Filters








20,996 Hits in 5.4 sec

Semi-supervised Feature Extraction Using Independent Factor Analysis

L. Oukhellou, E. Come, P. Aknin, T. Denoeux
2011 2011 10th International Conference on Machine Learning and Applications and Workshops  
In this paper we investigate the possibility of estimating independent factor analysis model (IFA) and thus projecting original data onto a lower dimensional space, when prior knowledge on the cluster  ...  Experimental results on real data sets are provided to demonstrate the ability of our approach to find law dimensional manifold with good explanatory power.  ...  Introduction A considerable amount of research has been devoted to dimensionality reduction of multivariate data sets.  ... 
doi:10.1109/icmla.2011.183 dblp:conf/icmla/OukhellouCAD11 fatcat:s2zdqpykijgdldeyf7rlejhv4m

High-dimensional data clustering

C. Bouveyron, S. Girard, C. Schmid
2007 Computational Statistics & Data Analysis  
This paper presents a family of Gaussian mixture models designed for high-dimensional data which combine the ideas of dimension reduction and parsimonious modeling.  ...  In order to correctly fit the data, HDDC estimates the specific subspace and the intrinsic dimension of each group.  ...  Acknowledgments This work was supported by the French department of research through the ACI Masse de données (Movistar project).  ... 
doi:10.1016/j.csda.2007.02.009 fatcat:q7fix4bghrcwtjuryhwnby6kzm

Semi-supervised anomaly detection – towards model-independent searches of new physics

Mikael Kuusela, Tommi Vatanen, Eric Malmi, Tapani Raiko, Timo Aaltonen, Yoshikazu Nagai
2012 Journal of Physics, Conference Series  
Most classification algorithms used in high energy physics fall under the category of supervised machine learning.  ...  We first model the background using a multivariate Gaussian mixture model.  ...  (ii) Proportion of anomalies: The mixing proportion of the anomaly model λ directly gives us an estimate for the proportion of anomalies in the observations.  ... 
doi:10.1088/1742-6596/368/1/012032 fatcat:ywjccojnlreq7azovtypbt6uma

Semi-supervised detection of collective anomalies with an application in high energy particle physics

Tommi Vatanen, Mikael Kuusela, Eric Malmi, Tapani Raiko, Timo Aaltonen, Yoshikazu Nagai
2012 The 2012 International Joint Conference on Neural Networks (IJCNN)  
Such mixture model allows us to perform classification of anomalies vs. background, estimate the proportion of anomalies in the sample and study the statistical significance of the anomalous contribution  ...  We study a novel type of a semi-supervised anomaly detection problem where the anomalies occur collectively among a background of normal data.  ...  ACKNOWLEDGEMENTS The authors are grateful to the CDF collaboration for providing access to the Higgs signal and background Monte Carlo samples, to the Academy of Finland for financial support and to Matti  ... 
doi:10.1109/ijcnn.2012.6252712 dblp:conf/ijcnn/VatanenKMRAN12 fatcat:ocbaazpaanfq7gqr4z7b66lgrq

Object Localization by Subspace Clustering of Local Descriptors [chapter]

C. Bouveyron, J. Kannala, C. Schmid, S. Girard
2006 Lecture Notes in Computer Science  
We therefore use a subspace clustering method called High-Dimensional Data Clustering (HDDC) which overcomes the curse of dimensionality.  ...  Furthermore, in many cases only a few of the clusters are useful to discriminate the object.  ...  GMM), spherical Gaussian mixture model (Spherical GMM), and data reduction with PCA combined with a diagonal Gaussian mixture model (PCA + diag.  ... 
doi:10.1007/11949619_41 fatcat:r2epwlffbbbd5dcqvyxxrmqq7i

Probabilistic model-based discriminant analysis and clustering methods in chemometrics

Charles Bouveyron
2013 Journal of Chemometrics  
In Chemometrics, the supervised and unsupervised classification of high-dimensional data has become a recurrent problem.  ...  The recent developments in model-based classification overcame these drawbacks and enabling the efficient classification of high-dimensional data, even in the "small n / large p" condition.  ...  For this reason, dimension reduction methods are frequently used to reduce the dimension of the data before the clustering step.  ... 
doi:10.1002/cem.2563 fatcat:bcowqw3z2zbtdd3r75gacgeuku

Probabilistic model-based discriminant analysis and clustering methods in chemometrics

Charles Bouveyron
2013 Journal of Chemometrics  
In Chemometrics, the supervised and unsupervised classification of high-dimensional data has become a recurrent problem.  ...  The recent developments in model-based classification overcame these drawbacks and enabling the efficient classification of high-dimensional data, even in the "small n / large p" condition.  ...  For this reason, dimension reduction methods are frequently used to reduce the dimension of the data before the clustering step.  ... 
doi:10.1002/cem.2560 fatcat:yyxavwgv6vhrjgse3yje2nqti4

A Mixture of Matrix Variate Bilinear Factor Analyzers [article]

Michael P.B. Gallaugher, Paul D. McNicholas
2018 arXiv   pre-print
Herein, we develop a mixture of matrix variate bilinear factor analyzers (MMVBFA) model for use in clustering high-dimensional matrix variate data.  ...  Parameter estimation is discussed, and the MMVBFA model is illustrated using simulated and real data.  ...  In this paper, we present a mixture of matrix variate bilinear factor analyzers (MMVBFA) model for use in clustering higher dimensional matrix variate data.  ... 
arXiv:1712.08664v3 fatcat:whls7s4f7rcjnkm6vkkmrhswjq

Robust supervised classification with mixture models: Learning from data with uncertain labels

Charles Bouveyron, Stéphane Girard
2009 Pattern Recognition  
In the supervised classification framework, human supervision is required for labeling a set of learning data which are then used for building the classifier.  ...  The idea of the proposed method is to confront an unsupervised modelling of the data with the supervised information carried by the labels of the learning data in order to detect inconsistencies.  ...  If the chosen mixture model involves Gaussian models for high-dimensional data, this step consists in estimating the following model parameters: the proportions π j , the means µ j , the subspace variances  ... 
doi:10.1016/j.patcog.2009.03.027 fatcat:bvlyldsru5gfjmcofgkboijpyy

Object recognition using proportion-based prior information: Application to fisheries acoustics

R. Lefort, R. Fablet, J.-M. Boucher
2011 Pattern Recognition Letters  
This paper addresses the inference of probabilistic classification models using weakly supervised learning.  ...  Research highlights ► Weakly supervised learning deals with prior annotation of objects in images. ► Classification model must be assessed by using probabilities. ► Reported results promote discriminative  ...  The rate of correct classification is reported as a function of the proportion complexity of the training dataset, from supervised learning to 7-class mixtures.  ... 
doi:10.1016/j.patrec.2010.10.001 fatcat:cicrhinhkzfqvlpvvb6bcs2x3u

Gaussian Mixture Models Based on Principal Components and Applications

Nada A. Alqahtani, Zakiah I. Kalantan
2020 Mathematical Problems in Engineering  
In this work, we deal with the reduced data using a bivariate mixture model and learning with a bivariate Gaussian mixture model.  ...  In general, high-dimensional data are reduced by obtaining a set of principal components so as to highlight similarities and differences.  ...  Acknowledgments e authors would like to mention their special thanks to Dr Jochen Einbeck of the University of Durham for constructive comments that greatly improved the paper. is work was funded by the  ... 
doi:10.1155/2020/1202307 fatcat:xvjmcf6wrrcfte2w3joyoutzvq

Clustering documents with labeled and unlabeled documents using fuzzy semi-Kmeans

Chien-Liang Liu, Tao-Hsing Chang, Hsuan-Hsun Li
2013 Fuzzy sets and systems (Print)  
The fuzzy semi-Kmeans is an extension of K-means clustering model, and it is inspired by an EM algorithm and a Gaussian mixture model.  ...  While focusing on document clustering, this work presents a fuzzy semi-supervised clustering algorithm called fuzzy semi-Kmeans.  ...  Percentage of Semi-supervised classification Semi-supervised clustering labeled examples Dimensionality reduction Without dimensionality reduction Dimensionality reduction Without dimensionality reduction  ... 
doi:10.1016/j.fss.2013.01.004 fatcat:5qgbucjr4fcxvhffxdgdqbi4gq

Model-based Clustering of High-Dimensional Data in Astrophysics

C. Bouveyron, D. Fraix-Burnet, S. Girard
2016 EAS Publications Series  
the numbers of parameters to estimate for the proportions, the means and the covariance matrices.  ...  Mixture of high-dimensional Gaussian mixture models First, Bouveyron et al. [16, 17] proposed a family of 28 parsimonious and flexible Gaussian models to deal with high-dimensional data.  ... 
doi:10.1051/eas/1677006 fatcat:zshwqmij3rgc5aerbyz45m7n7y

Pregnancy Labor Prediction Using Magnetomyography Sensing and a Self-Sorting Cybernetic Model

Ejay Nsugbe, Oluwarotimi Williams Samuel, Ibrahim Sanusi, Suresh Vishwakarma, Dawn Adams
2021 Engineering Proceedings  
The means of labor prediction methods from such signals appear to rely on a supervised learning post-processing framework whose calibration relies on an effective labelling of the training sample set.  ...  As a potential solution to this, using a reduced electrode channel from magnetomyography instrumentation, we propose a multi-stage self-sorting cybernetic model that is comprised of an ensemble of various  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/ecsa-8-11312 fatcat:m3sm6l4lhjeuzejrnr6kusfaua

Gaussian mixture models for the classification of high-dimensional vibrational spectroscopy data

Julien Jacques, Charles Bouveyron, Stéphane Girard, Olivier Devos, Ludovic Duponchel, Cyril Ruckebusch
2010 Journal of Chemometrics  
Section 2 introduces the Gaussian models for highdimensional data, estimation of their parameter and their use in supervised classification. The data sets and experiments are detailed in Section 3.  ...  In this work, a family of generative Gaussian models designed for the supervised classification of high-dimensional data is presented as well as the associated classification method called High Dimensional  ...  Fernandez Pierna from the Wallon Agricultural Research Centre (CRA-W) for providing the data of the 4-class MIR data set. We also thank the referees for comments which greatly improved this paper.  ... 
doi:10.1002/cem.1355 fatcat:ugfmt7qcgfhcdgwbntvpgh6gta
« Previous Showing results 1 — 15 out of 20,996 results