Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Mariam Kalakech"'
Publikováno v:
Journal of Imaging, Vol 4, Iss 10, p 112 (2018)
These last few years, several supervised scores have been proposed in the literature to select histograms. Applied to color texture classification problems, these scores have improved the accuracy by selecting the most discriminant histograms among a
Externí odkaz:
https://doaj.org/article/43b169708481485ba319ef355415645b
Publikováno v:
Advances in Data Analysis and Classification
Advances in Data Analysis and Classification, Springer Verlag, 2020, ⟨10.1007/s11634-020-00408-5⟩
Advances in Data Analysis and Classification, Springer Verlag, 2020, ⟨10.1007/s11634-020-00408-5⟩
Pairwise constraints, a cheaper kind of supervision information that does not need to reveal the class labels of data points, were initially suggested to enhance the performance of clustering algorithms. Recently, researchers were interested in using
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7433147d41b1748f7b3b4c45b841bf11
https://doi.org/10.1007/s11634-020-00408-5
https://doi.org/10.1007/s11634-020-00408-5
Publikováno v:
ACIT
Fighting poverty is one of the main objectives of sustainable development program. In a country like Lebanon, where poverty is a real threat and hidden under a good living looking, the situation should be explored in depth. This paper aims to evaluat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4b520b691707405d385c1b7420e370d1
https://doi.org/10.1109/acit.2018.8672723
https://doi.org/10.1109/acit.2018.8672723
Publikováno v:
MENACOMM
In this paper, we propose a semi-supervised margin-based feature selection algorithm called Relief-Sc. It is a modification of the well-known Relief algorithm from its optimization perspective. It utilizes cannot-link constraints only to solve a simp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c5ae5869b90d68910070548b99b1ae1d
https://doi.org/10.1109/menacomm.2018.8371002
https://doi.org/10.1109/menacomm.2018.8371002
Publikováno v:
2018 Sixth International Conference on Digital Information, Networking, and Wireless Communications (DINWC).
Fisher and Relief are two well-known and largely used scores for supervised feature selection. In this paper, we propose using these scores in order to select the relevant human development indicators that most contribute in the development classes a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::86a18569b8b280b17a2bd7b5cfcb81f8
https://doi.org/10.1109/dinwc.2018.8357003
https://doi.org/10.1109/dinwc.2018.8357003
Publikováno v:
Neural Processing Letters
Neural Processing Letters, Springer Verlag, 2013, pp.1-24. ⟨10.1007/s11063-013-9280-2⟩
Neural Processing Letters, Springer Verlag, 2013, pp.1-24. ⟨10.1007/s11063-013-9280-2⟩
International audience; Semi-supervised context characterized by the presence of a few pairs of constraints between learning samples is abundant in many real applications. Analysing these instance constraints by recent spectral scores has shown good
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5b8e4d99e1dcd7ad5cf67550284e1f27
https://doi.org/10.1007/s11063-013-9280-2
https://doi.org/10.1007/s11063-013-9280-2
Publikováno v:
ICDEc
Middle East countries, characterized by many income and non-income development indicators, can be classified into different groups that reflect the diversity in human development across those countries. However, few of these available indicators are
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c36d18eb79d816a3f23491dc657f464b
https://doi.org/10.1109/icdec.2016.7563141
https://doi.org/10.1109/icdec.2016.7563141
Publikováno v:
2016 Sixth International Conference on Digital Information Processing and Communications (ICDIPC).
Laplacian score used to select the most relevant income (input) indicators for Middle East countries, has shown good classification performances of those countries, while reducing their input indicator space. In this paper, we propose a new way to ca
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1c63cd16322572871289eff85102fafb
https://doi.org/10.1109/icdipc.2016.7470792
https://doi.org/10.1109/icdipc.2016.7470792
Publikováno v:
2015 International Conference on Image Processing Theory, Tools and Applications (IPTA)
2015 International Conference on Image Processing Theory, Tools and Applications (IPTA), Nov 2015, Orleans, France. pp.242-247, ⟨10.1109/IPTA.2015.7367138⟩
IPTA
2015 International Conference on Image Processing Theory, Tools and Applications (IPTA), Nov 2015, Orleans, France. pp.242-247, ⟨10.1109/IPTA.2015.7367138⟩
IPTA
This paper presents and compares a new adapted version of the Laplacian score used to select LBP histogram for color texture classification. During a supervised learning stage, we first compute a similarity matrix between images using the true class
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::981ead6586bbc39513a3a3fdfbecbe92
https://hal.archives-ouvertes.fr/hal-03031129
https://hal.archives-ouvertes.fr/hal-03031129
Publikováno v:
Pattern Recognition Letters
Pattern Recognition Letters, Elsevier, 2011, 32 (5), pp.656-665. ⟨10.1016/j.patrec.2010.12.014⟩
Pattern Recognition Letters, Elsevier, 2011, 32 (5), pp.656-665. ⟨10.1016/j.patrec.2010.12.014⟩
International audience; Recent feature selection scores using pairwise constraints (must-link and cannot-link) have shown better performances than the unsupervised methods and comparable to the supervised ones. However, these scores use only the pair
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8b4d9e0b5dcd3847f0fd8c6444654024
https://hal.archives-ouvertes.fr/hal-00732484/file/articlesoumis_en_deuxieme_version.pdf
https://hal.archives-ouvertes.fr/hal-00732484/file/articlesoumis_en_deuxieme_version.pdf