检索结果-内蒙古大学图书馆

Doubly selective channel estimation for subband OFDMA using basis expansion models

Science China(Information Sciences) 2011年第10期54卷 2113-2123页

作者： CHEN DongHua & QIU HongBing School of Telecommunications Engineering,Xidian University,Xi’an 710071,China 1. School of Telecommunications Engineering Xidian University Xi’an 710071 China

This letter considers the channel estimation for subband orthogonal frequency division multiple access (OFDMA) operating over highly time-frequency selective (i.e.,doubly selective) *** on general basis expansion model,two expectation maximization-type channel estimation methods are proposed for subband OFDMA in order to overcome channel time-frequency *** proposed method is compared with conventional approach and is shown to be superior to the conventional one.

关键词： orthogonal frequency division multiple access channel estimation basis expansion model expectation maximization algorithm time-frequency selectivity

来源：评论

学校读者我要写书评

暂无评论

A Note on Mixture Bivariate Model

A Note on Mixture Bivariate Model

引用

International Conference on Graphic and Image Processing (ICGIP)

作者： Cao, Hanwen Tian, Wei Deng, Chengzhi Nanchang Inst Technol Dept Sci Nanchang Peoples R China Nanchang Inst Technol Sch Informat Engn Nanchang Jiangxi Peoples R China

ISBN: (纸本)9780819489326

L. Sendur and I. W. Selesnick suggest four jointly non-Gaussian bivariate models to characterize the dependency between a coefficient and its parent, and respectively derive the corresponding MAP estimators based on noisy wavelet coefficients in detail in [6]. Among the four models, the second is a mixture model and it is quite complicated to evaluate parameters, so L. Sendur and I. W. Selesnick didn't give a concrete method. In this letter, a concrete mixture bivariate model will be described by drawing inspiration from Model 2. expectation maximization (EM) algorithm is employed to find the parameters of new model. The simulation results show that the values of PSNR have a bit improvement compared with Model 1. The results can be viewed as a supplementary of model 2 in [6].

关键词： Image denoising Mixture bivariate model Bayesian estimator expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Multi-state Travel Time Reliability Model: Impact of Incidents on Travel Time Reliability

Multi-state Travel Time Reliability Model: Impact of Inciden...

引用

14th International IEEE Conference on Intelligent Transportation Systems (ITSC)

作者： Park, Sangjun Rakha, Hesham Guo, Feng Virginia Tech Transportat Inst Ctr Sustainable Mobil Dept Civil Engn Blacksburg VA 24061 USA Virginia Tech Dept Stat Blacksburg VA 24061 USA

ISBN: (纸本)9781457721977

This paper attempts to quantify the impact of traffic incidents on travel time reliability using a newly proposed multi-state travel time reliability model. Given that the multi-state travel time reliability model provides significantly better fits when compared to using a single-mode density function, it is possible to quantify the incident impacts more accurately. In order to obtain travel times, the study simulates weekday traffic on a section of I-66 over 17 days, once with incidents and once without them, using the INTEGRATION microscopic traffic simulation software. The simulated travel time data sets are then used to fit a three-state travel time reliability model (three normal distributions) to calibrate the parameters of the density function using the expectation maximization (EM) algorithm. The study demonstrates that incidents do not introduce an additional component distribution when congestion has already onset;instead they increase the mean travel time and variability in travel times for the congested conditions. For instance, the 90th percentile travel time of the second component distribution increases by up to 93 percent. Additionally, the study addresses technical issues related to the calibration and interpretation of the model from a practical standpoint.

关键词： Calibration Data models Delay Density functional theory Reliability Road transportation Vehicles calibration density function expectation maximization algorithm expectation-maximisation algorithm integration microscopic traffic simulation multistate trave

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Color Image Segmentation by Clustering into Multivariate Gaussians

Unsupervised Color Image Segmentation by Clustering into Mul...

引用

5th International Conference on Information Processing (ICIP 2011)

作者： Raj, Jobin Govindan, V. K. Natl Inst Technol Calicut Dept Comp Sci & Engn Calicut Kerala India

ISBN: (纸本)9783642227851

An Unsupervised Color Image Segmentation algorithm by using Finite Gaussian Mixture Model (GMM) is proposed in this paper. The parameters of GMM are estimated using expectation maximization (EM) algorithm. A novel technique for initializing the EM algorithm is presented. The algorithm runs in two stages. The first stage performs an initial segmentation which initializes the EM algorithm. The second stage is the parameter estimation phase using EM algorithm. The scheme is computationally efficient in terms of space and time complexity.

关键词： expectation maximization algorithm Gaussian Mixture Model Image Segmentation Model-based Segmentation Multivariate Gaussian Distribution

来源：评论

学校读者我要写书评

暂无评论

Traffic Speed Forecasting by Mixture of Experts

Traffic Speed Forecasting by Mixture of Experts

引用

14th International IEEE Conference on Intelligent Transportation Systems (ITSC)

作者： Coric, Vladimir Wang, Zhuang Vucetic, Slobodan Temple Univ Philadelphia PA 19122 USA Siemens Res Corp Princeton NJ 08540 USA

ISBN: (纸本)9781457721977

Traffic speed is one of the most important quantities for travel information systems. Accurate speed forecasting can help in trip planning by allowing travelers to avoid the congested routes, either by choosing the alternative routes or by changing the departure time. It is also helpful for traffic monitoring, control, and planning. An important feature of traffic is that it consists of free flow and congested regimes, which have significantly different properties. Training a single traffic speed predictor for both regimes typically results in suboptimal accuracy. To address this problem, a mixture of experts algorithm which consists of two regime-specific linear predictors and a decision tree gating function was developed. A generalized expectation maximization algorithm was used to train the linear predictors and the decision tree. The proposed algorithm was evaluated on a 5-mile stretch of I35 highway in Minneapolis containing 10 single loop detector stations, with prediction horizons ranging from 5 minutes to one hour ahead. Experimental results showed that mixture of experts approach outperforms several popular benchmark approaches.

关键词： Forecasting Linear regression Markov processes Prediction algorithms Regression tree analysis Road transportation decision tree decision tree gating function decision trees expectation maximization algorithm expectation-maximisation algorithm experts algo

来源：评论

学校读者我要写书评

暂无评论

The gene normalization task in BioCreative III

引用

BMC BIOINFORMATICS 2011年第s8期12卷 S2-S2页

作者： Lu, Zhiyong Kao, Hung-Yu Wei, Chih-Hsuan Huang, Minlie Liu, Jingchen Kuo, Cheng-Ju Hsu, Chun-Nan Tsai, Richard Tzong-Han Dai, Hong-Jie Okazaki, Naoaki Cho, Han-Cheol Gerner, Martin Solt, Illes Agarwal, Shashank Liu, Feifan Vishnyakova, Dina Ruch, Patrick Romacker, Martin Rinaldi, Fabio Bhattacharya, Sanmitra Srinivasan, Padmini Liu, Hongfang Torii, Manabu Matos, Sergio Campos, David Verspoor, Karin Livingston, Kevin M. Wilbur, W. John Natl Lib Med Natl Ctr Biotechnol Informat Bethesda MD 20894 USA Natl Cheng Kung Univ Dept Comp Sci & Informat Engn Tainan 70101 Taiwan Tsinghua Univ Dept Comp Sci & Technol Beijing 100084 Peoples R China Acad Sinica Inst Informat Sci Taipei 115 Taiwan Univ So Calif Inst Informat Sci Marina Del Rey CA 90292 USA Yuan Ze Univ Dept Comp Sci & Engn Chungli Taiwan Natl Tsing Hua Univ Dept Comp Sci Hsinchu 30043 Taiwan Univ Tokyo Interfac Initiat Informat Studies Tokyo 1138654 Japan Univ Tokyo Grad Sch Informat Sci & Technol Tokyo 1138654 Japan Univ Manchester Fac Life Sci Manchester M13 9PT Lancs England Budapest Univ Technol & Econ Dept Telecommun & Media Informat H-1117 Budapest Hungary Univ Wisconsin Milwaukee WI 53201 USA Univ Geneva Div Med Informat Sci BiTem Grp CH-1211 Geneva 4 Switzerland Univ Appl Sci Dept Informat Sci BiTeM Grp Geneva Switzerland Novartis AG NITAS TMS Text Min Serv Basel Switzerland Univ Zurich Inst Computat Linguist Zurich Switzerland Univ Iowa Dept Comp Sci Iowa City IA 52242 USA Mayo Clin Coll Med Dept Hlth Sci Res Rochester MN 55905 USA Georgetown Univ Med Ctr Lab Text Intelligence Biomed Washington DC 20057 USA Univ Aveiro DETI IEETA P-3810193 Aveiro Portugal Univ Colorado Sch Med Ctr Computat Pharmacol Aurora CO USA

Background: We report the Gene Normalization (GN) challenge in BioCreative III where participating teams were asked to return a ranked list of identifiers of the genes detected in full-text articles. For training, 32 fully and 500 partially annotated articles were prepared. A total of 507 articles were selected as the test set. Due to the high annotation cost, it was not feasible to obtain gold-standard human annotations for all test articles. Instead, we developed an expectation maximization (EM) algorithm approach for choosing a small number of test articles for manual annotation that were most capable of differentiating team performance. Moreover, the same algorithm was subsequently used for inferring ground truth based solely on team submissions. We report team performance on both gold standard and inferred ground truth using a newly proposed metric called Threshold Average Precision (TAP-k). Results: We received a total of 37 runs from 14 different teams for the task. When evaluated using the gold-standard annotations of the 50 articles, the highest TAP-k scores were 0.3297 (k=5), 0.3538 (k=10), and 0.3535 (k=20), respectively. Higher TAP-k scores of 0.4916 (k=5, 10, 20) were observed when evaluated using the inferred ground truth over the full test set. When combining team results using machine learning, the best composite system achieved TAP-k scores of 0.3707 (k=5), 0.4311 (k=10), and 0.4477 (k=20) on the gold standard, representing improvements of 12.4%, 21.8%, and 26.6% over the best team results, respectively. Conclusions: By using full text and being species non-specific, the GN task in BioCreative III has moved closer to a real literature curation task than similar tasks in the past and presents additional challenges for the text mining community, as revealed in the overall team results. By evaluating teams using the gold standard, we show that the EM algorithm allows team submissions to be differentiated while keeping the manual annotation effort feasi

关键词： Confidence Score expectation maximization algorithm Name Entity Recognition Gene Mention Human Annotation

来源：评论

学校读者我要写书评

暂无评论

Fault reconnaissance agent for sensor networks

引用

MOBILE INFORMATION SYSTEMS 2010年第3期6卷 229-247页

作者： Shakshuki, Elhadi M. Xing, Xinyu Sheltami, Tarek R. Acadia Univ Jodrey Sch Comp Sci Wolfville NS B4P 2R6 Canada Univ Colorado Dept Comp Sci Boulder CO 80309 USA King Fahd Univ Petr & Minerals Dept Comp Engn Dhahran 31261 Saudi Arabia

One of the key prerequisite for a scalable, effective and efficient sensor network is the utilization of low-cost, low-overhead and high-resilient fault-inference techniques. To this end, we propose an intelligent agent system with a problem solving capability to address the issue of fault inference in sensor network environments. The intelligent agent system is designed and implemented at base-station side. The core of the agent system - problem solver - implements a fault-detection inference engine which harnesses expectation maximization (EM) algorithm to estimate fault probabilities of sensor nodes. To validate the correctness and effectiveness of the intelligent agent system, a set of experiments in a wireless sensor testbed are conducted. The experimental results show that our intelligent agent system is able to precisely estimate the fault probability of sensor nodes.

关键词： Management intelligent agents expectation maximization algorithm wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Parameter Estimation for a Bidimensional Partially Observed Ornstein-Uhlenbeck Process with Biological Application

引用

SCANDINAVIAN JOURNAL OF STATISTICS 2010年第2期37卷 200-220页

作者： Favetto, Benjamin Samson, Adeline Univ Paris 05 Lab MAP5 UMR CNRS 8145 F-75006 Paris France

We consider a bidimensional Ornstein-Uhlenbeck process to describe the tissue microvascularization in anti-cancer therapy. Data are discrete, partial and noisy observations of this stochastic differential equation (SDE). Our aim is to estimate the SDE parameters. We use the main advantage of a one-dimensional observation to obtain an easy way to compute the exact likelihood using the Kalman filter recursion, which allows to implement an easy numerical maximization of the likelihood. Furthermore, we establish the link between the observations and an ARMA process and we deduce the asymptotic properties of the maximum likelihood estimator. We show that this ARMA property can be generalized to a higher dimensional underlying Ornstein-Uhlenbeck diffusion. We compare this estimator with the one obtained by the well-known expectation maximization algorithm on simulated data. Our estimation methods can be directly applied to other biological contexts such as drug pharmacokinetics or hormone secretions.

关键词： ARMA process expectation maximization algorithm hidden Markov model Kalman filter maximum likelihood estimation Ornstein-Uhlenbeck process partial observations

来源：评论

学校读者我要写书评

暂无评论

A two-component nonlinear mixed effects model for longitudinal data, with application to gastric emptying studies

引用

STATISTICS IN MEDICINE 2010年第17期29卷 1839-1856页

作者： Kim, Inyoung Cohen, Noah D. Roussel, Allen Wang, Naisyin Virginia Polytech Inst & State Univ Dept Stat Blacksburg VA 24061 USA Texas A&M Univ Coll Vet Med Dept Large Anim Clin Sci College Stn TX 77843 USA Texas A&M Univ Dept Stat College Stn TX 77843 USA

Gastric emptying studies are of great interest in human and veterinary medical research to evaluate effects of medications or diets for promoting gastrointestinal motility and to examine unintended side-effects of new or existing medications, diets, or procedures. Summarizing gastric emptying data is important to allow easier comparison between treatments or groups of subjects and comparisons of results among studies. The standard method for assessing gastric emptying is by using scintigraphy and summarizing the nonlinear emptying of the radioisotope. A popular model for fitting gastric emptying data is the power exponential model. This model can only describes a globally decreasing pattern and thus has the limitation of poorly describing localized intragastric events that can occur during emptying. Hence, we develop a new model for gastric emptying studies to improve population and individual inferences using a mixture of nonlinear mixed effects models. One mixture component is based on a power exponential model which captures globally decreasing patterns. The other is based on a locally extended power exponential model which captures both local bumping and rapid decay. We refer to this mixture model as a two-component nonlinear mixed effects model. The parameters in our model have clear graphical interpretations that provide a more accurate representation and summary of the curves of gastric emptying pattern. Two methods are developed to fit our proposed model: one is the mixture of an expectation maximization algorithm and a global two-stage method and the other is the mixture of an expectation maximization algorithm and the Monte Carlo expectation maximization algorithm. We compare our methods using simulation, showing that the two approaches are comparable to one another. For estimating the variance and covariance matrix, the second approach appears approximately more efficient and is also numerically more stable in some cases. Our new model and approaches are

关键词： expectation maximization algorithm global two-stage method random coefficient model

来源：评论

学校读者我要写书评

暂无评论

FACTOR ANALYZED VOICE MODELS FOR HMM-BASED SPEECH SYNTHESIS

FACTOR ANALYZED VOICE MODELS FOR HMM-BASED SPEECH SYNTHESIS

引用

2010 IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： Kazumi, Kyosuke Nankaku, Yoshihiko Tokuda, Keiichi Nagoya Inst Technol Nagoya Aichi Japan

ISBN: (纸本)9781424442966

This paper describes factor analyzed voice models for realizing various voice characteristics in the HMM-based speech synthesis. The eigenvoice method can synthesize speech with arbitrary voice characteristics by interpolating representative HMM sets. However, the objective of PCA is to accurately reconstruct each speaker-dependent HMM set, and this is not equivalent to estimating models which represent training data accurately. To overcome this problem, we propose a general speech model which generates speech utterances with various voice characteristics directly. In the proposed method, the HMM states, factors representing voice characteristics and contextual decision trees are simultaneously optimized within a unified framework.

关键词： HMM-based speech synthesis eigenvoice factor analysis expectation maximization algorithm deterministic annealing EM 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：