检索结果-内蒙古大学图书馆

2007 IEEE International Conference on Multimedia and Expo (ICME 2007), vol.3

作者： Wenming Lu Wanqing Li Rei Safavi-Naini Philip Ogunbona University of Wollongong Australia

Based on the observation that an attack applied on a watermarked image, from a decoding point of view, modifies the distribution of the detection values away from the ideal distribution (without attack) for corresponding watermarking scheme, we propose a generic maximum likelihood decoding scheme by approximating the distribution with a finite Gaussian mixture model. The parameters of the model are estimated using expectation-maximization algorithm. The scheme allows the decoding to be automatically adapted to attacks that the watermarked images have undergone and, in consequence, to improve the decoding accuracy. Experiments on a QIM based watermarking system have clearly verified the significant improvement of the decoding accuracy achieved by the proposed maximum likelihood decoding in comparison to conventional threshold decoding.

关键词： Watermarking Maximum likelihood decoding Maximum likelihood estimation Maximum likelihood detection Noise robustness Additive noise Image coding Parameter estimation expectation-maximization algorithms Image processing

来源：评论

学校读者我要写书评

暂无评论

Stochastic Modeling and Quantization of Harmonic Phases in Speech using Wrapped Gaussian Mixture Models

Stochastic Modeling and Quantization of Harmonic Phases in S...

引用

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

作者： Yannis Agiomyrgiannakis Yannis Stylianou Department of Computer Science Hellas and Institute of Computer Science University of Crete Forth Greece

Harmonic sinusoidal representations of speech have proven to be useful in many speech processing tasks. This work focuses on the phase spectra of the harmonics and provides a methodology to analyze and subsequently to model the statistics of the harmonic phases. To do so, we propose the use of a wrapped Gaussian mixture model (WGMM), a model suitable for random variables that belong to circular spaces, and provide an expectation-maximization algorithm for training. The WGMM is then used to construct a phase quantizer. The quantizer is employed in a prototype variable rate narrow-band VoIP sinusoidal codec that is equivalent to iLBC in terms of PESQ-MOS, at ~13 kbps.

关键词： Stochastic processes Quantization Speech processing Harmonic analysis Statistical analysis Random variables expectation-maximization algorithms Prototypes Narrowband Codecs

来源：评论

学校读者我要写书评

暂无评论

Multiscale Reconstruction for Photon-Limited Shifted Excitation Raman Spectroscopy

Multiscale Reconstruction for Photon-Limited Shifted Excitat...

引用

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

作者： Rebecca Willett Department of Electrical and Computer Engineering Duke University Durham NC USA

Shifted excitation Raman spectroscopy results in multiple observations of the sum of a material's fluorescent and Raman spectra. The fluorescent spectrum is typically stationary with respect to the excitation frequency induced by the instrument, while the Raman spectrum is subject to a nonlinear shift which depends explicitly and in a known manner upon the excitation frequency. This phenomenon has been exploited to reconstruct Raman spectra indirectly by subtracting spectra observed at two closely spaced excitation frequencies. The technique, known as shifted excitation Raman difference spectroscopy (SERDS), is of limited utility, however, in that observations with low photon counts are difficult to process accurately, and that one must still reconstruct the spectrum from the estimate of the derivative. This paper presents an innovative alternative approach to Raman spectrum reconstruction based on an expectation-maximization algorithm and multiresolution photon-limited signal analysis. Using this method, it is shown that using multiple excitation frequencies (while keeping the total excitation laser power and total expected photon counts constant) can result in dramatic improvements in reconstruction accuracy.

关键词： Raman scattering Spectroscopy Frequency Fluorescence Laser excitation Instruments expectation-maximization algorithms Signal resolution Signal analysis Power lasers

来源：评论

学校读者我要写书评

暂无评论

Linear Dynamical System Response Modeling of Trial-to-Trial Amplitude Variability in Event-Related MEG/EEG

Linear Dynamical System Response Modeling of Trial-to-Trial ...

引用

IEEE/SP Workshop on Statistical Signal Processing (SSP)

作者： Tulaya Limpiti Barry D. Van Veen Srikantan S. Nagarajan Hagai T. Attias Department of Electrical and Computer Engineering University of Wisconsin Madison Madison WI USA Biomagnetic Imaging Lab Department of Radiology University of California San Francisco San Francisco CA USA Joint Graduate Group in Bioengineering UCSF UC Berkeley CA USA Golden Metallic Inc. San Francisco CA USA

We propose a linear dynamical system response (LDSR) model to describe amplitude variability across trials in event-related magnetoencephalographic/electroencephalographic (MEG/EEG) data. Variability across trials may reflect habituation, fatigue, or changes in cognitive states of the brain. A wide range of trial-to-trial variability can be represented using the LDSR model, including the constant response (CR) model as a limiting case. The spatiotemporal signal waveform is assumed constant but unknown, and is represented using a linear combination of spatial and temporal basis functions. The background noise is assumed to be spatially correlated with unknown covariance matrix. We obtain the maximum-likelihood estimates of the amplitude variability and signal waveform via a generalized expectation-maximization algorithm. The expectation step involves a Kalman fixed-interval smoother which tracks the trial-to-trial amplitude variability while the maximization step estimates the signal waveform, spatial noise covariance, and LDSR model parameters. We demonstrate the effectiveness of the proposed model using both real and simulated evoked response data. The performance of the algorithm is analyzed in terms of the mean squared error of the amplitude estimates.

关键词： Brain modeling Electroencephalography Amplitude estimation Fatigue Chromium Spatiotemporal phenomena Background noise Covariance matrix Maximum likelihood estimation expectation-maximization algorithms

来源：评论

学校读者我要写书评

暂无评论

An Efficient expectation-Maximisation Algorithm for Spike Classification

An Efficient Expectation-Maximisation Algorithm for Spike Cl...

引用

International Conference on Digital Signal Processing (DSP)

作者： Pedro Tomas Leonel Sousa INESC-ID/IST Technical University of Lisbon Lisboa Portugal

This paper presents a new expectation-Maximisation algorithm for classifying a data set originated from an unknown number of sources. The proposed algorithm is based on the Kullback-Leibler divergence and uses a minimum message length criteria to penalise adding extra data sources. It is able to estimate the parameters of the model for each data source and to determine the total number of sources producing the data. We apply our algorithm to the classification of spikes originated from multiple neurons but recorded by a single microelectrode. The obtained experimental results show the effectiveness of the proposed algorithm.

关键词： expectation-maximization algorithms Iterative algorithms Neurons Retina Microelectrodes Unsupervised learning Blind source separation Parameter estimation Classification algorithms Extracellular

来源：评论

学校读者我要写书评

暂无评论

Scintillation Time Series Synthesis for Satellite Links with Hidden Markov Model

Scintillation Time Series Synthesis for Satellite Links with...

引用

International Workshop on Satellite and Space Communications (IWSSC)

作者： Laszlo Csurgai-Horvath Janos Bito Department of Broadband Infocommunications and Electromagnetic Theory Budapest University슠of슠Technology슠and슠Economics Budapest Hungary

This paper introduces a method to model the rapid attenuation fluctuations (the scintillation) on satellite links with generating the time series of attenuation levels. The applied model is a hidden Markov model which is parameterized from an appropriate filtered Gaussian white noise signal. For the parameterization of the Markov chain the Baum-Welch expectation-maximization algorithm has been used. The resulting Markov model is applicable to generate scintillation time series for any desired duration with the time and amplitude resolution of the original training data. From the synthesized time series the statistical properties like the cumulative distribution and the dynamics of the scintillation can be also determined. To prove the accuracy of the model at first the cumulative distribution function of the original and synthesized time series are compared. A further test of the model validity is the comparison with real scintillation measurement on a land mobile satellite link. Finally, the spectral test of the filtered Gaussian model, the hidden Markov model and the satellite link measurement shows that the constant and decreasing parts in the periodograms are showing similarities what confirms the good quality of the model.

关键词： Satellites Hidden Markov models Signal synthesis Attenuation Testing Fluctuations White noise expectation-maximization algorithms Signal resolution Training data

来源：评论

学校读者我要写书评

暂无评论

New Detectors for Watermarks with Unknown Power Based on Student-t Image Priors

New Detectors for Watermarks with Unknown Power Based on Stu...

引用

IEEE Workshop on Multimedia Signal Processing

作者： Antonis Mairgiotis Giannis Chantas Nikolaos Galatsanos Konstantinos Blekas Yongyi Yang Department of Computer Science University of Ioannina (UoI) Ioannina Greece Department of Electrical and Computer Engineering Illinois Institute of Technology Chicago IL USA

ISBN: (纸本)9781424412730

In this paper we present new detectors for additive watermarks when the power of the watermark is unknown. These detectors are based on modeling the image using student-t statistics. As a result, due to the generative properties of the student-t density function, such models are spatially adaptive and the expectation-maximization algorithm can be used to obtain maximum likelihood estimates of their parameters. Using these image models detectors based on the generalized likelihood ratio and Rao tests are derived for this problem. Numerical experiments are presented that demonstrate the properties of these detectors and compared them with previously proposed detectors.

关键词： Detectors Watermarking Additives Statistics Density functional theory expectation-maximization algorithms Maximum likelihood detection Maximum likelihood estimation Parameter estimation Testing

来源：评论

学校读者我要写书评

暂无评论

Estimation of Node Losses in Optical Burst Switched Networks Using Network Tomography

Estimation of Node Losses in Optical Burst Switched Networks...

引用

IEEE GLOBECOM 2007 - IEEE Global Telecommunications Conference

作者： A. Sankar Adida T. Venkatesh Tamarapalli C. Siva Ram Murthy Indian Institute of Technology Madras Chennai Tamil Nadu IN Department of Computer Science and Engineering Indian Institute of Technology Madras Chennai India

Optical burst switching (OBS) is envisioned as the paradigm for a high-bandwidth Internet. Losses due to contention is a serious problem in OBS networks. Since the core nodes have limited capabilities, loss rate cannot be determined at the nodes. Thus, estimating the losses on a path purely based on end-to-end measurements and thereafter develop proactive measures for loss reduction is an attractive option. For the first time, we apply a tomographic technique that can estimate the losses at the core nodes from end-to-end measurement between the edge nodes. We use passive unicast tomography to minimize the network overhead. We model the problem of estimating loss rate at the nodes from path-level measurements as a maximum likelihood problem and solve it using the expectation-maximization algorithm. In simulations, we use a multiple source, multiple destination embedding on the NSFNET topology and observe losses on multiple paths to infer losses at the core nodes. The estimated losses are found to match closely with actual losses measured.

关键词： Optical losses Optical fiber networks Tomography Loss measurement Optical burst switching Internet Time measurement Unicast Maximum likelihood estimation expectation-maximization algorithms

来源：评论

学校读者我要写书评

暂无评论

Receiver design for MIMO OFDM transmission over time variant channels

Receiver design for MIMO OFDM transmission over time variant...

引用

IEEE Workshop on Signal Processing Advances in Wireless Communications (SPAWC)

作者： Tareq Y. Al-Naffouri Electrical Engineering Department King Fahd University of Petroleum and Minerals Saudi Arabia

This paper considers receiver design for space time block coded MIMO OFDM transmission over frequency and time selective channels. The receiver employs the expectation-maximization algorithm for joint channel and data recovery. It makes collective use of the data and channel constraints of the communication problem. The data constraints include pilots, the cyclic prefix, the finite alphabet constraint, and space-time block coding. The channel constraints include the finite delay spread and frequency and time correlation as well as spatial correlation. The channel estimation part of the receiver boils down to an EM-based forward-backward Kalman filter. To avoid the latency and storage associated with smoothing, we introduce a forward-only Kalman that performs channel (and data) recovery with no latency. Simulations show that the receiver outperforms other least-squares based iterative receivers.

关键词： MIMO OFDM Channel estimation Block codes Delay effects Delay estimation Frequency estimation Petroleum Minerals expectation-maximization algorithms

来源：评论

学校读者我要写书评

暂无评论

Relevance feedback based on non-negative matrix factorisation for image retrieval

引用

IEE PROCEEDINGS-VISION IMAGE AND SIGNAL PROCESSING 2006年第4期153卷 436-444页

作者： Liang, D. Yang, J. Chang, Y. Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Shanghai 200030 Peoples R China

As a powerful tool for content-based image retrieval, many techniques have been proposed for relevance feedback. A non-negative matrix factorisation (NMF)-based relevance feedback approach is introduced. This approach uses a standard NMF algorithm to construct a reliable semantic space from a pool of relevant images based on a user's interactions, because the latent semantic space derived by NMF does not need to be orthogonal, and each image is guaranteed to take only non-negative values in all the latent semantic directions. It means that each axis in the space derived by NMF has a straightforward correspondence with each image semantic class. In addition, the hidden semantic features of the query and images in the database are extracted with an NMF-projecting algorithm. By memorising the feedback information provided by the user, the knowledge accumulated from past relevance interaction is used to update semantic space, which results in the semantic space being closer to the user's expectation. The experiments show that the proposed NMF-based relevance feedback approach performs better than other relevance feedback approaches.

关键词： INFORMATION retrieval PRINCIPAL components analysis FACTOR analysis expectation-maximization algorithms IMAGE processing IMAGING systems

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：