Articles producció científica> Enginyeria Informàtica i Matemàtiques

Effect of Denoising in Band Selection for Regression Tasks in Hyperspectral Datasets

  • Identification data

    Identifier: imarina:9299005
    Authors:
    Latorre-Carmona, PedroMartinez Sotoca, JosePla, FilibertoBioucas-Dias, JoseJulia Ferre, Carme
    Abstract:
    This paper presents a comparative analysis of six band selection methods applied to hyperspectral datasets for biophysical variable estimation problems, where the effect of denoising on band selection performance has also been analyzed. In particular, we consider four hyperspectral datasets and three regressors of different nature (epsilon-SVR, Regression Trees, and Kernel Ridge Regression). Results show that the denoising approach improves the band selection quality of all the tested methods. We show that noise filtering is more beneficial for the selection methods that use an estimator based on the whole dataset for the prediction of the output than for methods that use strategies based on local information (neighboring points).
  • Others:

    Author, as appears in the article.: Latorre-Carmona, Pedro; Martinez Sotoca, Jose; Pla, Filiberto; Bioucas-Dias, Jose; Julia Ferre, Carme;
    Department: Enginyeria Informàtica i Matemàtiques
    URV's Author/s: Julià Ferré, Maria Carmen
    Keywords: Variable selection Regression Optimization Noise Models Land Imagery Hyperspectral datasets Feature selection Errors Classification
    Abstract: This paper presents a comparative analysis of six band selection methods applied to hyperspectral datasets for biophysical variable estimation problems, where the effect of denoising on band selection performance has also been analyzed. In particular, we consider four hyperspectral datasets and three regressors of different nature (epsilon-SVR, Regression Trees, and Kernel Ridge Regression). Results show that the denoising approach improves the band selection quality of all the tested methods. We show that noise filtering is more beneficial for the selection methods that use an estimator based on the whole dataset for the prediction of the output than for methods that use strategies based on local information (neighboring points).
    Thematic Areas: Saúde coletiva Remote sensing Planejamento urbano e regional / demografia Odontología Matemática / probabilidade e estatística Interdisciplinar Imaging science & photographic technology Geography, physical Geografía Geociências Engineering, electrical & electronic Engenharias iv Engenharias iii Engenharias i Computers in earth sciences Ciências ambientais Ciências agrárias i Ciência da computação Biodiversidade Atmospheric science
    licence for use: https://creativecommons.org/licenses/by/3.0/es/
    Author's mail: carme.julia@urv.cat
    Author identifier: 0000-0003-3440-6175
    Record's date: 2023-05-20
    Papper version: info:eu-repo/semantics/acceptedVersion
    Link to the original source: https://ieeexplore.ieee.org/document/6461428
    Papper original source: Ieee Journal Of Selected Topics In Applied Earth Observations And Remote Sensing. 6 (2): 473-481
    APA: Latorre-Carmona, Pedro; Martinez Sotoca, Jose; Pla, Filiberto; Bioucas-Dias, Jose; Julia Ferre, Carme; (2013). Effect of Denoising in Band Selection for Regression Tasks in Hyperspectral Datasets. Ieee Journal Of Selected Topics In Applied Earth Observations And Remote Sensing, 6(2), 473-481. DOI: 10.1109/JSTARS.2013.2241022
    Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
    Article's DOI: 10.1109/JSTARS.2013.2241022
    Entity: Universitat Rovira i Virgili
    Journal publication year: 2013
    Publication Type: Journal Publications
  • Keywords:

    Atmospheric Science,Computers in Earth Sciences,Engineering, Electrical & Electronic,Geography, Physical,Imaging Science & Photographic Technology,Remote Sensing
    Variable selection
    Regression
    Optimization
    Noise
    Models
    Land
    Imagery
    Hyperspectral datasets
    Feature selection
    Errors
    Classification
    Saúde coletiva
    Remote sensing
    Planejamento urbano e regional / demografia
    Odontología
    Matemática / probabilidade e estatística
    Interdisciplinar
    Imaging science & photographic technology
    Geography, physical
    Geografía
    Geociências
    Engineering, electrical & electronic
    Engenharias iv
    Engenharias iii
    Engenharias i
    Computers in earth sciences
    Ciências ambientais
    Ciências agrárias i
    Ciência da computação
    Biodiversidade
    Atmospheric science
  • Documents:

  • Cerca a google

    Search to google scholar