In this paper we adapt online estimation strategies to perform model-based clustering on large networks. Our work focuses on two algorithms, the first based on the SAem algorithm, and the second on variational methods...
详细信息
In this paper we adapt online estimation strategies to perform model-based clustering on large networks. Our work focuses on two algorithms, the first based on the SAem algorithm, and the second on variational methods. These two strategies are compared with existing approaches on simulated and real data. We use the method to decipher the connexion structure of the political websphere during the US political campaign in 2008. We show that our online em-based algorithms offer a good trade-off between precision and speed, when estimating parameters for mixture distributions in the context of random graphs.
In this paper, we extend the latent segmentation approach to the Kuhn-Tucker (KT) model. The proposed approach models heterogeneity in preferences for recreational behavior, using a utility theoretical framework to si...
详细信息
In this paper, we extend the latent segmentation approach to the Kuhn-Tucker (KT) model. The proposed approach models heterogeneity in preferences for recreational behavior, using a utility theoretical framework to simultaneously model participation and site selection decisions. Estimation of the latent segmentation KT model with standard maximum likelihood techniques is numerically difficult because of the large number of parameters in the segment membership functions and the utility function for each latent segment. To address this problem, we propose the expectation-maximization (em) algorithm to estimate the model. In the empirical section, we implement the em latent segmentation KT approach to analyze a Southern California beach recreation data set. Our empirical analysis suggests that three groups exist in the sample. Using the model to analyze two hypothetical beach management policy scenarios illustrates different welfare impacts across groups. (C) 2010 Elsevier Inc. All rights reserved.
in this paper, we address the problem of image categorization with a fast novel method based on the unsupervised clustering of graphs in the context of both region-based segmentation and the constellation approach to ...
详细信息
in this paper, we address the problem of image categorization with a fast novel method based on the unsupervised clustering of graphs in the context of both region-based segmentation and the constellation approach to object recognition. Such method is an em central clustering algorithm which builds prototypical graphs on the basis of either Softassign or fast matching with graph transformations. We present two realistic applications and their experimental results: categorization of image segmentations and visual localization. We compare our graph prototypes with the set median graphs. Our results reveal that, on the one hand, structure extracted from images improves appearance-based visual localization accuracy. On the other hand, we show that the cost of our central graph clustering algorithm is the cost of a pairwise algorithm. We also discuss how the method scales with an increasing amount of images. In addition, we address the scientific question of what are the bounds of structural learning for categorization. Our in-depth experiments both for region-based and feature-based image categorization, will show that such bounds depend hardly on structural variability. (C) 2008 Elsevier B.V. All rights reserved.
In this paper, we propose a series of techniques to enhance the computational performance of existing Belief Propagation (BP) based stereo matching that relies on automatic estimation of the Markov random field (MRF) ...
详细信息
ISBN:
(纸本)9781424417650
In this paper, we propose a series of techniques to enhance the computational performance of existing Belief Propagation (BP) based stereo matching that relies on automatic estimation of the Markov random field (MRF) parameters. First, we show how convergence in matching can be achieved faster than with the existing message comparison technique by skipping comparisons in early inferences. Second, assuming that a stereo pair is captured. with identical cameras, we apply a hypothesis called noise equivalence to pre-estimate the likelihood parameters and thus, avoid costly nested inferences to reduce the computational time. The likelihood parameters and intensity information are used for accelerated message propagation in image regions lacking gradients. Third, the prior model parameters are estimated with a combination of maximum likelihood (ML) estimation and disparity gradient constraint to further reduce the computational time. Supporting experiments for the proposed algorithms show encouraging results on ground truth test images.
Objective. A recent study of adenocarcinoma of the oesophagus (ACO) incidence rates in Denmark showed a steep fall in the over-80 population, interpreted as the result of a decline in the prevalence of Barrett's o...
详细信息
Objective. A recent study of adenocarcinoma of the oesophagus (ACO) incidence rates in Denmark showed a steep fall in the over-80 population, interpreted as the result of a decline in the prevalence of Barrett's oesophagus (BO) in this age group, for which three hypotheses were advanced: the specific mortality from ACO and, superimposed, either excess mortality from causes of death unrelated to ACO or a birth cohort effect. The aim of this study was to create models estimating the BO population fitting each of these three hypotheses, in order to select the most plausible hypothesis and to gain insight into the Danish BO population. Material and methods. Models were designed for these three hypotheses, conforming to the generally accepted 0.4 - 0.5% annual ACO incidence in BO patients. These models employed expectation-maximization ( em) algorithms, Danish life tables and the observed ACO incidence rates. The models enabled the estimation of a BO population for each hypothesis. Results. After testing against set criteria, the most plausible model was found to be that describing a birth cohort effect which predicted a +/- 5% annual rise in the prevalence of BO and, consequently, in the incidence rate of ACO in Denmark. This prediction was borne out over the subsequent decade. Conclusions. This rising ACO incidence rate is likely to continue into the foreseeable future. The use of em algorithms enabled a first estimate of the BO population at risk of ACO, although, owing to the limitations imposed by the models, the age- and gender-specific ACO risk for the entire Danish BO population could not as yet be ascertained.
A particle filtering algorithm using the parameters in the em (Expectation-Maximization) algorithm is proposed for tracking multiple sound sources. Differently from the conventional em based algorithms, the proposed a...
详细信息
ISBN:
(纸本)9781424407286
A particle filtering algorithm using the parameters in the em (Expectation-Maximization) algorithm is proposed for tracking multiple sound sources. Differently from the conventional em based algorithms, the proposed algorithm can track multiple sound sources without knowing their starting points. Moreover, an idea of the group tracking is applied to the particle filtering algorithm so that better tracking performances can be obtained. Experimental results show the validity of the proposed algorithm.
Motivation: Motif identification for sequences has many important applications in biological studies, e.g., diagnostic probe design, locating binding sites and regulatory signals, and potential drug target identificat...
详细信息
ISBN:
(纸本)9783540734369
Motivation: Motif identification for sequences has many important applications in biological studies, e.g., diagnostic probe design, locating binding sites and regulatory signals, and potential drug target identification. There are two versions. 1. Single Group: Given a group of n sequences, find a length-l motif that appears in each of the given sequences and those occurrences of the motif are similar. 2. Two Groups: Given two groups of sequences B and G, find a length-1 (distinguishing) motif that appears in every sequence in B and does not appear in anywhere of the sequences in G. Here the occurrences of the motif in the given sequences have errors. Currently, most of existing programs can only handle the case of single group. Moreover, it is very difficult to use edit distance (allowing indels and replacements) for motif detection. Results: (1) We propose a randomized algorithm for the one group problem that can handle indels in the occurrences of the motif. (2) We give an algorithm for the two groups problem. (3) Extensive simulations have been done to evaluate the algorithms.
In this paper, we address the problem of comparing and classifying protein surfaces with graph-based methods. Comparison relies on matching surface graphs, extracted from the surfaces by considering concave and convex...
详细信息
In this paper, we address the problem of comparing and classifying protein surfaces with graph-based methods. Comparison relies on matching surface graphs, extracted from the surfaces by considering concave and convex patches, through a kernelized version of the Softassign graph-matching algorithm. On the other hand, classification is performed by clustering the surface graphs with ail em-like algorithm, also relying on kernelized Softassign, and then calculating the distance of an input surface graph to the closest prototype. We present experiments showing the Suitability of kernelized Softassign for both comparing and classifying surface graphs. (c) 2005 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.
In order to alleviate the problem of local convergence of the usual em algorithm, a split-and-merge operation is introduced into the em algorithm for Gaussian mixtures. The split-and-merge equations are first presente...
详细信息
In order to alleviate the problem of local convergence of the usual em algorithm, a split-and-merge operation is introduced into the em algorithm for Gaussian mixtures. The split-and-merge equations are first presented theoretically. These equations show that the merge operation is a well-posed problem, whereas the split operation is an ill-posed problem because it is the inverse procedure of the merge. Two methods for solving this ill-posed problem are developed through the singular value decomposition and the Cholesky decomposition. Accordingly, a new modified em algorithm is constructed. Our experiments demonstrate that this algorithm is efficient for unsupervised color image segmentation. (C) 2003 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.
In this paper we describe an algorithm designed for learning perceptual organization of an autonomous agent. The learning algorithm performs incremental clustering of a perceptual input under reward. The distribution ...
详细信息
In this paper we describe an algorithm designed for learning perceptual organization of an autonomous agent. The learning algorithm performs incremental clustering of a perceptual input under reward. The distribution of the input samples is modeled by a Gaussian mixture density, which serves as a state space for the policy learning algorithm. The agent learns to select actions in response to the presented stimuli simultaneously with estimating the parameters of the input mixture density. The feedback from the environment is given to the agent in the form of a scalar value, or a reward, which represents the utility of a particular clustering configuration for the action selection. The setting of the learning task makes it impossible to use supervised or partially supervised techniques to estimate the parameters of the input density. The paper introduces the notion of weak transduction and shows a solution to it using an em-based framework. (C) 2002 Elsevier Science B.V. All rights reserved.
暂无评论