5,723 Hits in 2.2 sec

Summarizing Finite Mixture Model with Overlapping Quantification

Shunki Kyoya, Kenji Yamanishi
2021 Entropy  
Finite mixture models are widely used for modeling and clustering data. When they are used for clustering, they are often interpreted by regarding each component as one cluster.  ...  The primary purpose of this paper is to establish a theoretical framework for interpreting the overlapping mixture models by estimating how they overlap, using measures of information such as entropy and  ...  Related Work on Finite Mixture Models and Model-Based Clustering In this section, we present related work on finite mixture models and model-based clustering in four parts: roles of overlap, model, optimization  ... 
doi:10.3390/e23111503 pmid:34828201 pmcid:PMC8622449 fatcat:64uxyo5pl5bdxen5zhxzqvn7gy

Data mapping by probabilistic modular networks and information-theoretic criteria

Yue Wang, Shang-Hung Lin, Huai Li, Sun-Yuan Kung
1998 IEEE Transactions on Signal Processing  
of each class model with locally mixture clusters; 2) estimation of the data distributions for each induced cluster inside each class; 3) classification of the data into classes that realizes the data  ...  Examples of the application of this framework to medical image quantification, automated face recognition, and featured database analysis, are presented as well.  ...  Local class distribution is modeled by a standard finite mixture.  ... 
doi:10.1109/78.735311 fatcat:32mcfazlingbvhbqrwhwf6ubu4

Quantification and segmentation of brain tissues from MR images: a probabilistic neural network approach

Yue Wang, T. Adah, Sun-Yuan Kung, Z. Szabo
1998 IEEE Transactions on Image Processing  
Index Terms-Finite mixture models, image segmentation, information theoretic criteria, model estimation, probabilistic neural networks, relaxation algorithm.  ...  The quantification is achieved by probabilistic self-organizing mixtures and the segmentation by a probabilistic constraint relaxation network.  ...  The MR brain image is modeled by a standard finite normal mixture model and an extended localized formulation.  ... 
doi:10.1109/83.704309 pmid:18172510 pmcid:PMC2171050 fatcat:iqhwaooehrbsraxeegf4xnfwvm

Automatic threshold selection using histogram quantization

Tulay Adali
1997 Journal of Biomedical Optics  
Experimental results show that this new approach is easy to implement yet is highly efficient, robust with respect to noise, and yields reliable estimates of the threshold levels. © 1997 Society of Photo-Optical  ...  In the quantification experiment, we used a standard finite normal mixture (SFNM) to model the true pixel density distribution and apply the EM algorithm to obtain the maximum likelihood estimate. 3,  ...  In our recent work, 4 we developed a framework by combining the SLMHQ step with a stochastic model-based technique for image quantification and segmentation.  ... 
doi:10.1117/12.268965 pmid:23014875 fatcat:wd2vugod4bh77eqcccqhuy6eli

Uncertainty in stretch extrapolation of laminar flame speed from expanding spherical flames

Fujia Wu, Wenkai Liang, Zheng Chen, Yiguang Ju, Chung K. Law
2015 Proceedings of the Combustion Institute  
The present findings show that the weakly stretched flame assumption fails for lean hydrogen mixtures, and give a good explanation to the discrepancies between experiments and model predictions for H 2  ...  speed and stretch rate that can be used to assess the uncertainty of extrapolation models.  ...  With Results on H 2 /air H 2 /air mixtures are most suitable for uncertainty quantification for the following reasons.  ... 
doi:10.1016/j.proci.2014.05.065 fatcat:gcyzqbqqbjffnp6rycx3sgomia

Computational Quantification of Peptides from LC-MS Data

Ole Schulz-Trieglaff, Rene Hussong, Clemens Gröpl, Andreas Leinenbach, Andreas Hildebrandt, Christian Huber, Knut Reinert
2008 Journal of Computational Biology  
By explicitly modeling the instrument inaccuracy, we are also able to cope with data sets of different quality and resolution.  ...  We present an algorithm for the detection and quantification of peptides in LC-MS data. Our approach is flexible and independent of the MS technology in use.  ...  ACKNOWLEDGMENTS We are indebted to Jens Joachim and Marcel Grunert who helped to implement an earlier version of the peptide quantification algorithm.  ... 
doi:10.1089/cmb.2007.0117 pmid:18707556 fatcat:vmu57z3b3vc7xgicgfdr6ezrxu

Multi-Dimensional Uniform Initialization Gaussian Mixture Model for Spar Crack Quantification under Uncertainty

Qiuhui Xu, Shenfang Yuan, Tianxiang Huang
2021 Sensors  
Considering these uncertainties, the Gaussian mixture model (GMM) is studied to model the probability distribution of GW features.  ...  Finally, the proposed method is applied for online crack quantification on the notched specimen of an aircraft spar with complex fan-shaped cracks under uncertainty.  ...  The implementation process of the MdUI-GMM based crack quantification process is summarized as well.  ... 
doi:10.3390/s21041283 pmid:33670240 pmcid:PMC7916970 fatcat:k654fkackrfojowgsg7lwaal7e

Selection of features with consistent profiles improves relative protein quantification in mass spectrometry experiments

Tsung-Heng Tsai, Meena Choi, Balazs Banfai, Yansheng Liu, Brendan MacLean, Tom Dunkley, Olga Vitek
2020 Molecular & Cellular Proteomics  
We evaluated the proposed approach on a series of benchmark controlled mixtures and biological investigations with DDA, DIA and SRM data acquisitions.  ...  In bottom-up mass spectrometry-based proteomics, relative protein quantification is often achieved with data-dependent acquisition (DDA), data-independent acquisition (DIA), or selected reaction monitoring  ...  Nesvizhskii (University of Michigan) for processing the controlled mixture datasets.  ... 
doi:10.1074/mcp.ra119.001792 pmid:32234965 pmcid:PMC7261813 fatcat:i2trln65p5djtmu5p6hia4ckke

On the choice of spatial and categorical scale in remote sensing land cover classification

Junchang Ju, Sucharita Gopal, Eric D. Kolaczyk
2005 Remote Sensing of Environment  
We then show how a statistical model selection strategy may be used with the finite mixture models to provide a data-adaptive choice of spatial scale, varying by location (i.e., multiscale), from which  ...  We show that the use of statistical finite mixture models with groups of original pixel-scale measurements, at successive spatial scales, offers improved pixel-wise classification accuracy as compared  ...  To summarize, the use of statistical finite mixture models with the original, pixel-scale spectral measurements improves classification accuracy at each of the successive spatial scales as compared to  ... 
doi:10.1016/j.rse.2005.01.016 fatcat:uo6xh647rjfwvcuaww2dqsclkm

Multi-Isotope Capabilities of a Small-Animal Multi-Pinhole SPECT System

Mathias Lukas, Anne Kluge, Nicola Beindorff, Winfried Brenner
2020 Journal of Nuclear Medicine  
Methods: Phantom measurements with single-, dual- and triple-isotope combinations of 99mTc, 111In, 123I, 177Lu, and 201Tl were performed with the NanoSPECT/CTPLUS to evaluate system energy resolution,  ...  count rate sensitivities and when the system calibration is performed with phantoms of appropriate size.  ...  Table 3 summarizes the absolute quantification errors for dualisotope combinations without object source scatter.  ... 
doi:10.2967/jnumed.119.226027 pmid:31896726 fatcat:ztz6ko3agjeq7n6x3uxd4g4vju

Quantifying Registration Uncertainty With Sparse Bayesian Modelling

Loic Le Folgoc, Herve Delingette, Antonio Criminisi, Nicholas Ayache
2017 IEEE Transactions on Medical Imaging  
We investigate uncertainty quantification under a sparse Bayesian model of medical image registration.  ...  In earlier work, approximate inference under the sparse Bayesian model was tackled in an efficient Variational Bayes (VB) framework.  ...  The middle factor penalizes the inclusion of basis k if it overlaps with bases in the active set S, in the sense of the metric induced by R. κ k is a measure of overlap of basis k with all bases in the  ... 
doi:10.1109/tmi.2016.2623608 pmid:27831863 fatcat:ovykhsxc3fcqnaz55ln6csyxly

Robust classification of multivariate time series by imprecise hidden Markov models

Alessandro Antonucci, Rocco De Rosa, Alessandro Giusti, Fabio Cuzzolin
2015 International Journal of Approximate Reasoning  
A novel technique to classify time series with imprecise hidden Markov models is presented. The learning of these models is achieved by coupling the EM algorithm with the imprecise Dirichlet model.  ...  The computation of the bounds of these descriptors with respect to the imprecise quantification of the parameters is reduced to, respectively, linear and quadratic optimization tasks, and hence efficiently  ...  Acknowledgements We thank Marco Zaffalon for suggesting us the idea of using expected counts in the imprecise Dirichlet model to learn credal sets from incomplete data.  ... 
doi:10.1016/j.ijar.2014.07.005 fatcat:uv23obie2bbstc2ts6c4bcuge4

Simultaneous determination of acesulfame-K, aspartame and stevioside in sweetener blends by ultraviolet spectroscopy with variable selection by sipls algorithm

Yang-Chun He, Sheng Fang, Xue-Jiao Xu
2012 Macedonian Journal of Chemistry and Chemical Engineering  
A chemometric-assisted UV absorption spectroscopic method is proposed for the simultaneous determination of acesulfame-K, aspartame and stevioside in raw powder mixtures of commercial sweeteners.  ...  The utilization of spectral region selection aims to construct better partial least squares (PLS) model than that established from the full-spectrum range.  ...  Therefore, the siPLS models using the spectrum subintervals 1, 2 3, and 4 were developed for the quantification of aspartame.  ... 
doi:10.20450/mjcce.2012.53 doaj:7d70d24d19104c068d151b3c595ae1c6 fatcat:nelygkfx7ndghkqhwq5vb3m5ei

Bayesian Cluster Analysis: Point Estimation and Credible Balls (with Discussion)

Sara Wade, Zoubin Ghahramani
2018 Bayesian Analysis  
In a Bayesian analysis, the posterior of a real-valued parameter of interest is often summarized by reporting a point estimate such as the posterior mean along with 95% credible intervals to characterize  ...  Clustering is widely studied in statistics and machine learning, with applications in a variety of fields.  ...  Model-based clustering methods utilize finite mixture models, where each mixture component corresponds to a cluster (Fraley and Raftery (2002) ).  ... 
doi:10.1214/17-ba1073 fatcat:le4ojpxmuzghbbre7jwqwtjgzm

A nonparametric Bayesian alternative to spike sorting

Frank Wood, Michael J. Black
2008 Journal of Neuroscience Methods  
In lieu of sorting neural data to produce a single best spike train, we estimate a probabilistic model of spike trains given the observed data.  ...  In this paper we address this issue using a novel probabilistic model that accounts for several important sources of uncertainty and error in spike sorting.  ...  The following section briefly summarizes the data used here. Section 3 introduces notation and reviews finite Gaussian mixture modeling.  ... 
doi:10.1016/j.jneumeth.2008.04.030 pmid:18602697 pmcid:PMC3880746 fatcat:j2r3oyt6pnfqlgwqcayr6bdvpe
« Previous Showing results 1 — 15 out of 5,723 results