检索结果-内蒙古大学图书馆

STRATEGIES FOR ONLINE INFERENCE OF MODEL-BASED CLUSTERING IN LARGE AND GROWING NETWORKS

ANNALS OF APPLIED STATISTICS 2010年第2期4卷 687-714页

作者： Zanghi, Hugo Picard, Franck Miele, Vincent Ambroise, Christophe Exalead F-75008 Paris France UCB Lyon 1 Lab Biometrie & Biol Evolut F-69622 Villeurbanne France CNRS INRA Lab Stat & Genome UEVE 1152UMR 8071 F-91000 Evry France

In this paper we adapt online estimation strategies to perform model-based clustering on large networks. Our work focuses on two algorithms, the first based on the SAem algorithm, and the second on variational methods. These two strategies are compared with existing approaches on simulated and real data. We use the method to decipher the connexion structure of the political websphere during the US political campaign in 2008. We show that our online em-based algorithms offer a good trade-off between precision and speed, when estimating parameters for mixture distributions in the context of random graphs.

关键词： Graph clustering em algorithms online strategies web graph structure analysis

来源：评论

学校读者我要写书评

暂无评论

Identification of dynamical systems population described by a mixed effect ARX model structure

引用

IFAC-PapersOnLine 2017年第1期50卷 13516-13520页

作者： Batista, Levy Djermoune, El Hadi Bastogne, Thierry CYBERnano Telecom Nancy 193 av. Paul Muller Villers-les-Nancy54602 France CRAN CNRS UMR 7039 BP 70239 Vandoeuvre-les-Nancy CedexF-54506 France INRIA BIGS BP 70239 Vandoeuvre-les-Nancy CedexF-54506 France

System identification is a data-driven input-output modeling approach more and more used in biology and biomedicine. In this application context, several assays are repeated to estimate the response variability and reproducibility. The inference of the modeling conclusions to the whole population requires to account for the inter-individual variability within the modeling procedure. One solution consists of using mixed effects models but up to now no similar approach exists in the system identification literature. In this article, we propose a first solution based on an ARX (Auto Regressive model with eXternal inputs) structure using the em (Expectation-Maximisation) algorithm for the estimation of the model parameters. Using the Fisher information matrix, the parameter standard errors are estimated; this allows for group comparison tests. Simulations show the relevance of this solution compared with a classical procedure of system identification repeated on each subject. Taking into account all the information available in the population allows to gather the parameters between individuals. © 2017

关键词： Parameter estimation Dynamical systems Fisher information matrix Identification (control systems) Religious buildings Arx structures Auto regressive models Biosignals em algorithms Expectation maximisation Identification of dynamical systems Individual variability Mixed effects models

来源：评论

学校读者我要写书评

暂无评论

A latent segmentation approach to a Kuhn-Tucker model: An application to recreation demand

引用

JOURNAL OF ENVIRONMENTAL ECONOMICS AND MANAGemENT 2010年第3期60卷 209-220页

作者： Kuriyama, Koichi Hanemann, W. Michael Hilger, James R. Kyoto Univ Div Nat Resource Econ Grad Sch Agr Sakyo Ku Kyoto 6068502 Japan Univ Calif Berkeley Dept Agr & Resource Econ Berkeley CA 94720 USA

In this paper, we extend the latent segmentation approach to the Kuhn-Tucker (KT) model. The proposed approach models heterogeneity in preferences for recreational behavior, using a utility theoretical framework to simultaneously model participation and site selection decisions. Estimation of the latent segmentation KT model with standard maximum likelihood techniques is numerically difficult because of the large number of parameters in the segment membership functions and the utility function for each latent segment. To address this problem, we propose the expectation-maximization (em) algorithm to estimate the model. In the empirical section, we implement the em latent segmentation KT approach to analyze a Southern California beach recreation data set. Our empirical analysis suggests that three groups exist in the sample. Using the model to analyze two hypothetical beach management policy scenarios illustrates different welfare impacts across groups. (C) 2010 Elsevier Inc. All rights reserved.

关键词： Welfare analysis Demand system em algorithms Beach recreation

来源：评论

学校读者我要写书评

暂无评论

Modelling a population with Barrett's oesophagus from oesophageal adenocarcinoma incidence data

引用

SCANDINAVIAN JOURNAL OF GASTROENTEROLOGY 2007年第3期42卷 308-317页

作者： Van Blankenstein, Mark Looman, Caspar W. N. Kruijshaar, Michelle E. Siersema, Peter D. Kuipers, Ernst J. Bytzer, Peter Erasmus Univ Med Ctr Dept Gastroenterol & Hepatol Rotterdam Netherlands Erasmus Univ Med Ctr Dept Publ Hlth Rotterdam Netherlands Glostrup Univ Hosp Dept Gastroenterol Copenhagen Denmark

Objective. A recent study of adenocarcinoma of the oesophagus (ACO) incidence rates in Denmark showed a steep fall in the over-80 population, interpreted as the result of a decline in the prevalence of Barrett's oesophagus (BO) in this age group, for which three hypotheses were advanced: the specific mortality from ACO and, superimposed, either excess mortality from causes of death unrelated to ACO or a birth cohort effect. The aim of this study was to create models estimating the BO population fitting each of these three hypotheses, in order to select the most plausible hypothesis and to gain insight into the Danish BO population. Material and methods. Models were designed for these three hypotheses, conforming to the generally accepted 0.4 - 0.5% annual ACO incidence in BO patients. These models employed expectation-maximization ( em) algorithms, Danish life tables and the observed ACO incidence rates. The models enabled the estimation of a BO population for each hypothesis. Results. After testing against set criteria, the most plausible model was found to be that describing a birth cohort effect which predicted a +/- 5% annual rise in the prevalence of BO and, consequently, in the incidence rate of ACO in Denmark. This prediction was borne out over the subsequent decade. Conclusions. This rising ACO incidence rate is likely to continue into the foreseeable future. The use of em algorithms enabled a first estimate of the BO population at risk of ACO, although, owing to the limitations imposed by the models, the age- and gender-specific ACO risk for the entire Danish BO population could not as yet be ascertained.

关键词： Barrett's oesophagus cancer risk em algorithms epidemiology oesophageal adenocarcinoma

来源：评论

学校读者我要写书评

暂无评论

A subjectivity-aware algorithm for label aggregation in crowdsourcing 22

A subjectivity-aware algorithm for label aggregation in crow...

引用

22nd IEEE International Conference on Computational Science and Engineering (IEEE CSE) / 17th IEEE International Conference on embedded and Ubiquitous Computing (IEEE EUC)

作者： Wu, Ming Li, Qianmu Wang, Shuo Hou, Jun Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing Peoples R China Wuyi Univ Intelligent Mfg Dept Jiangmen Peoples R China

ISBN: (纸本)9781728116648

Crowdsourcing has already attracted a wide attention in the field of machine learning and its related fields. A large amount of labeled data can be obtained quickly and cheaply on crowdsourcing platforms. To deal with the problem that labels collected from crowds are usually noisy due to the low accuracy of non-expert online workers, we use quality control methods to improve the qualities of crowd data. Unfortunately, current quality control methods only consider the instance difficulty or the worker reliability to account for the variety of labels to the same instance, and these methods did not take subjectivity of workers into consideration which also effects the responses. In this paper, we present a novel subjectivity-aware algorithm for label aggregation, which also model the difficulty of instances and reliability of workers as latent parameters. This method is an em-like algorithm, which not only infers the ground truth of the instances, but also simultaneously estimates the latent parameters. Experimental results on real-world datasets show that our method outperforms the state-of-the-art ground truth inference algorithms.

关键词： crowdsourcing quality control subjectivity difficulty reliability em algorithms

来源：评论

学校读者我要写书评

暂无评论

Particle filtering algorithms for tracking multiple sound sources using microphone arrays

Particle filtering algorithms for tracking multiple sound so...

引用

32nd IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Kawamoto, Mitsuru Asano, Futoshi Asoh, Hideki Yamamoto, Kiyoshi Natl Inst Adv Ind Sci & Technol Tsukuba Ibaraki 3058568 Japan

ISBN: (纸本)9781424407286

A particle filtering algorithm using the parameters in the em (Expectation-Maximization) algorithm is proposed for tracking multiple sound sources. Differently from the conventional em based algorithms, the proposed algorithm can track multiple sound sources without knowing their starting points. Moreover, an idea of the group tracking is applied to the particle filtering algorithm so that better tracking performances can be obtained. Experimental results show the validity of the proposed algorithm.

关键词： particle filtering algorithms em algorithms tracking multiple sound sources microphone arrays

来源：评论

学校读者我要写书评

暂无评论

An Expectation-Maximization Method for Calibrating Synchronous Machine Models

An Expectation-Maximization Method for Calibrating Synchrono...

引用

General Meeting of the IEEE-Power-and-Energy-Society (PES)

作者： Meng, Da Zhou, Ning Lu, Shuai Lin, Guang PNNL Richland WA 99354 USA

ISBN: (纸本)9781479913039

The accuracy of a power system dynamic model is essential to its secure and efficient operation. Lower confidence in model accuracy usually leads to conservative operation and lowers asset usage. To improve model accuracy, this paper proposes an expectation-maximization (em) method to calibrate the synchronous machine model using phasor measurement unit (PMU) data. First, an extended Kalman filter (EKF) is applied to estimate the dynamic states using measurement data. Then, the parameters are calculated based on the estimated states using the maximum likelihood estimation (MLE) method. The em method iterates over the preceding two steps to improve estimation accuracy. The proposed em method's performance is evaluated using a single-machine infinite bus system and compared with a method where both state and parameters are estimated using an EKF method. Sensitivity studies of the parameter calibration using the em method also are presented to show the robustness of the proposed method for different levels of measurement noise and initial parameter uncertainty.

关键词： Extended Kalman Filter em algorithms State Estimation Parameter Calibration

来源：评论

学校读者我要写书评

暂无评论

Identification of distinguishing motifs

Identification of distinguishing motifs

引用

18th Annual Symposium on Combinatorial Pattern Matching

作者： Feng, WangSen Wang, Zhanyong Wang, Lusheng Peking Univ Dept Comp Sci Beijing Peoples R China City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China

ISBN: (纸本)9783540734369

Motivation: Motif identification for sequences has many important applications in biological studies, e.g., diagnostic probe design, locating binding sites and regulatory signals, and potential drug target identification. There are two versions. 1. Single Group: Given a group of n sequences, find a length-l motif that appears in each of the given sequences and those occurrences of the motif are similar. 2. Two Groups: Given two groups of sequences B and G, find a length-1 (distinguishing) motif that appears in every sequence in B and does not appear in anywhere of the sequences in G. Here the occurrences of the motif in the given sequences have errors. Currently, most of existing programs can only handle the case of single group. Moreover, it is very difficult to use edit distance (allowing indels and replacements) for motif detection. Results: (1) We propose a randomized algorithm for the one group problem that can handle indels in the occurrences of the motif. (2) We give an algorithm for the two groups problem. (3) Extensive simulations have been done to evaluate the algorithms.

关键词： motif detection em algorithms two groups

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT BP STEREO WITH AUTOMATIC PARAMemETER ESTIMATION

EFFICIENT BP STEREO WITH AUTOMATIC PARAMEMETER ESTIMATION

引用

15th IEEE International Conference on Image Processing (ICIP 2008)

作者： Huq, Shafik Koschan, Andreas Abidi, Besma Abidi, Mongi Univ Tennessee Dept Elect Engn & Comp Sci Knoxville TN 37996 USA

ISBN: (纸本)9781424417650

In this paper, we propose a series of techniques to enhance the computational performance of existing Belief Propagation (BP) based stereo matching that relies on automatic estimation of the Markov random field (MRF) parameters. First, we show how convergence in matching can be achieved faster than with the existing message comparison technique by skipping comparisons in early inferences. Second, assuming that a stereo pair is captured. with identical cameras, we apply a hypothesis called noise equivalence to pre-estimate the likelihood parameters and thus, avoid costly nested inferences to reduce the computational time. The likelihood parameters and intensity information are used for accelerated message propagation in image regions lacking gradients. Third, the prior model parameters are estimated with a combination of maximum likelihood (ML) estimation and disparity gradient constraint to further reduce the computational time. Supporting experiments for the proposed algorithms show encouraging results on ground truth test images.

关键词： Stereo Belief Propagation em algorithms parameter estimation maximum likelihood

来源：评论

学校读者我要写书评

暂无评论

Modelling of User Behaviour in Cellular Networks

Modelling of User Behaviour in Cellular Networks

引用

22nd IEEE Signal Processing and Communications Applications Conference (SIU)

作者： Dalman, Engin Akinci, Mehmet Nuri Kurt, Gunes Karabulut Istanbul Tech Univ Elekt & Haberlesme Muhendisligi Bolumu Istanbul Turkey

ISBN: (纸本)9781479948741

Modeling of user behaviour becomes almost a necessity on data networks nowadays. Besides using their resources more efficiently, many data communication systems will perform more effective via estimation of statistical distribution of packet counts transferred (uploaded or downloaded) by users at once. Hence, the purpose of this study is to search suitable statistical models for distribution of packet counts that is transferred by user at once, on a arbitrary network. For this aim, an Android application is used to track Internet usage of real users. A detailed statistical analysis is performed using this data and the results are checked by applying different performance tests. Consequently, it is observed that the most suitable statistical distribution to model user behaviour is lognormal family.

关键词： Flow size distribution Android em algorithms Kullback-Leibler divergence (KLD) Weighted mean relative difference (WMRD) Transmission control protocol (TCP)

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：