1,308 research outputs found
Introduction to Machine Learning - Data Classification
No full textThe document main.pdf contains an introductory course on machine learning for classification given by Florent Chatelain and Mathieu Fauvel. Several ipython notebooks are also provided.
The last version is available at
https://framagit.org/mfauvel/omp_machine_learnin
Analysis of Mathieu Equation Stable Solutions in the First Zone of Stability
No full textAbstractThe paper presents the results of a homogeneous Mathieu equation studies. Mathieu equation solutions are oscillations, modulated in amplitude and frequency. In the computational experiments we found dependences of the given oscillations on the ratio of the coefficients. These dependences are shown in graphs that can be used for an approximate estimation of the Mathieu equation solutions without integration
Data Set: Hyperspectral image unmixing with LiDAR data-aided spatial regularization
No full text<p>Data set and matlab codes used for the experimental section of "Hyperspectral Image Unmixing With LiDAR Data-Aided Spatial Regularization"</p>
<p>T. Uezato, M. Fauvel and N. Dobigeon, "Hyperspectral Image Unmixing With LiDAR Data-Aided Spatial Regularization," in <em>IEEE Transactions on Geoscience and Remote Sensing</em>, vol. 56, no. 7, pp. 4098-4108, July 2018.<br>
doi: 10.1109/TGRS.2018.2823419<br>
URL: <a href="http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8347066&isnumber=8393475">http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8347066&isnumber=8393475</a><br>
</p>
Classification d’images hyperspectrales pour la caractérisation du milieu urbain par une approche multirésolution
No full textProjecte final de carrera fet en col.laboració amb Ecole Nationale Supérieure d'Electronique et de
Radioélectricité de Grenoble i Télécom - ENSIMAGThe classification of optical urban remote‐sensing images is addressed. Support Vector
Machines (SVM) are proposed to classify hyperspectral images. An introduction to SVM is
given in this report in order to help understand how they classify data according to the spectral
information. Some kernel functions which are used to improve classification accuracy are
presented as well. Then the use of spatial information through multiresolution decomposition
is detailed.
The objective of this report is to propose a methodology including the spatial information in
the classification process and trying to evaluate and improve the accuracy of this classification.
Spatial information is extracted from a wavelet analysis of the image.
Finally experimental results are presented for each classification method: spectral, spatial and
combining both spatial and spectral, and kernel parameters are selected in order to optimize
the classification. After including the spatial information, classification accuracy has been
improved
Classification d’images hyperspectrales pour la caractérisation du milieu urbain par une approche multirésolution
No full textProjecte final de carrera fet en col.laboració amb Ecole Nationale Supérieure d'Electronique et de
Radioélectricité de Grenoble i Télécom - ENSIMAGThe classification of optical urban remote‐sensing images is addressed. Support Vector
Machines (SVM) are proposed to classify hyperspectral images. An introduction to SVM is
given in this report in order to help understand how they classify data according to the spectral
information. Some kernel functions which are used to improve classification accuracy are
presented as well. Then the use of spatial information through multiresolution decomposition
is detailed.
The objective of this report is to propose a methodology including the spatial information in
the classification process and trying to evaluate and improve the accuracy of this classification.
Spatial information is extracted from a wavelet analysis of the image.
Finally experimental results are presented for each classification method: spectral, spatial and
combining both spatial and spectral, and kernel parameters are selected in order to optimize
the classification. After including the spatial information, classification accuracy has been
improved
Approximation de matrices pour l’apprentissage des hyperparamètres des fonctions noyaux Gaussiennes
No full textLe problème considéré dans cet article concerne l’optimisation des hyperparamètres d’une fonction noyau Gaussienne à l’aide de mesures de similitude entre matrices. Deux contributions sont proposées : 1) une nouvelle mesure de similarité entre fonctions noyaux et 2) une nouvelle paramétrisation pour les noyaux Gaussiens. Des améliorations des temps de calculs et des taux de bonnes classifications par rapport à la validation croisée pour un classifier k-nn sont obtenues sur des jeux de données standards.The problem considered in this paper concerns the optimization of the hyperparameters of a Gaussian kernel function using a similarity measure between matrices. Two contributions are proposed: 1) a new measure of similarity between kernel functions and 2) a new parameterization for the Gaussian kernel. Improvements in terms of computation time and classification accuracies by comparison to cross-validation are obtained on standard data set for a k-nn classifier
Classification d’images hyperspectrales pour la caractérisation du milieu urbain par une approche multirésolution
No full textProjecte final de carrera fet en col.laboració amb Ecole Nationale Supérieure d'Electronique et de
Radioélectricité de Grenoble i Télécom - ENSIMAGThe classification of optical urban remote‐sensing images is addressed. Support Vector
Machines (SVM) are proposed to classify hyperspectral images. An introduction to SVM is
given in this report in order to help understand how they classify data according to the spectral
information. Some kernel functions which are used to improve classification accuracy are
presented as well. Then the use of spatial information through multiresolution decomposition
is detailed.
The objective of this report is to propose a methodology including the spatial information in
the classification process and trying to evaluate and improve the accuracy of this classification.
Spatial information is extracted from a wavelet analysis of the image.
Finally experimental results are presented for each classification method: spectral, spatial and
combining both spatial and spectral, and kernel parameters are selected in order to optimize
the classification. After including the spatial information, classification accuracy has been
improved
Pensar las escalas para pensar las luchas: Autor: Mathieu UHEL
No full textA través de un título sugerente, “pensar las escalas para pensar las luchas”, Mathieu Uhel entreteje la construcción teórico-crítica del concepto escala, generada por la geografía radical anglosajona de finales del siglo XX, con la necesidad/utilidad práctica de la escala para concienciar las luchas sociales. El artículo cumple un doble propósito: por un lado, delinear los elementos de lectura sobre el concepto escala; y, con ello, promover la atención de esta problemática en las luchas contemporáneas. En un primer apartado, Uhel ubica las discusiones académicas en torno a la escala, como herramienta metodológica útil para comprender la complejidad de las sociedades capitalistas; en el segundo apartado, el autor avanza la exposición en torno al contexto de la dimensión escalar del imperialismo capitalista; finalmente, el autor se centra en el rol de la actividad política a escala nacional en la tensa relación entre las imposiciones del capital y la lucha social.Por meio de um título sugestivo, “pensando escalas para pensar lutas”, Mathieu Uhel entrelaça a construção teórico-crítica do conceito de escala, gerado pela geografia radical anglo-saxônica do final do século XX, com a necessidade / utilidade prática escala para aumentar a consciência das lutas sociais. O artigo tem um duplo propósito: por um lado, delinear os elementos de leitura sobre o conceito de escala; e, com isso, promover atenção a esse problema nas lutas contemporâneas. Na primeira seção, Uhel localiza as discussões acadêmicas em torno da escala, como uma ferramenta metodológica útil para compreender a complexidade das sociedades capitalistas; na segunda seção, o autor avança a exposição em torno do contexto da dimensão escalar do imperialismo capitalista; por fim, o autor enfoca o papel da atividade política em escala nacional na tensa relação entre as imposições do capital e a luta social.Mathieu Uhel\u27s suggestive title, “Thinking about scales to think about struggles”, he interweaves the theoretical-critical construction of concept scale, generated by radical Anglo-Saxon geography in the late 20th century, with it´s practical utility to social struggles. The article serves two purposes: on the one hand, Uhel locates academic discussion around scale; and, with this, he promotes attention to this problem in contemporary struggles. In the first section, Uhel locates academic discussions around scale, as a useful methodological tool to understand the complexity of capitalist societies; in the second section, the author advances the argument around the context of the scalar dimension of capitalist imperialism; finally, the author focuses on the role of political activity on a national scale in the tense relationship between the impositions of capital and the social movement
- …
