检索结果-内蒙古大学图书馆

IEEE Conference on Computational Intelligence and Games (CIG)

作者： Synnaeve, Gabriel Bessiere, Pierre

ISBN: (纸本)9781457700095

This paper presents a Bayesian model to predict the opening (first strategy) of opponents in real-time strategy (RTS) games. Our model is general enough to be applied to any RTS game with the canonical gameplay of gathering resources to extend a technology tree and produce military units and we applied it to StarCraft1. This model can also predict the possible technology trees of the opponent, but we will focus on openings here. The parameters of this model are learned from replays (game logs), labeled with openings. We present a semi-supervised method of labeling replays with the expectation-maximization algorithm and key features, then we use these labels to learn our parameters and benchmark our method with cross-validation. Uses of such a model range from a commentary assistant (for competitive games) to a core component of a dynamic RTS bot/AI, as it will be part of our StarCraft AI competition entry bot.

关键词： Bayes methods Bayesian methods Bayesian model Buildings Games Hidden Markov models Labeling Predictive models RTS game StarCraft commentary assistant competitive game computer games expectation-maximisation algorithm expectation-maximization algorithm opening prediction real-time strategy game semisupervised method

来源：评论

学校读者我要写书评

暂无评论

algorithms for iterative phase noise estimation based on a truncated DCT expansion

Algorithms for iterative phase noise estimation based on a t...

引用

12th IEEE International Workshop on Signal Processing Advances in Wireless Communications

作者： Bhatti, Jabran Noels, Nele Moeneclaey, Marc Univ Ghent Dept Telecommun & Informat Proc Ghent Belgium

ISBN: (纸本)9781424493326

We present two phase noise estimation algorithms for single-carrier burst communications. The first and second estimation techniques (denoted as PEA1 and PEA2 respectively) are based on a truncated discrete cosine transform (DCT) basis expansion of the phase noise and of the corresponding phasor, respectively and do not require any knowledge of the phase noise statistics. An initial pilot-based estimate is iteratively improved by means of the expectation-maximization algorithm, yielding a soft-decision-directed phase noise estimate. The performances of PEA1 and PEA2 are compared in terms of the mean-square phase error and bit-error rate. Numerical results show that PEA2 out performs PEA1 for practical values of the signal-to-noise ratio.

关键词： algorithm design and analysis Bit error rate Discrete cosine transforms Estimation Phase estimation Phase noise Signal processing algorithms bit-error rate channel estimation discrete cosine transforms error statistics expectation-maximisation algorithm expectation-maximization algorithm iterative phase noise estimation algorithm phase noise signal-to-noise ratio single-carrier burst communications telecommunication networks truncated DCT expansion truncated discrete cosine transform

来源：评论

学校读者我要写书评

暂无评论

EM-based Channel Estimation in OFDM Systems with Phase Noise

EM-based Channel Estimation in OFDM Systems with Phase Noise

引用

54th Annual IEEE Global Telecommunications Conference (GLOBECOM)

作者： Carvajal, Rodrigo Agueero, Juan C. Godoy, Boris I. Goodwin, Graham C. Univ Newcastle Callaghan NSW 2308 Australia

ISBN: (纸本)9781424492688

In this paper we address the joint estimation of phase noise (PHN) and channel impulse response (CIR) in orthogonal frequency division multiplexing (OFDM) systems. We solve the estimation problem utilizing an algorithm based on a Monte Carlo (MC) implementation of the expectation-maximization (EM) algorithm. Our approach exploits the linear and Gaussian structure associated with the transmitted signal. We also focus on the impact that inaccurate estimation of PHN bandwidth has on the accuracy of the channel estimates. We show the benefits of the proposed algorithm via simulation studies.

关键词： Approximation methods Bandwidth Channel estimation EM-based channel estimation Estimation Gaussian processes Gaussian structure Monte Carlo implementation Monte Carlo methods Monte Carlo methods OFDM OFDM modulation OFDM systems Phase noise channel impulse response expectation-maximisation algorithm expectation-maximization algorithm linear structure orthogonal frequency division multiplexing phase noise phase noise

来源：评论

学校读者我要写书评

暂无评论

Robust EM Continual Reassessment Method in Oncology Dose Finding

引用

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION 2011年第495期106卷 818-831页

作者： Yuan, Ying Yin, Guosheng Univ Texas MD Anderson Canc Ctr Dept Biostat Unit 1411 Houston TX 77230 USA Univ Hong Kong Dept Stat & Actuarial Sci Hong Kong Hong Kong Peoples R China

The continual reassessment method (CRM) is a commonly used dose-finding design for phase I clinical trials. Practical applications of this method have been restricted by two limitations: (1) the requirement that the toxicity outcome needs to be observed shortly after the initiation of the treatment;and (2) the potential sensitivity to the prespecified toxicity probability at each dose. To overcome these limitations, we naturally treat the unobserved toxicity outcomes as missing data, and use the expectation-maximization (EM) algorithm to estimate the dose toxicity probabilities based on the incomplete data to direct dose assignment. To enhance the robustness of the design, we propose prespecifying multiple sets of toxicity probabilities, each set corresponding to an individual CRM model. We carry out these multiple CRMs in parallel, across which model selection and model averaging procedures are used to make more robust inference. We evaluate the operating characteristics of the proposed robust EM-CRM designs through simulation studies and show that the proposed methods satisfactorily resolve both limitations of the CRM. Besides improving the MTD selection percentage, the new designs dramatically shorten the duration of the trial, and are robust to the prespecification of the toxicity probabilities.

关键词： Adaptive design expectation-maximization algorithm Late-onset toxicity Maximum tolerated dose Missing data Model averaging Model selection

来源：评论

学校读者我要写书评

暂无评论

Semiparametric Efficient Estimation for a Class of Generalized Proportional Odds Cure Models

引用

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION 2010年第489期105卷 302-311页

作者： Mao, Meng Wang, Jane-Ling Univ Calif Davis Dept Stat Davis CA 95616 USA

We present a mixture cure model with the survival time of the "uncured" group coming from a class of linear transformation models, which is an extension of the proportional odds model This class of model. first proposed by Dabrowska and Doksum ( 988). which we term "generalized proportional odds model," is well suited for the mixture cure model setting due to a clear separation between long-term and short-term effects A standard expectation-maximization algorithm can he employed to locate the nonparametric likelihood estimators which are shown to he consistent and semiparametric efficient However. there are difficulties in the M-step due to the nonparametric component We overcome these difficulties by proposing two different algorithms The first is to employ an majorize-minimize (MM) algorithm in the M-step instead of the usual Newton-Raphson method, and the other is based on an alternative form to express the model as a proportional hazards frailty model The two new algorithms are compared in a simulation study with an existing estimating equation approach by DJ and Ying (2004) The MM algorithm provides both computational stability and efficiency A case study of leukemia dam is conducted to illustrate the proposed procedures

关键词： expectation-maximization algorithm Logistic regression Majorize-minimize algorithm Newton-Raphson algorithm Nonparametric maximum likelihood estimator Transformation model

来源：评论

学校读者我要写书评

暂无评论

Uplink Synchronization in OFDMA Spectrum-Sharing Systems

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2010年第5期58卷 2771-2782页

作者： Sanguinetti, Luca Morelli, Michele Poor, H. Vincent Univ Pisa Dept Informat Engn I-56126 Pisa Italy Princeton Univ Dept Elect Engn Princeton NJ 08544 USA

Spectrum sharing employs dynamic allocation of frequency resources for a more efficient use of the radio spectrum. Despite its appealing features, this technology inevitably complicates the synchronization task, which must be accomplished in an environment that may involve interference. This paper considers the uplink of an orthogonal frequency-division multiple-access (OFDMA)-based spectrum sharing system and provides solutions for estimating the frequency and timing errors of multiple unsynchronized users. In doing so, we exploit suitably designed training blocks and apply maximum likelihood methods after modeling the interference power on each subcarrier as a random variable with an inverse gamma distribution. The resulting frequency estimator turns out to be the extension to a multiuser scenario of a scheme that has previously been proposed for single-user spectrum-sharing systems. Timing recovery is more challenging and leads to a complete search over a multidimensional domain. To overcome such a difficulty, two alternative approaches are proposed. The first one relies on a simplifying assumption about the interference distribution in the frequency domain, while the second scheme operates in an iterative fashion according to the expectation-maximization algorithm.

关键词： expectation-maximization algorithm frequency estimation narrowband interference OFDMA spectrum sharing timing estimation

来源：评论

学校读者我要写书评

暂无评论

Differentiation of Two Subtypes of Adult Hydrocephalus by Mixture of Experts

引用

JOURNAL OF MEDICAL SYSTEMS 2010年第3期34卷 281-290页

作者： Ubeyli, Elif Derya Ilbay, Konuralp Ilbay, Gul Sahin, Deniz Akansel, Gur TOBB Ekon Teknol Univ Fac Engn Dept Elect & Elect Engn TR-06530 Ankara Turkey Kocaeli Univ Fac Med Dept Neurosurg TR-31380 Kocaeli Turkey Kocaeli Univ Fac Med Dept Physiol TR-31380 Kocaeli Turkey Kocaeli Univ Fac Med Dept Radiol TR-31380 Kocaeli Turkey

This paper illustrates the use of mixture of experts (ME) network structure to guide model selection for diagnosis of two subtypes of adult hydrocephalus (normal-pressure hydrocephalus-NPH and aqueductal stenosis-AS). The ME is a modular neural network architecture for supervised learning. expectation-maximization (EM) algorithm was used for training the ME so that the learning process is decoupled in a manner that fits well with the modular structure. To improve classification accuracy, the outputs of expert networks were combined by a gating network simultaneously trained in order to stochastically select the expert that is performing the best at solving the problem. The classifiers were trained on the defining features of NPH and AS (velocity and flux). Three types of records (normal, NPH and AS) were classified with the accuracy of 95.83% by the ME network structure. The ME network structure achieved accuracy rates which were higher than that of the stand-alone neural network models.

关键词： Mixture of experts expectation-maximization algorithm Normal-pressure hydrocephalus Aqueductal stenosis Classification accuracy

来源：评论

学校读者我要写书评

暂无评论

Statistical Modeling in the Wavelet Domain for Compact Feature Extraction and Similarity Measure of Images

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2010年第3期20卷 439-445页

作者： Yuan, Hua Zhang, Xiao-Ping Ryerson Univ Dept Elect & Comp Engn Toronto ON M5B 2K3 Canada

Image feature extraction and similarity measure in feature space are active research topics. They are basic components in a content-based image retrieval (CBIR) system. In this letter, we present a new statistical model-based image feature extraction method in the wavelet domain and a novel Kullback divergence-based similarity measure. First, a Gaussian mixture model (GMM) and a more systematic generalized Gaussian mixture model (GGMM) are employed to describe the statistical characteristics of the wavelet coefficients and the model parameters are employed to construct a compact image feature space. A nontrivial expectation-maximization (EM) algorithm for the GGMM model is derived. Subsequently, a new Kullback divergence-based similarity measure with low-computation cost is derived and analyzed. The Brodatz texture image database and some other image databases are used to evaluate the retrieval performance based on the presented new methods. Experimental results indicate that the GMM and the GGMM-based image texture features are very effective in representing multiscale image characteristics and that the new methods outperforms other conventional wavelet-based methods in retrieval performance with a comparable level of computational complexity. It is also demonstrated that for image features extracted by the new statistical models, the similarity measure based on Kullback divergence is more effective than conventional similarity measures.

关键词： expectation-maximization algorithm feature extraction Gaussian mixture model generalized Gaussian mixture model image retrieval Kullback divergence similarity measure wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Direct Importance Estimation with a Mixture of Probabilistic Principal Component Analyzers

引用

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2010年第10期E93D卷 2846-2849页

作者： Yamada, Makoto Sugiyama, Masashi Wichern, Gordon Simm, Jaak Tokyo Inst Technol Tokyo 1528552 Japan JST PRESTO Tokyo 1528552 Japan MIT Lincoln Lab Lexington MA 02420 USA

Estimating the ratio of two probability density functions (a.k.a. the importance) has recently gathered a great deal of attention since importance estimators can be used for solving various machine learning and data mining problems. In this paper, we propose a new importance estimation method using a mixture of probabilistic principal component analyzers. The proposed method is more flexible than existing approaches, and is expected to work well when the target importance function is correlated and rank-deficient. Through experiments, we illustrate the validity of the proposed approach.

关键词： importance Kullback-Leibler importance estimation procedure mixture of probabilistic principal component analyzers expectation-maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Joint NDA Estimation of Carrier Frequency/Phase and SNR for Linearly Modulated Signals

引用

IEEE SIGNAL PROCESSING LETTERS 2010年第5期17卷 517-520页

作者： Gappmair, Wilfried Lopez-Valcarce, Roberto Mosquera, Carlos Graz Univ Technol Inst Commun Networks & Satellite Commun A-8010 Graz Austria Univ Vigo Dept Signal Theory & Commun Vigo 36310 Spain

We consider the problem of joint non-data-aided (NDA) estimation of carrier frequency and phase offsets, together with that of signal and noise powers, obtained from the baud-rate samples of a linearly modulated signal distorted by Gaussian noise. The Cramer-Rao lower bound (CRLB) is derived, for quadrature-symmetric constellations showing that the carrier parameters are decoupled from signal and noise powers. Furthermore, a joint NDA maximum-likelihood estimator is developed, based on the application of the expectation-maximization algorithm, which exhibits a jitter performance close to the CRLB for a wide SNR range.

关键词： Carrier offset estimation Cramer-Rao lower bound expectation-maximization algorithm SNR estimation

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：