检索结果-内蒙古大学图书馆

12th International Symposium on Bioinformatics Research and Applications (ISBRA)

作者： Wang, Lu Zhu, Dongxiao Li, Yan Dong, Ming Wayne State Univ Dept Comp Sci Detroit MI 48202 USA

ISBN: (纸本)9783319387826;9783319387819

A major computational challenge in analyzing metagenomics sequencing reads is to identify unknown sources of massive and heterogeneous short DNA reads. A promising approach is to efficiently and sufficiently extract and exploit sequence features, i.e., k-mers, to bin the reads according to their sources. Shorter k-mers may capture base composition information while longer k-mers may represent reads abundance information. We present a novel Poisson-Markov mixture Model (PMM) to systematically integrate the information in both long and short k-mers and develop a parallel algorithm for improving both reads binning performance and running time. We compare the performance and running time of our PMM approach with selected competing approaches using simulated data sets, and we also demonstrate the utility of our PMM approach using a time course metagenomics data set. The proba-bilistic modeling framework is sufficiently flexible and general to solve a wide range of supervised and unsupervised learning problems in metagenomics.

关键词： Probabilistic clustering expectation-maximization algorithm Metagenomics Next-generation sequencing (NGS) Parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

NON-NEGATIVE DECOMPOSITION OF LINEAR RELATIONSHIPS: APPLICATION TO MULTI-SOURCE OCEAN REMOTE SENSING DATA 41

NON-NEGATIVE DECOMPOSITION OF LINEAR RELATIONSHIPS: APPLICAT...

引用

41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Lopez-Radcenco, Manuel Aissa-El-Bey, Abdeldjalil Ailliot, Pierre Tandeo, Pierre Fablet, Ronan Telecom Bretagne Inst Mines Telecom UMR CNRS LabSTICC 6285 Technopole Brest Iroise CS83818 F-29238 Brest 3 France Univ Brest Lab Math Bretagne Atlantique UMR 6205 6 Ave Victor Le GorgeuBP 809 F-29285 Brest France

ISBN: (纸本)9781479999880

The identification and separation of contributions associated with different sources or processes is a general problem in signal and image processing. Here, we focus on the decomposition of multiple linear relationships and introduce a non-negative formulation. The proposed models can be viewed as generalizations of latent class regression models and account for possibly varying magnitudes of the linear transfer functions. Along with these models, we present model calibration algorithms. We first demonstrate their performance on simulated data. We also report an application to the analysis of upper ocean dynamics from remote sensing data (namely, satellite-derived Sea Surface Height (SSH) and Sea Surface temperature (SST) image series). This application further stresses the proposed formulation's relevance compared to state-of-the-art regression models.

关键词： Linear relationships non-negativity latent class model expectation-maximization algorithm multi-source remote sensing data

来源：评论

学校读者我要写书评

暂无评论

Model-Based Discriminant Analysis of High-Dimensional Data

Model-Based Discriminant Analysis of High-Dimensional Data

引用

作者： Mingzhu Sun The University of Queensland

学位级别：博士

This thesis addresses two important problems in modern statistics: discriminant analysis of big data and dimension reduction of high-dimensional data such as microarray gene expression data. These problems are commonly encountered in various scientific fields and can pose considerable challenges since traditional approaches might not work properly or even break down in the high-dimensional setting. For the first problem of discriminant analysis of big data, one of the widely used parametric approaches is to model the distribution of the feature vector in each of the predefined classes via a normal mixture distribution. The component-covariance matrices in the normal mixture for a class are highly parameterized, thus, rendering them impractical for high-dimensional datasets. Therefore, as the dimension increases, some forms of regularization need to be implemented. In this thesis, an innovative factor model approach, called mixtures of common factor ana- lyzers for discriminant analysis (MCFDA), is proposed. With this approach, the component- covariance matrices are taken to have a factor-analytic form with common loadings across the classes (common before the transformation of the factors into white noise). This approach also allows the data to be viewed in low-dimensional spaces by plotting the (estimated) values of the latent factors corresponding to the observed data points. To improve the robustness of our MCFDA approach for data which have heavy tails or atypical observations, we also adopt the multivariate t-family for the component-error and factor distri- butions. We refer to this model as the mixtures of common t-factor analyzers for discriminant analysis (MCtFDA). With this approach, both the common factor loadings and the diagonal matrix of error terms need to be specified as the same across the classes. This approach has great flexibility for modelling data which are non-normal or with outliers. For the second problem of dimension reduction, we focus on

关键词： finite mixture models discriminant analysis clustering microarray gene expression data expectation-maximization algorithm factor analysis model dimension reduction machine learning error rates

来源：评论

学校读者我要写书评

暂无评论

Covariances matrix under the multivariate-Gh funtion to desing portfolios

引用

Contaduria y Administracion 2016年第3期61卷 535-550页

作者： Núñez Mora, José Antonio Mata Mata, Leovardo EGADE Business School Tecnologico de Monterrey Mexico

In this paper we developed the estimation implementation of the generalized hyperbolic multivariate (GH) distribution with a non-fixed Bessel function. The covariance matrix estimated through the GH distribution complements the use of the Markowitz procedure to construct an efficient portfolio and reduce the variation coefficient of the expected return. The data are from the Stockholm index 30 from January 2010 to April 2014. © 2015 Universidad Nacional Autónoma de México, Facultad de Contaduría y Administración.

关键词： Covariance matrix expectation-maximization algorithm Generalized hyperbolic distribution Markowitz portfolio

来源：评论

学校读者我要写书评

暂无评论

CUDA-based Parallel Implementation of IBM Word Alignment algorithm for Statistical Machine Translation 17

CUDA-based Parallel Implementation of IBM Word Alignment Alg...

引用

17th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT)

作者： Jing, Si-Yuan Yan, Gao-Rong Chen, Xing-Yuan Jin, Peng Guo, Zhao-Yi Leshan Normal Univ Sch Comp Sci Leshan Peoples R China Leshan Normal Univ Sch Foreign Language Leshan Peoples R China

ISBN: (纸本)9781509050819

Word alignment is a basic task in natural language processing and it usually serves as the starting point when building a modern statistical machine translation system. However, the state-of-art parallel algorithm for word alignment is still time-consuming. In this work, we explore a parallel implementation of word alignment algorithm on Graphics Processor Unit (GPU), which has been widely available in the field of high performance computing. We use the Compute Unified Device Architecture (CUDA) programming model to re-implement a state-of-the-art word alignment algorithm, called IBM expectation-maximization (EM) algorithm. A Tesla K40M card with 2880 cores is used for experiments and execution times obtained with the proposed algorithm are compared with a sequential algorithm and a multi-threads algorithm on an IBM X3850 server, which has two Intel Xeon E7 CPUs (2.0GHz * 10 cores). The best experimental results show a 16.8-fold speedup compared to the multi-threads algorithm and a 234.7-fold speedup compared to the sequential algorithm.

关键词： Word Alignment GPU Parallel Computation expectation-maximization algorithm CUDA

来源：评论

学校读者我要写书评

暂无评论

A COPULA APPROACH TO JOINT MODELING OF LONGITUDINAL MEASUREMENTS AND SURVIVAL TIMES USING MONTE CARLO expectation-maximization WITH APPLICATION TO AIDS STUDIES

引用

JOURNAL OF BIOPHARMACEUTICAL STATISTICS 2015年第5期25卷 1077-1099页

作者： Ganjali, M. Baghfalaki, T. Shahid Beheshti Univ Dept Stat Tehran Iran Tarbiat Modares Univ Dept Stat Tehran Iran Inst Res Fundamental Sci IPM Sch Biol Sci Tehran Iran

Joint modeling of longitudinal measurements and time to event data is often performed by fitting a shared parameter model. Another method for joint modeling that may be used is a marginal model. As a marginal model, we use a Gaussian model for joint modeling of longitudinal measurements and time to event data. We consider a regression model for longitudinal data modeling and a Weibull proportional hazard model for event time data modeling. A Gaussian copula is used to consider the association between these two models. A Monte Carlo expectation-maximization approach is used for parameter estimation. Some simulation studies are conducted in order to illustrate the proposed method. Also, the proposed method is used for analyzing a clinical trial dataset.

关键词： Copula models expectation-maximization algorithm Longitudinal model Non-ignorability Shared parameter model Time to event model

来源：评论

学校读者我要写书评

暂无评论

Iterative Channel Estimation for Higher Order Modulated STBC-OFDM Systems with Reduced Complexity

引用

KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS 2016年第6期10卷 2446-2462页

作者： Basturk, Ilhan Ozbek, Berna Adnan Menderes Univ Dept Elect & Elect Engn Aydin Turkey Izmir Inst Technol Dept Elect & Elect Engn Izmir Turkey

In this paper, a frequency domain expectation-maximization (EM)-based channel estimation algorithm for Space Time Block Coded-Orthogonal Frequency Division Multiplexing (STBC-OFDM) systems is investigated to support higher data rate applications in wireless communications. The computational complexity of the frequency domain EM-based channel estimation is increased when higher order constellations are used because of the ascending size of the search set space. Thus, a search set reduction algorithm is proposed to decrease the complexity without sacrificing the system performance. The performance results of the proposed algorithm is obtained in terms of Bit Error Rate (BER) and Mean Square Error (MSE) for 16QAM and 64QAM modulation schemes.

关键词： Channel estimation space-time block codes OFDM expectation-maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Sparse Bayesian Learning for DOA Estimation in MIMO Radar with Unknown Nonuniform Noise

Sparse Bayesian Learning for DOA Estimation in MIMO Radar wi...

引用

CIE International Conference on Radar (RADAR)

作者： Wang, Xianpeng Huang, Mengxing Bi, Guoan Hainan Univ State Key Lab Marine Resource Utilizat South Chin Haikou 570228 Hainan Peoples R China Hainan Univ Coll Informat Sci & Technol Haikou 570228 Hainan Peoples R China Nanyang Technol Univ Sch Elect & Elect Engn Singapore 639798 Singapore

ISBN: (纸本)9781509048281

In this paper, a sparse Bayesian learning framework for DOA estimation in multiple input multiple output (MIMO) radar is proposed with unknown nonuniform noise. In the proposed method, the redundant elements of MIMO radar can be eliminated by using the reduced dimensional (RD) transformation. Then a sparse Bayesian model of covariance vector is formulated by assuming that the prior source power is independent zero-mean Gaussian distributed with hyperparameters for its unknown variance. The hyperparameters and nonuniform noise variances are estimated by utilizing the expectation-maximization (EM) algorithm and least squares (LS) criterion, respectively. Finally, the spectrum of hyperparameters is used to estimate the coarse DOA, and a high-precision DOA estimation is achieved by using a refined 1-D searching procedure based on the reconstruction result. Simulation results have demonstrated that the proposed method can work well with different nonuniform noise and achieve better performance.

关键词： MIMO radar direction of arrival estimation sparse Bayesian learning expectation-maximization algorithm nonuniform noise

来源：评论

学校读者我要写书评

暂无评论

Ehapp2: Estimate haplotype frequencies from pooled sequencing data with prior database information

引用

JOURNAL OF BIOINFORMATICS AND COMPUTATIONAL BIOLOGY 2016年第4期14卷 1650017-1650017页

作者： Cao, Chang-Chang Sun, Xiao Southeast Univ Sch Biol Sci & Med Engn State Key Lab Bioelect Nanjing 210096 Jiangsu Peoples R China

To reduce the cost of large-scale re-sequencing, multiple individuals are pooled together and sequenced called pooled sequencing. Pooled sequencing could provide a cost-effective alternative to sequencing individuals separately. To facilitate the application of pooled sequencing in haplotype-based diseases association analysis, the critical procedure is to accurately estimate haplotype frequencies from pooled samples. Here we present Ehapp2 for estimating haplotype frequencies from pooled sequencing data by utilizing a database which provides prior information of known haplotypes. We first translate the problem of estimating frequency for each haplotype into finding a sparse solution for a system of linear equations, where the NNREG algorithm is employed to achieve the solution. Simulation experiments reveal that Ehapp2 is robust to sequencing errors and able to estimate the frequencies of haplotypes with less than 3% average relative difference for pooled sequencing of mixture of real Drosophila haplotypes with 50 x total coverage even when the sequencing error rate is as high as 0.05. Owing to the strategy that proportions for local haplotypes spanning multiple SNPs are accurately calculated first, Ehapp2 retains excellent estimation for recombinant haplotypes resulting from chromosomal crossover. Comparisons with present methods reveal that Ehapp2 is state-of-the-art for many sequencing study designs and more suitable for current massive parallel sequencing.

关键词： Haplotype frequency estimation pooled sequencing expectation-maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Generative Modeling of Voice Fundamental Frequency Contours

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2015年第6期23卷 1042-1053页

作者： Kameoka, Hirokazu Yoshizato, Kota Ishihara, Tatsuma Kadowaki, Kento Ohishi, Yasunori Kashino, Kunio Univ Tokyo Grad Sch Informat Sci & Technol Tokyo 1138656 Japan NTT Corp NTT Commun Sci Labs Tokyo 2430198 Japan

This paper introduces a generative model of voice fundamental frequency (F-0) contours that allows us to extract prosodic features from raw speech data. The present F-0 contour model is formulated by translating the Fujisaki model, a well-founded mathematical model representing the control mechanism of vocal fold vibration, into a probabilistic model described as a discrete-time stochastic process. There are two motivations behind this formulation. One is to derive a general parameter estimation framework for the Fujisaki model that allows the introduction of powerful statistical methods. The other is to construct an automatically trainable version of the Fujisaki model that we can incorporate into statistical-model-based text-to-speech synthesizers in such a way that the Fujisaki-model parameters can be learned from a speech corpus in a unified manner. It could also be useful for other speech applications such as emotion recognition, speaker identification, speech conversion and dialogue systems, in which prosodic information plays a significant role. We quantitatively evaluated the performance of the proposed Fujisaki model parameter extractor using real speech data. Experimental results revealed that our method was superior to a state-of-the-art Fujisaki model parameter extractor.

关键词： expectation-maximization algorithm Fujisaki model prosody voice fundamental frequency contour

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：