View in EDS

Crop classification by support vector machine with intelligently selected training data for an operational application.

Saved in:
Bibliographic Details
Title: Crop classification by support vector machine with intelligently selected training data for an operational application.
Authors: Mathur, Ajay1 (AUTHOR), Foody, GilesM.2 (AUTHOR) Giles.Foody@Nottingham.ac.uk
Source: International Journal of Remote Sensing. Apr2008, Vol. 29 Issue 8, p2227-2240. 14p. 2 Color Photographs, 1 Diagram, 3 Charts, 1 Graph.
Subjects: Classification, Crops, Machinery, Training, Maps, Remote sensing, Land use
Geographic Terms: Punjab (India), India
Abstract: The accuracy of a supervised classification is dependent to a large extent on the training data used. The aim in training is often to capture a large training set to fully describe the classes spectrally, commonly with the requirements of a conventional statistical classifier in mind. However, it is not always necessary to provide a complete description of the classes, especially if using a support vector machine (SVM) as the classifier. An SVM seeks to fit an optimal hyperplane between the classes and uses only some of the training samples that lie at the edge of the class distributions in feature space (support vectors). This should allow the definition of the most informative training samples prior to the analysis. An approach to identify informative training samples was demonstrated for the classification of agricultural classes in south-western part of Punjab state, India. A small, intelligently selected, training dataset was acquired in the field with the aid of ancillary information. This dataset contained the data from training sites that were predicted before the classification to be amongst the most informative for an SVM classification. The intelligent training collection scheme yielded a classification of comparable accuracy, ∼91%, to one derived using a larger training set acquired by a conventional approach. Moreover, from inspection of the training sets it was apparent that the intelligently defined training set contained a greater proportion of support vectors (0.70), useful training sites, than that acquired by the conventional approach (0.41). By focusing on the most informative training samples, the intelligent scheme required less investment in training than the conventional approach and its adoption would have reduced the total financial outlay in classification production and evaluation by ∼26%. Additionally, the analysis highlighted the possibility to further reduce the training set size without any significant negative impact on classification accuracy. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Remote Sensing is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 31417086
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Crop classification by support vector machine with intelligently selected training data for an operational application.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Mathur%2C+Ajay%22">Mathur, Ajay</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Foody%2C+GilesM%2E%22">Foody, GilesM.</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> Giles.Foody@Nottingham.ac.uk</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Remote+Sensing%22">International Journal of Remote Sensing</searchLink>. Apr2008, Vol. 29 Issue 8, p2227-2240. 14p. 2 Color Photographs, 1 Diagram, 3 Charts, 1 Graph.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Classification%22">Classification</searchLink><br /><searchLink fieldCode="DE" term="%22Crops%22">Crops</searchLink><br /><searchLink fieldCode="DE" term="%22Machinery%22">Machinery</searchLink><br /><searchLink fieldCode="DE" term="%22Training%22">Training</searchLink><br /><searchLink fieldCode="DE" term="%22Maps%22">Maps</searchLink><br /><searchLink fieldCode="DE" term="%22Remote+sensing%22">Remote sensing</searchLink><br /><searchLink fieldCode="DE" term="%22Land+use%22">Land use</searchLink>
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Punjab+%28India%29%22">Punjab (India)</searchLink><br /><searchLink fieldCode="DE" term="%22India%22">India</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The accuracy of a supervised classification is dependent to a large extent on the training data used. The aim in training is often to capture a large training set to fully describe the classes spectrally, commonly with the requirements of a conventional statistical classifier in mind. However, it is not always necessary to provide a complete description of the classes, especially if using a support vector machine (SVM) as the classifier. An SVM seeks to fit an optimal hyperplane between the classes and uses only some of the training samples that lie at the edge of the class distributions in feature space (support vectors). This should allow the definition of the most informative training samples prior to the analysis. An approach to identify informative training samples was demonstrated for the classification of agricultural classes in south-western part of Punjab state, India. A small, intelligently selected, training dataset was acquired in the field with the aid of ancillary information. This dataset contained the data from training sites that were predicted before the classification to be amongst the most informative for an SVM classification. The intelligent training collection scheme yielded a classification of comparable accuracy, ∼91%, to one derived using a larger training set acquired by a conventional approach. Moreover, from inspection of the training sets it was apparent that the intelligently defined training set contained a greater proportion of support vectors (0.70), useful training sites, than that acquired by the conventional approach (0.41). By focusing on the most informative training samples, the intelligent scheme required less investment in training than the conventional approach and its adoption would have reduced the total financial outlay in classification production and evaluation by ∼26%. Additionally, the analysis highlighted the possibility to further reduce the training set size without any significant negative impact on classification accuracy. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of International Journal of Remote Sensing is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=31417086
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/01431160701395203
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 14
        StartPage: 2227
    Subjects:
      – SubjectFull: Classification
        Type: general
      – SubjectFull: Crops
        Type: general
      – SubjectFull: Machinery
        Type: general
      – SubjectFull: Training
        Type: general
      – SubjectFull: Maps
        Type: general
      – SubjectFull: Remote sensing
        Type: general
      – SubjectFull: Land use
        Type: general
      – SubjectFull: Punjab (India)
        Type: general
      – SubjectFull: India
        Type: general
    Titles:
      – TitleFull: Crop classification by support vector machine with intelligently selected training data for an operational application.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Mathur, Ajay
      – PersonEntity:
          Name:
            NameFull: Foody, GilesM.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 20
              M: 04
              Text: Apr2008
              Type: published
              Y: 2008
          Identifiers:
            – Type: issn-print
              Value: 01431161
          Numbering:
            – Type: volume
              Value: 29
            – Type: issue
              Value: 8
          Titles:
            – TitleFull: International Journal of Remote Sensing
              Type: main
ResultId 1