检索结果-内蒙古大学图书馆

Stacked Laplace-EM algorithm for duration models with time-varying and random effects

COMPUTATIONAL STATISTICS & DATA ANALYSIS 2008年第5期52卷 2514-2528页

作者： Kauermann, Goran Xu, Ronghui Vaida, Florin Univ Bielefeld Fac Econ & Business Adm D-33502 Bielefeld Germany Univ Calif San Diego Dept Math Div Biostat & Bioinformat La Jolla CA 92093 USA Univ Calif San Diego Sch Med Div Biostat & Bioinformat La Jolla CA 92093 USA

An extension of the Cox proportional hazards model for clustered survival data is proposed. This allows both general random effects (frailties) and time-varying regression coefficients, the latter being smooth functions of time. The model is fitted using a mixed-model representation of penalized spline smoothing which offers a unified framework for estimation of the baseline hazard, the smooth effects and the random effects. The estimator is computed using a stacked laplace-EM (SLaEM) algorithm. More specifically, the smoothing parameters are integrated out in the log likelihood via a Laplace approximation. The approximation itself involves an integrated log-likelihood over the random cluster effects, for which the EM algorithm is used. A marginal Akaike information criterion is developed for selection among possible candidate models. The time-varying and mixed effects model is applied to unemployment data taken from the German Socio-Economic Panel. The duration of unemployment is modeled in a flexible way including smooth covariate effects and individual random effects. (c) 2007 Elsevier B.V. All rights reserved.

关键词： time varying regression coefficients expectation-maximisation algorithm random effect Cox Proportional Hazards Models smoothing TIME FUNCTIONS Unemployment

来源：评论

学校读者我要写书评

暂无评论

Joint delay-Doppler estimation for passive bistatic radar with direct-path interference using MCMC method

引用

IET RADAR SONAR AND NAVIGATION 2018年第1期12卷 130-136页

作者： Zhao, Yongsheng Zhao, Yongjun Zhao, Chuang Natl Digital Switching Syst Engn & Technol Res Ct Zhengzhou Henan Peoples R China

This study deals with the problem of joint delay-Doppler estimation in a practically motivated scenario of passive bistatic radar, where the surveillance channel is polluted by the direct-path signal residual. A new joint delay-Doppler maximum-likelihood estimator (MLE) based on Markov chain Monte Carlo (MCMC) is proposed. The MCMC method allows one to compute the MLE in a computationally efficient manner. The proposed estimator is based upon generating random variates using a Markov Chain whose stationary distribution approximates the likelihood function and guarantees convergence to the global maximum. In contrast to the recently proposed modified cross-correlation estimator, and the expectation-maximisation-based MLE, it avoids grid search which may lead to a straddle loss or initialisation-dependent iteration which may lead to convergence problems. Simulation results indicate that the proposed estimator achieves a significant performance improvement over existing methods.

关键词： Doppler radar passive radar interference (signal) expectation-maximisation algorithm Monte Carlo methods Markov processes statistical distributions approximation theory convergence of numerical methods radar signal processing joint delay-Doppler estimation passive bistatic radar direct-path interference MCMC method surveillance channel direct-path signal residual joint delay-Doppler maximum-likelihood estimator Markov chain Monte Carlo method MLE random variates stationary distribution likelihood function modified cross-correlation estimator expectation-maximisation-based MLE

来源：评论

学校读者我要写书评

暂无评论

Parameter estimation of impulsive noise for channel coded communication systems

引用

IET COMMUNICATIONS 2021年第3期15卷 445-452页

作者： Chen, Chun-Yin Chiu, Mao-Ching Natl Chung Cheng Univ Dept Commun Engn Chiayi Taiwan

In this paper, an impulsive noise estimation algorithm for generating bit log-likelihood ratios (LLRs) for channel coded systems in impulsive noise environments is proposed. This approach is to design the LLR detector in the maximum-likelihood (ML) sense, which requires the parameters of the impulsive noise. The expectation-maximisation (EM) algorithm is utilised to estimate the parameters of the Bernoulli-Gaussian (B-G) impulsive noise model. The estimated parameters is then used to generate the bit LLRs for the soft-input channel decoder. Simulation results show that over a wide range of impulsive noise power, the proposed algorithm approaches the optimal performance (with ideal estimation) even under Middleton class-A (M-CA) impulsive noise models.

关键词： impulse noise expectation-maximisation algorithm Gaussian noise Middleton class-A impulsive noise models maximum likelihood decoding soft-input channel decoder parameter estimation Codes bit LLR wireless channels Bernoulli-Gaussian impulsive noise model bit log-likelihood ratios channel coding channel coded communication systems impulsive noise parameter estimation maximum-likelihood sense Radio links and equipment impulsive noise estimation algorithm Other topics in statistics

来源：评论

学校读者我要写书评

暂无评论

Doubly iterative multiple-input-multiple-output-bit-interleaved coded modulation receiver with joint channel estimation and randomised sampling detection

引用

IET SIGNAL PROCESSING 2016年第4期10卷 335-341页

作者： Bai, Lin Dou, Shengyue Xiao, Zhengyu Choi, Jinho Beihang Univ Sch Elect & Informat Engn Beijing 100191 Peoples R China Huawei Technol Shanghai Co LTD Shanghai Peoples R China GIST Sch Informat & Commun Gwangju South Korea

In this study, the authors propose a lattice reduction (LR)-based doubly iterative receiver for joint channel estimation and detection in multiple-input-multiple-output (MIMO) bit-interleaved coded modulation systems. For the inner iteration loop of the receiver, LR-based randomised sampling detection is employed to enjoy the tradeoff between performance and complexity while for the outer iteration loop, the expectation-maximisation (EM)-based iterative channel estimation using sampling results is proposed to achieve the maximum likelihood channel estimation performance. Besides, a modified computational efficient EM-based channel estimation approach is also derived to reduce the complexity further. Simulation results demonstrate that the proposed doubly MIMO iterative receiver can have comparable bit-error rate performance with a reasonable computational complexity.

关键词： iterative decoding modulation coding interleaved codes MIMO communication radio receivers channel estimation computational complexity expectation-maximisation algorithm signal detection signal sampling doubly iterative multiple-input-multiple-output-bit-interleaved coded modulation receiver joint channel estimation lattice reduction-based doubly iterative receiver MIMO bit-interleaved coded modulation systems inner iteration loop LR-based randomised sampling detection outer iteration loop expectation-maximisation-based iterative channel estimation maximum likelihood channel estimation performance modified computational efficient EM-based channel estimation approach bit-error rate performance computational complexity

来源：评论

学校读者我要写书评

暂无评论

Follow a guide to solve urban problems: the creation and application of urban knowledge graph

引用

IET SOFTWARE 2017年第3期11卷 126-134页

作者： Shan, Shubing Cao, Buyang Tongji Univ Sch Software Engn 4800 Caoan Rd Shanghai Peoples R China China Intelligent Urbanizat Cocreat Ctr 1239 Siping Rd Shanghai Peoples R China

It is a hot research topic today to find out the potential knowledge from the scattered urban data and take advantage of the relationship between the knowledge to solve the challenges of urban governance and smart city construction. The urban knowledge graph is an effective way to establish the relationship between the knowledge and address the urban issues. This study proposes the methodology to create an urban knowledge graph and its framework. It elaborates the approaches of urban knowledge acquisition, reasoning and expression. Furthermore, a hybrid reasoning algorithm known as EG is given based on expectation-maximisation algorithm and Gibbs algorithm, which has the complementary advantages of the both methods. Through a study case, this study illustrates constructing and working process of an urban knowledge graph. The case shows that the urban knowledge graph has a good application prospect.

关键词： knowledge acquisition inference mechanisms graph theory expectation-maximisation algorithm urban problems urban knowledge graph urban knowledge acquisition hybrid reasoning algorithm EG expectation-maximisation algorithm Gibbs algorithm

来源：评论

学校读者我要写书评

暂无评论

Iterative PIC detection and channel estimation for DS-CDMA communications in AWGN and satellite/HAPS channels

引用

EUROPEAN TRANSACTIONS ON TELECOMMUNICATIONS 2005年第1期16卷 91-100页

作者： Morosi, S del Re, E Fantacci, R Rufolo, P Univ Florence Dept Elect & Telecommun I-50139 Florence Italy

This paper presents a turbo multiuser detector for turbo-coded DS-code division multiple access (CDMA) systems, based on the utilisation of a parallel interference cancellator (PIC) and a bank of turbo decoders: in the proposed receiver the interference cancellation is performed after each constituent decoder of the turbo decoding scheme. Moreover, the soft outputs of the turbo decoders are used iteratively to improve the channel parameter estimation during the updating step, which is formally equivalent to one step of the expectation-maximisation algorithm. By means of computer simulations, we will show that the proposed receiver achieves performance comparable with the one obtained by systems, which suppose perfect knowledge of the channel parameters for medium to high system loads, in AWGN channel. Finally, the proposed receiver is also applied in HAPS (high altitude platform station) and satellite channel, for different values of the elevation angle, affording remarkable performance. Copyright (C) 2005 AEIT.

关键词： Turbo Parameter estimation AWGN Punctate inner choroidopathy decoders satellite channel Angle of elevation expectation-maximisation algorithm Direct-sequence code-division multiple access channel estimation Worm gears Receivers high altitude platform station Interference cancellation

来源：评论

学校读者我要写书评

暂无评论

Measurement of Stable Isotope Ratios in Methylamphetamine: A Link to Its Precursor Source

引用

ANALYTICAL CHEMISTRY 2013年第19期85卷 9400-9408页

作者： Salouros, Helen Sutton, Gordon J. Howes, Joanna Hibbert, D. Brynn Collins, Michael Natl Measurement Inst N Ryde NSW Australia Univ Technol Ultimo NSW Australia Univ New S Wales Sch Chem Sydney NSW 2052 Australia

The illicit drug methylamphetamine is often prepared from the precursor ephedrine or pseudoephedrine, which in turn are obtained by three processes: extraction from the Ephedra plant ("natural"), via fermentation of sugars ("semi-synthetic"), and by a "fully synthetic" route from propiophenone. We report the first method to differentiate between the three industrial routes used to produce the precursors ephedrine and pseudoephedrine by measurement of stable isotope ratios of nitrogen (delta N-15), hydrogen (delta H-2), and carbon (delta C-13). Analysis of 782 samples of seized methylamphetamine allowed classification into three groups using k-means clustering or the expectation-maximization algorithm applied to a Gaussian mixture model. By preparation of 30 samples of ephedrine by the "fully synthetic" industrial process and measuring their delta N-15, delta H-2, and delta C-13 values, we observed that N-15 becomes significantly depleted compared to the methylamine starting material. Conversion of ten ephedrine samples to methylamphetamine showed that this depletion is maintained in the final drug product, of which the delta N-15, delta C-13, and delta H-2 values were distinct from those of ephedrine and methylamphetamine samples of a semi-synthetic (fermentation pathway) origin. Combining modeling analysis with the new experiments and published information on the values of delta H-2 gave a definitive assignment of the three model groups, and equations to obtain probabilities for the precursor origin of any new sample. A simple rule of thumb is also presented. Making an assignment using delta values is particularly useful when no other chemical profiling information is available.

关键词： Heuristics Methamphetamine Pharmaceutical Preparations Ephedrine expectation-maximisation algorithm Pseudoephedrine stable isotopes isotope ratios Propiophenones

来源：评论

学校读者我要写书评

暂无评论

POSITRON EMISSION TOMOGRAPHIC-IMAGES AND expectation MAXIMIZATION - A VLSI ARCHITECTURE FOR MULTIPLE ITERATIONS PER SECOND

引用

IEEE TRANSACTIONS ON NUCLEAR SCIENCE 1988年第1期35卷 620-624页

作者： JONES, WF BYARS, LG CASEY, ME Computer Technology and Imaging Inc. Knoxville TN USA

A digital electronic architecture for parallel processing of the expectation maximization (EM) algorithm for positron-emission-tomography (PET) image reconstruction is proposed. Rapid (0.2-s) EM iterations on high-resolution (256*256) images are supported. Arrays of two VLSI chips perform forward and back projection calculations. The architecture is described, including data flow and partitioning relevant to EM and parallel processing. EM images are shown that are produced with software simulating the proposed hardware reconstruction algorithm. Projected cost of the system is estimated to be small in comparison to the cost of current PET scanners.

关键词： computer software Positron Emission Tomography Systems expectation-maximisation algorithm Reconstruction algorithm arrays ARCHITECTURE Building construction PARALLEL PROCESSING (COMPUTERS) data flow Digital electronics Small Costing systems backprojection

来源：评论

学校读者我要写书评

暂无评论

PARAMETER-ESTIMATION OF DEPENDENCE TREE MODELS USING THE EM algorithm

引用

IEEE SIGNAL PROCESSING LETTERS 1995年第8期2卷 157-159页

作者： RONEN, O ROHLICEK, JR OSTENDORF, M BBN HARK SYST CORP CAMBRIDGEMA 02138

A dependence tree is a model for the joint probability distribution of an n-dimensional random vector, which requires a relatively small number of free parameters by making Markov-like assumptions on the tree. In this letter, we address the problem of maximum likelihood estimation of dependence tree models with missing observations, using the expectation-maximization algorithm. The solution involves computing observation probabilities with an iterative ''upward-downward'' algorithm, which is similar to an algorithm proposed for belief propagation in causal trees, a special case of Bayesian networks.

关键词： Belief propagation expectation-maximisation algorithm algorithms random vector Parameter estimation Iterative Bayesian networks maximum likelihood estimation DEPENDENCE Probability distribution

来源：评论

学校读者我要写书评

暂无评论

Adaptive bandwidth mode detection algorithm

引用

IET IMAGE PROCESSING 2011年第8期5卷 645-660页

作者： Dagher, I. Dahdah, K. Univ Balamand Dept Comp Engn El Koura Lebanon

In this study a new algorithm 'adaptive bandwidth mode detection' (ABMD) algorithm has been developed to recover the correct density function without the need to either specify the correct number of Gaussians in the model or the correct bandwidth. The ABMD is employed in modelling visual features in applications such as image segmentation and real-time visual tracking. A simple type of model for these visual features are the Gaussian mixtures, where the number of Gaussian components is variable, thus, making it a flexible method for multimodal representation. This algorithm is used at initialisation for target modelling, where the target update will be done based on the mode propagation with adaptive bandwidth tracker method. It is based on an optimisation technique where a gradient ascent method is used and the optimal solution is selected based on a log-likelihood function. The mode detection ability of ABMD algorithm is compared with both the expectation maximisation and mean-shift algorithms. Furthermore, different video sequences have been employed to show how this approach has the ability to track an object regardless of whether the target model is corrupted with unwanted data at new frames.

关键词： Gaussian component number video sequences Optimisation techniques video signal processing Gaussian mixtures Computer vision and image processing techniques density function recovery Gaussian processes Optical, image and video signal processing expectation maximisation algorithms image segmentation object tracking log-likelihood function multimodal representation image sequences optimisation technique mode propagation visual feature modelling ABMD algorithm optimisation Interpolation and function approximation (numerical analysis) mean-shift algorithms real-time visual tracking Video signal processing adaptive bandwidth mode detection algorithm adaptive bandwidth tracker method target modelling Other topics in statistics gradient methods gradient ascent method expectation-maximisation algorithm

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：