Positron emission tomography (PET) can reveal subtle metabolic process, which is an important modality for diagnosis. However, spatial resolution of PET images is not as good as computed tomography (CT) or magnetic re...
详细信息
Positron emission tomography (PET) can reveal subtle metabolic process, which is an important modality for diagnosis. However, spatial resolution of PET images is not as good as computed tomography (CT) or magnetic resonance imaging (MRI), which can show precise anatomical details. Our study is to improve image quality of PET using better reconstruction methods. In this paper, we use a new and efficient method to incorporate the correlated structural information obtained from MRI. A mean estimate smoothing the maximum likelihood estimate (MLE) locally within each region of interest is derived according to the boundaries provided by the structural information. Since the boundaries may not be correct, a penalized MLE using the mean estimate is sought. The resulting reconstruction is called a cross-reference maximum likelihood estimate (CRMLE). The CRMLE is obtained through a modified expectationmaximization (EM) algorithm, which is shown to be computationally efficient by our phantom and clinical studies.
In this paper, we propose a new expectation-maximization (EM) algorithm which speeds up the training of feedforward networks with local activation functions such as the Radial Basis Function (RBF) nctw ork. The core o...
详细信息
This paper introduces a uniform statistical framework for both 3-D and 2-D object recognition using intensity images as input data. The theoretical part provides a mathematical tool for stochastic modeling. The algori...
详细信息
This paper introduces a uniform statistical framework for both 3-D and 2-D object recognition using intensity images as input data. The theoretical part provides a mathematical tool for stochastic modeling. The algorithmic part introduces methods for automatic model generation, localization, and recognition of objects. 2-D images are used for learning the statistical appearance of 3-D objects;both the depth information and the matching between image and model features are missing for model generation. The implied incomplete data estimation problem is solved by the expectation maximization algorithm. This leads to a novel class of algorithms for automatic model generation from projections. The estimation of pose parameters corresponds to a non-linear maximum likelihood estimation problem which is solved by a global optimization procedure. Classification is done by the Bayesian decision rule. This work includes the experimental evaluation of the various facets of the presented approach. An empirical evaluation of learning algorithms and the comparison of different pose estimation algorithms show the feasibility of the proposed probabilistic framework.
In this article we consider robust filtering and smoothing for Markov Modulated Poisson Processes (MMPPs). Using the EM algorithm, these filters and smoothers can be applied to estimate the parameters of our model. Ou...
详细信息
ISBN:
(纸本)0780366387
In this article we consider robust filtering and smoothing for Markov Modulated Poisson Processes (MMPPs). Using the EM algorithm, these filters and smoothers can be applied to estimate the parameters of our model. Our dynamics do not involve stochastic integrals and our new formulae, in terms of time integrals, are easily discretized.
Finite-dimensional filters for integrals and stochastic integrals of moments of the state for continuous-time nonlinear systems with Benes nonlinearity are derived. These new filters can be used with the expectation m...
详细信息
Finite-dimensional filters for integrals and stochastic integrals of moments of the state for continuous-time nonlinear systems with Benes nonlinearity are derived. These new filters can be used with the expectationmaximization (EM) algorithm to compute maximum likelihood estimates of the model parameters.
In this paper the authors derive a new class of finite-dimensional recursive filters for linear dynamical systems. The Kalman filter is a special case of their general filter. Apart from being of mathematical interest...
详细信息
In this paper the authors derive a new class of finite-dimensional recursive filters for linear dynamical systems. The Kalman filter is a special case of their general filter. Apart from being of mathematical interest, these new finite-dimensional filters can be used with the expectationmaximization (EM) algorithm to yield maximum likelihood estimates of the parameters of a linear dynamical system. Important advantages of their filter-based EM algorithm compared with the standard smoother-based EM algorithm include: 1) substantially reduced memory requirements and 2) ease of parallel implementation on a multiprocessor system. The algorithm has applications in multisensor signal enhancement of speech signals and also econometric modeling.
Predicting conditional probability densities with neural networks requires complex (at least two-hidden-layer) architectures, which normally leads to rather long training times. By adopting the RVFL concept and constr...
详细信息
Predicting conditional probability densities with neural networks requires complex (at least two-hidden-layer) architectures, which normally leads to rather long training times. By adopting the RVFL concept and constraining a subset of the parameters to randomly chosen initial values (such that the EM-algorithm can be applied), the training process can be accelerated by about two orders of magnitude. This allows training of a whole ensemble of networks at the same computational costs as would be required otherwise for training a single model. The simulations performed suggest that in this way a significant improvement of the generalization performance can be achieved. (C) 1998 Elsevier Science Ltd. All rights reserved.
In this paper, we derive a new class of finite-dimensional filters for integrals and stochastic integrals of moments of the state for continuous-time linear Gaussian systems. Apart from being of significant mathematic...
详细信息
In this paper, we derive a new class of finite-dimensional filters for integrals and stochastic integrals of moments of the state for continuous-time linear Gaussian systems. Apart from being of significant mathematical interest, these new filters can be used with the expectationmaximization (EM) algorithm to yield maximum likelihood estimates of the model parameters.
In this paper we consider de-interleaving a finite number of stochastic parametric sources. The sources are modeled as independent autoregressive (AR) processes. Based on a Markovian switching policy, we assume that t...
详细信息
In this paper we consider de-interleaving a finite number of stochastic parametric sources. The sources are modeled as independent autoregressive (AR) processes. Based on a Markovian switching policy, we assume that the different sources transmit signals on the same single channel, The receiver records the 1-bit quantized version of the transmitted signal and aims to identify the sequence of active sources. Once the source sequence has been identified, the characteristics (parameters) of each source are estimated. We formulate the parametric pulse train de-interleaving problem as a 1-bit quantized Markov modulated AR series, The algorithm proposed in this paper combines Hidden Markov Model (HMM) and Binary Time Series (BTS) estimation techniques. Our estimation scheme generalizes Kedem's (1980) binary time series algorithm for linear time series to Markov modulated time series. (C) 1997 Elsevier Science B.V.
In this paper we propose algorithms for parameter estimation of fast-sampled homogeneous Markov chains observed in white Gaussian noise. Our algorithms are obtained by the robust discretization of stochastic different...
详细信息
In this paper we propose algorithms for parameter estimation of fast-sampled homogeneous Markov chains observed in white Gaussian noise. Our algorithms are obtained by the robust discretization of stochastic differential equations involved in the estimation of continuous-time Hidden Markov Models (HMM's) via the EM algorithm. We present two algorithms: The first is based on the robust discretization of continuous-time filters that were recently obtained by Elliott to estimate quantities used in the EM algorithm. The second is based on the discretization of continuous-time smoothers, yielding essentially the well-known Baum-Welch re-estimation equations. The smoothing formulas for continuous-time HMM's are new, and their derivation involves two sided stochastic integrals. The choice of discretization results in equations which are identical to those obtained by deriving the results directly in discrete time. The filter-based EM algorithm has negligible memory requirements;indeed, independent of the number of observations. In comparison the smoother-based discrete-time EM algorithm require the use of the forward-backward algorithm, which is a fixed-interval smoothing algorithm and has memory requirements proportional to the number of observations. On the other hand, the computational complexity of the filter-based EM algorithm is greater than that of the smoother-based scheme. However, the filters may be suitable for parallel implementation. Using computer simulations we compare the smoother-based and filter-based EM algorithms for HMM estimation. We provide also estimates for the discretization error.
暂无评论