable inference in factor models when the number of factors is unknown. The method relies on a continuous shrinkage prior for efficient maximum a posteriori estimation of a low-rank and sparse loadings matrix. The structure of the prior leads to an estimation algorithm that accommodates uncertainty in the number of factors. We propose an information criterion to select the hyperparameters of the prior. Expandable factor analysis has better false discovery rates and true positive rates than its competitors across diverse simulation settings. We apply the proposed approach to a gene expression study of ageing in mice, demonstrating superior results relative to four competing methods.

关键词： expectation-maximization algorithm Factor analysis Shrinkage prior Sparsity Variable selection

来源：评论

学校读者我要写书评

暂无评论

Item selection by latent class-based methods: an application to nursing home evaluation

引用

ADVANCES IN DATA ANALYSIS AND CLASSIFICATION 2016年第2期10卷 245-262页

作者： Bartolucci, Francesco Montanari, Giorgio E. Pandolfi, Silvia Univ Perugia Dept Econ I-06100 Perugia Italy Univ Perugia Dept Polit Sci I-06100 Perugia Italy

The evaluation of nursing homes is usually based on the administration of questionnaires made of a large number of polytomous items to their patients. In such a context, the latent class model represents a useful tool for clustering subjects in homogenous groups corresponding to different degrees of impairment of the health conditions. It is known that the performance of model-based clustering and the accuracy of the choice of the number of latent classes may be affected by the presence of irrelevant or noise variables. In this paper, we show the application of an item selection algorithm to a dataset collected within a project, named ULISSE, on the quality-of-life of elderly patients hosted in Italian nursing homes. This algorithm, which is closely related to that proposed by Dean and Raftery in 2010, is aimed at finding the subset of items which provides the best clustering according to the Bayesian Information Criterion. At the same time, it allows us to select the optimal number of latent classes. Given the complexity of the ULISSE study, we perform a validation of the results by means of a sensitivity analysis, with respect to different specifications of the initial subset of items, and of a resampling procedure.

关键词： Bayesian information criterion expectation-maximization algorithm Polytomous items Quality-of-life ULISSE project

来源：评论

学校读者我要写书评

暂无评论

Mathematical characterization of spatiotemporal congested traffic patterns: mixed speed data analysis in the greater Toronto and Hamilton area, Canada

引用

TRANSPORTATION PLANNING AND TECHNOLOGY 2016年第3期39卷 318-328页

作者： Kyriakopoulou, Natalia Photis, Yorgos N. Kanaroglou, Pavlos Natl Tech Univ Athens Sch Rural & Surveying Engn 9 Iroon PolytechZographou Campus Athens 15780 Greece McMaster Univ Sch Geog & Earth Sci Ctr Spatial Anal CSpA Hamilton ON L8S 4K1 Canada

This paper formulates a comprehensive methodology for analyzing, quantifying and identifying congestion characteristics based on speed distribution. Utilizing vehicle speed data, a mathematical approach is applied, in order to characterize roadway segments, in terms of travel reliability, congestion severity and duration. We argue that the Gaussian mixture model (GMM) and its parameter combination is the appropriate tool if we are to obtain quantitative congestion measures and rank roadway performance. A significant contribution of our approach is that it is based on assumptions regarding mixed components as well as speed distribution and can be applied to large databases. We test our framework on the greater Toronto and Hamilton area in Ontario, Canada, and conclude that congestion quantification through the application of the GMM can be successfully accomplished. Results indicate that speed patterns differ significantly between counties as well as days of the week.

关键词： bimodal distribution expectation-maximization algorithm Traffic congestion Gaussian mixture model

来源：评论

学校读者我要写书评

暂无评论

Stochastic Short-term High-resolution Prediction of Solar Irradiance and Photovoltaic Power Output

Stochastic Short-term High-resolution Prediction of Solar Ir...

引用

North American Power Symposium (NAPS)

作者： Olama, Mohammed Melin, Alex Dong, Jin Djouadi, Seddik Zhang, Yichen Oak Ridge Natl Lab Computat Sci & Engn Div Oak Ridge TN 37831 USA Oak Ridge Natl Lab Elect & Elect Syst Res Div Oak Ridge TN 37831 USA Oak Ridge Natl Lab Energy & Transportat Sci Div Oak Ridge TN 37831 USA Univ Tennessee Dept Elect Engn & Comp Sci Knoxville TN 37996 USA

ISBN: (纸本)9781538626993

The increased penetration of solar photovoltaic (PV) energy sources into electric grids has increased the need for accurate modeling and prediction of solar irradiance and power production. Existing modeling and prediction techniques focus on long-term low-resolution prediction over minutes to years. This paper examines the stochastic modeling and short-term high-resolution prediction of solar irradiance and PV power output. We propose a stochastic state-space model to characterize the behaviors of solar irradiance and PV power output. This prediction model is suitable for the development of optimal power controllers for PV sources. A filter-based expectation-maximization and Kalman filtering mechanism is employed to estimate the parameters and states in the statespace model. The mechanism results in a finite dimensional filter which only uses the first and second order statistics. The structure of the scheme contributes to a direct prediction of the solar irradiance and PV power output without any linearization process or simplifying assumptions of the signal's model. This enables the system to accurately predict small as well as large fluctuations of the solar signals. The mechanism is recursive allowing the solar irradiance and PV power to be predicted online from measurements. The mechanism is tested using solar irradiance and PV power measurement data collected locally in our laboratory.

关键词： Photovoltaics solar variability distributed energy resources stochastic prediction state-space model Kalman filter expectation-maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Cross-View Action Recognition Based on a Statistical Translation Framework

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2016年第8期26卷 1461-1475页

作者： Wang, Jing Zheng, Huicheng Gao, Jinyu Cen, Jiepeng Sun Yat Sen Univ Sch Informat Sci & Technol Guangzhou 510275 Guangdong Peoples R China

Actions captured under view changes pose serious challenges to modern action recognition methods. In this paper, we propose an effective approach for cross-view action recognition based on a statistical translation framework, which boils down to estimation of visual word transfer probabilities across views. Specifically, local features are extracted from action video frames and form bags of words based on k-means clustering. Though the appearance of an action may vary due to view changes, the underlying transfer tendency between visual words across views can be exploited. We propose two methods to measure the visual-word-based transfer relationship that are eventually based on frequency counts of word pairs. In the first method, word transfer probabilities are estimated by maximizing the likelihood of a shared action set with the EM algorithm. In the second method, word transfer probabilities are estimated by using likelihood-ratio tests. The two methods achieve comparable results and perform better when they are combined. For cross-view action classification, we compute action transfer probabilities based on the estimated word transfer probabilities and then implement a K-NN-like classification based on action video transfer probabilities. We verified our method on the public multiview IXMAS dataset and the WVU dataset. Promising results are obtained compared with state-of-the-art methods.

关键词： Cross-view action recognition expectation-maximization algorithm log-likelihood-ratio tests statistical machine translation transfer probabilities

来源：评论

学校读者我要写书评

暂无评论

A New Semiparametric Finite Mixture Model-Based Adaptive Arithmetic Coding for Lossless Image Compression

引用

CIRCUITS SYSTEMS AND SIGNAL PROCESSING 2016年第4期35卷 1163-1186页

作者： Masmoudi, Atef Masmoudi, Afif Puech, William Natl Engn Sch Sfax Lab Elect & Technol Informat Sfax Tunisia Univ Montpellier I CNRS UMR 5506 LIRMM F-34392 Montpellier 05 France Univ Sfax Fac Sci Sfax Lab Probabil & Stat Sfax Tunisia

In this paper, we propose a new approach for block-based lossless image compression by defining a new semiparametric finite mixture model-based adaptive arithmetic coding. Conventional adaptive arithmetic encoders start encoding a sequence of symbols with a uniform distribution, and they update the frequency of each symbol by incrementing its count after it has been encoded. When encoding an image row by row or block by block, conventional adaptive arithmetic encoders provide the same compression results. In addition, images are normally non-stationary signals, which means that different areas in an image have different probability distributions, so conventional adaptive arithmetic encoders which provide probabilities for the whole image are not very efficient. In the proposed compression scheme, an image is divided into non-overlapping blocks of pixels, which are separately encoded with an appropriate statistical model. Hence, instead of starting to encode each block with a uniform distribution, we propose to start with a probability distribution which is modeled by a semiparametric mixture obtained from the distributions of its neighboring blocks. The semiparametric model parameters are estimated through maximum likelihood using the expectation-maximization algorithm in order to maximize the arithmetic coding efficiency. The results of comparative experiments show that we provide significant improvements over conventional adaptive arithmetic encoders and the state-of-the-art lossless image compression standards.

关键词： Arithmetic coding Semiparametric mixture models expectation-maximization algorithm Lossless image compression

来源：评论

学校读者我要写书评

暂无评论

Supervised Latent Factor Analysis for Process Data Regression Modeling and Soft Sensor Application

引用

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY 2016年第3期24卷 1004-1011页

作者： Ge, Zhiqiang Zhejiang Univ Coll Control Sci & Engn State Key Lab Ind Control Technol Hangzhou 310027 Zhejiang Peoples R China

This brief proposed a new supervised latent factor analysis (FA) method for process data regression modeling. Different from the traditional principal component analysis/regression model, the new model can successfully estimate heterogeneous variances from different process variables, which is more practical. Under the same probabilistic modeling framework, the single supervised latent FA model is further extended to the mixture form. Efficient expectation-maximization algorithms are developed for parameter learning in both single and mixture supervised latent FA models. Based on the regression modeling between easy-to-measure and difficult-to-measure process variables, two soft sensors are built for quality prediction in the process. Two case studies are provided to evaluate the modeling and performances of the new methods.

关键词： expectation-maximization algorithm probabilistic regression modeling process data analysis soft sensor supervised latent factor analysis (FA)

来源：评论

学校读者我要写书评

暂无评论

Noise-enhanced convolutional neural networks

引用

NEURAL NETWORKS 2016年 78卷 15-23页

作者： Audhkhasi, Kartik Osoba, Osonde Kosko, Bart Univ So Calif Dept Elect Engn Signal & Informat Proc Inst Los Angeles CA 90089 USA

Injecting carefully chosen noise can speed convergence in the backpropagation training of a convolutional neural network (CNN). The Noisy CNN algorithm speeds training on average because the backpropagation algorithm is a special case of the generalized expectation-maximization (EM) algorithm and because such carefully chosen noise always speeds up the EM algorithm on average. The CNN framework gives a practical way to learn and recognize images because backpropagation scales with training data. It has only linear time complexity in the number of training samples. The Noisy CNN algorithm finds a special separating hyperplane in the network's noise space. The hyperplane arises from the likelihood-based positivity condition that noise-boosts the EM algorithm. The hyperplane cuts through a uniform-noise hypercube or Gaussian ball in the noise space depending on the type of noise used. Noise chosen from above the hyperplane speeds training on average. Noise chosen from below slows it on average. The algorithm can inject noise anywhere in the multilayered network. Adding noise to the output neurons reduced the average per-iteration training-set cross entropy by 39% on a standard MNIST image test set of handwritten digits. It also reduced the average per-iteration training-set classification error by 47%. Adding noise to the hidden layers can also reduce these performance measures. The noise benefit is most pronounced for smaller data sets because the largest EM hill-climbing gains tend to occur in the first few iterations. This noise effect can assist random sampling from large data sets because it allows a smaller random sample to give the same or better performance than a noiseless sample gives. (C) 2015 Elsevier Ltd. All rights reserved.

关键词： 2 Backpropagation Noise injection Convolutional neural network expectation-maximization algorithm Stochastic resonance Sampling from big data sets

来源：评论

学校读者我要写书评

暂无评论

Reliability estimation of a system subject to condition monitoring with two dependent failure modes

引用

IIE TRANSACTIONS 2016年第11期48卷 1058-1071页

作者： Khaleghei, Akram Makis, Viliam Univ Toronto Dept Mech & Ind Engn Toronto ON Canada

A new competing risk model is proposed to calculate the Conditional Mean Residual Life (CMRL) and Conditional Reliability Function (CRF) of a system subject to two dependent failure modes, namely, degradation failure and catastrophic failure. The degradation process can be represented by a three-state continuous-time stochastic process having a healthy state, a warning state, and a failure state. The system is subject to condition monitoring at regular sampling times that provides partial information about the system is working state and only the failure state is observable. To model the dependency between two failure modes, it is assumed that the joint distribution of the time to catastrophic failure and sojourn time in the healthy state follow Marshal-Olkin bivariate exponential distributions. The expectation-maximization algorithm is developed to estimate the model's parameters and the explicit formulas for the CRF and CMRL are derived in terms of the posterior probability that the system is in the warning state. A comparison with a previously published model is provided to illustrate the effectiveness of the proposed model using real data.

关键词： Competing risk conditional reliability function dependent failure modes expectation-maximization algorithm mean residual life

来源：评论

学校读者我要写书评

暂无评论

A finite mixture model of geometric distributions for lossless image compression

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2016年第4期10卷 671-678页

作者： Masmoudi, Atef Chaoui, Slim Masmoudi, Afif Univ Sfax Lab Elect & Technol Informat Sfax Tunisia Univ Montpellier 2 UMR CNRS 5506 LIRMM F-34392 Montpellier 05 France Univ Carthage Lab Elect Syst & Commun Networks Carthage Tunisia Univ Sfax Lab Stat & Probabil Sfax Tunisia

In this paper, we proposed a new geometric finite mixture model-based adaptive arithmetic coding (AAC) for lossless image compression. Applying AAC for image compression, large compression gains can be achieved only through the use of sophisticated models that provide more accurate probabilistic descriptions of the image. In this work, we proposed to divide the residual image into non-overlapping blocks, and then we model the statistics of each block by a mixture of geometric distributions of parameters estimated through the maximum likelihood estimation using the expectation-maximization algorithm. Moreover, a histogram tail truncation method within each predicted error block is used in order to reduce the number of symbols in the arithmetic coding and therefore to reduce the effect of the zero-occurrence symbols. Experimentally, we showed that using convenient block size and number of mixture components in conjunction with the prediction technique median edge detector, the proposed method outperforms the well known lossless image compressors.

关键词： Adaptive arithmetic coding Lossless image compression expectation-maximization algorithm Mixture of geometric distributions

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：