A hybrid method for increasing the speed of SVM training using belief function theory and boundary region View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-03-15

AUTHORS

Somaye Moslemnejad, Javad Hamidzadeh

ABSTRACT

The training of the support vector machine (SVM) classifier has high computational complexity and is not suitable for large data classification. Since the classification hyperplane is determined by the support vectors and the other instances do not have an effect on the classifier, a method is introduced that does not use all instances for training. Data set may include inappropriate instances such as noisy and outlier instances. In this paper, a novel method is introduced in which at the first step using the belief function theory, the instances uncertainty such as noisy and outlier instances are identified and discarded, at the second step using the geometric method, called, boundary region, the boundary instances are determined. Finally, at the last step, by using the obtained boundary instances, the training of the SVM classifier is done. In the proposed method BF–BR (Belief Function–Boundary Region), the computational cost of the classification training is reduced without losing classification accuracy. The performance has been evaluated on real world data sets from UCI repository by the tenfold cross validation method. The results of the experiments have been compared with the other methods, which indicate superiority of the proposed method in terms of the number of training instances and training time while good classification accuracy for SVM training is achieved. More... »

PAGES

1-18

References to SciGraph publications

  • 2016-02. Large symmetric margin instance selection algorithm in INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
  • 2017-08. Hierarchically penalized support vector machine with grouped variables in INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
  • 1995. The Nature of Statistical Learning Theory in NONE
  • 1995-09. Support-vector networks in MACHINE LEARNING
  • 2019-03. Feature extraction by PCA and diagnosis of breast tumors using SVM with DE-based parameter tuning in INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
  • 2008. Computational Geometry, Algorithms and Applications in NONE
  • 2016-06. Fusing sequential minimal optimization and Newton’s method for support vector training in INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s13042-019-00944-3

    DOI

    http://dx.doi.org/10.1007/s13042-019-00944-3

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1112779028


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "name": [
                "Department of Computer Engineering, Salman Institute of Higher Education, Mashhad, Iran"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Moslemnejad", 
            "givenName": "Somaye", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Sadjad University of Technology", 
              "id": "https://www.grid.ac/institutes/grid.444813.e", 
              "name": [
                "Faculty of Computer Engineering and Information Technology, Sadjad University of Technology, Mashhad, Iran"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Hamidzadeh", 
            "givenName": "Javad", 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1016/j.knosys.2013.08.005", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1006934373"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1162/089976602753633402", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1008605532"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.ijleo.2015.06.010", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1011468980"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s13042-014-0265-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1012905067", 
              "https://doi.org/10.1007/s13042-014-0265-x"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1961189.1961199", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1013637525"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s13042-016-0494-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1017204591", 
              "https://doi.org/10.1007/s13042-016-0494-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s13042-016-0494-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1017204591", 
              "https://doi.org/10.1007/s13042-016-0494-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.patcog.2012.09.003", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1017777088"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neucom.2014.07.038", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1019937018"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neunet.2011.10.006", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1021018868"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neucom.2015.12.046", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1022484674"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.asoc.2015.03.033", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1022830071"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.knosys.2016.07.029", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024723303"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00994018", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1025150743", 
              "https://doi.org/10.1007/bf00994018"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-1-4757-2440-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1027312764", 
              "https://doi.org/10.1007/978-1-4757-2440-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-1-4757-2440-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1027312764", 
              "https://doi.org/10.1007/978-1-4757-2440-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neucom.2015.11.081", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1027980512"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.asoc.2016.06.014", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1029241520"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.knosys.2015.08.007", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1029920728"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neucom.2013.05.040", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1030252933"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.patcog.2016.07.004", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1030830976"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neucom.2013.01.058", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1035330761"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.patcog.2014.11.005", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1038571142"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.ijar.2015.05.002", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1038737160"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.knosys.2014.11.013", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040326146"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.ymssp.2016.04.001", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040475132"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neucom.2014.03.037", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040916121"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0020-0190(73)90020-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1041132033"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.patcog.2016.04.008", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1041528745"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neucom.2014.04.078", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1042786159"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1080/03081078308960825", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1044845053"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neunet.2015.03.013", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1045354958"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://app.dimensions.ai/details/publication/pub.1045724697", 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-77974-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1045724697", 
              "https://doi.org/10.1007/978-3-540-77974-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-77974-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1045724697", 
              "https://doi.org/10.1007/978-3-540-77974-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0004-3702(94)90026-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1049557093"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0004-3702(94)90026-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1049557093"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s13042-014-0239-z", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1049760626", 
              "https://doi.org/10.1007/s13042-014-0239-z"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.proeng.2011.08.366", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1050090745"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.knosys.2016.10.031", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1052402903"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neucom.2014.08.033", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1053183317"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/21.376493", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061122112"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/72.788640", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061219233"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tii.2016.2643689", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061633044"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tnn.2006.873281", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061717015"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tnn.2006.878123", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061717067"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tnn.2009.2020908", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061717555"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tnnls.2012.2187307", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061718070"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tsmc.2015.2421883", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061794346"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tsmca.2005.853483", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061795115"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.epsr.2017.03.030", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1084931678"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.physa.2017.04.113", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1085181105"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/access.2017.2697408", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1085284787"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.asoc.2017.05.021", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1085431177"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.patcog.2017.06.003", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1085857833"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neunet.2017.06.008", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1090448589"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.asoc.2017.07.038", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1090857977"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpds.2017.2731764", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1090973146"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.ins.2017.08.033", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1091147411"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.tcs.2017.08.014", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1091328218"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.patcog.2017.09.035", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1091914310"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s13042-017-0741-1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1092619156", 
              "https://doi.org/10.1007/s13042-017-0741-1"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s13042-017-0741-1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1092619156", 
              "https://doi.org/10.1007/s13042-017-0741-1"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s13042-017-0741-1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1092619156", 
              "https://doi.org/10.1007/s13042-017-0741-1"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tsmc.2017.2759090", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093129769"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.patcog.2018.05.023", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1104264473"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2019-03-15", 
        "datePublishedReg": "2019-03-15", 
        "description": "The training of the support vector machine (SVM) classifier has high computational complexity and is not suitable for large data classification. Since the classification hyperplane is determined by the support vectors and the other instances do not have an effect on the classifier, a method is introduced that does not use all instances for training. Data set may include inappropriate instances such as noisy and outlier instances. In this paper, a novel method is introduced in which at the first step using the belief function theory, the instances uncertainty such as noisy and outlier instances are identified and discarded, at the second step using the geometric method, called, boundary region, the boundary instances are determined. Finally, at the last step, by using the obtained boundary instances, the training of the SVM classifier is done. In the proposed method BF\u2013BR (Belief Function\u2013Boundary Region), the computational cost of the classification training is reduced without losing classification accuracy. The performance has been evaluated on real world data sets from UCI repository by the tenfold cross validation method. The results of the experiments have been compared with the other methods, which indicate superiority of the proposed method in terms of the number of training instances and training time while good classification accuracy for SVM training is achieved.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1007/s13042-019-00944-3", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1136696", 
            "issn": [
              "1868-8071", 
              "1868-808X"
            ], 
            "name": "International Journal of Machine Learning and Cybernetics", 
            "type": "Periodical"
          }
        ], 
        "name": "A hybrid method for increasing the speed of SVM training using belief function theory and boundary region", 
        "pagination": "1-18", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "bbfa903eebeb1ffd5c3ebbbe5fe8cf3d63dc916b58c9d6df1be6680b05f1ef8a"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s13042-019-00944-3"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1112779028"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s13042-019-00944-3", 
          "https://app.dimensions.ai/details/publication/pub.1112779028"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-11T11:51", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000359_0000000359/records_29183_00000004.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://link.springer.com/10.1007%2Fs13042-019-00944-3"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/s13042-019-00944-3'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s13042-019-00944-3'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s13042-019-00944-3'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s13042-019-00944-3'


     

    This table displays all metadata directly associated to this object as RDF triples.

    248 TRIPLES      21 PREDICATES      84 URIs      16 LITERALS      5 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s13042-019-00944-3 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Ne12d151731904345a317c130e769444c
    4 schema:citation sg:pub.10.1007/978-1-4757-2440-0
    5 sg:pub.10.1007/978-3-540-77974-2
    6 sg:pub.10.1007/bf00994018
    7 sg:pub.10.1007/s13042-014-0239-z
    8 sg:pub.10.1007/s13042-014-0265-x
    9 sg:pub.10.1007/s13042-016-0494-2
    10 sg:pub.10.1007/s13042-017-0741-1
    11 https://app.dimensions.ai/details/publication/pub.1045724697
    12 https://doi.org/10.1016/0004-3702(94)90026-4
    13 https://doi.org/10.1016/0020-0190(73)90020-3
    14 https://doi.org/10.1016/j.asoc.2015.03.033
    15 https://doi.org/10.1016/j.asoc.2016.06.014
    16 https://doi.org/10.1016/j.asoc.2017.05.021
    17 https://doi.org/10.1016/j.asoc.2017.07.038
    18 https://doi.org/10.1016/j.epsr.2017.03.030
    19 https://doi.org/10.1016/j.ijar.2015.05.002
    20 https://doi.org/10.1016/j.ijleo.2015.06.010
    21 https://doi.org/10.1016/j.ins.2017.08.033
    22 https://doi.org/10.1016/j.knosys.2013.08.005
    23 https://doi.org/10.1016/j.knosys.2014.11.013
    24 https://doi.org/10.1016/j.knosys.2015.08.007
    25 https://doi.org/10.1016/j.knosys.2016.07.029
    26 https://doi.org/10.1016/j.knosys.2016.10.031
    27 https://doi.org/10.1016/j.neucom.2013.01.058
    28 https://doi.org/10.1016/j.neucom.2013.05.040
    29 https://doi.org/10.1016/j.neucom.2014.03.037
    30 https://doi.org/10.1016/j.neucom.2014.04.078
    31 https://doi.org/10.1016/j.neucom.2014.07.038
    32 https://doi.org/10.1016/j.neucom.2014.08.033
    33 https://doi.org/10.1016/j.neucom.2015.11.081
    34 https://doi.org/10.1016/j.neucom.2015.12.046
    35 https://doi.org/10.1016/j.neunet.2011.10.006
    36 https://doi.org/10.1016/j.neunet.2015.03.013
    37 https://doi.org/10.1016/j.neunet.2017.06.008
    38 https://doi.org/10.1016/j.patcog.2012.09.003
    39 https://doi.org/10.1016/j.patcog.2014.11.005
    40 https://doi.org/10.1016/j.patcog.2016.04.008
    41 https://doi.org/10.1016/j.patcog.2016.07.004
    42 https://doi.org/10.1016/j.patcog.2017.06.003
    43 https://doi.org/10.1016/j.patcog.2017.09.035
    44 https://doi.org/10.1016/j.patcog.2018.05.023
    45 https://doi.org/10.1016/j.physa.2017.04.113
    46 https://doi.org/10.1016/j.proeng.2011.08.366
    47 https://doi.org/10.1016/j.tcs.2017.08.014
    48 https://doi.org/10.1016/j.ymssp.2016.04.001
    49 https://doi.org/10.1080/03081078308960825
    50 https://doi.org/10.1109/21.376493
    51 https://doi.org/10.1109/72.788640
    52 https://doi.org/10.1109/access.2017.2697408
    53 https://doi.org/10.1109/tii.2016.2643689
    54 https://doi.org/10.1109/tnn.2006.873281
    55 https://doi.org/10.1109/tnn.2006.878123
    56 https://doi.org/10.1109/tnn.2009.2020908
    57 https://doi.org/10.1109/tnnls.2012.2187307
    58 https://doi.org/10.1109/tpds.2017.2731764
    59 https://doi.org/10.1109/tsmc.2015.2421883
    60 https://doi.org/10.1109/tsmc.2017.2759090
    61 https://doi.org/10.1109/tsmca.2005.853483
    62 https://doi.org/10.1145/1961189.1961199
    63 https://doi.org/10.1162/089976602753633402
    64 schema:datePublished 2019-03-15
    65 schema:datePublishedReg 2019-03-15
    66 schema:description The training of the support vector machine (SVM) classifier has high computational complexity and is not suitable for large data classification. Since the classification hyperplane is determined by the support vectors and the other instances do not have an effect on the classifier, a method is introduced that does not use all instances for training. Data set may include inappropriate instances such as noisy and outlier instances. In this paper, a novel method is introduced in which at the first step using the belief function theory, the instances uncertainty such as noisy and outlier instances are identified and discarded, at the second step using the geometric method, called, boundary region, the boundary instances are determined. Finally, at the last step, by using the obtained boundary instances, the training of the SVM classifier is done. In the proposed method BF–BR (Belief Function–Boundary Region), the computational cost of the classification training is reduced without losing classification accuracy. The performance has been evaluated on real world data sets from UCI repository by the tenfold cross validation method. The results of the experiments have been compared with the other methods, which indicate superiority of the proposed method in terms of the number of training instances and training time while good classification accuracy for SVM training is achieved.
    67 schema:genre research_article
    68 schema:inLanguage en
    69 schema:isAccessibleForFree false
    70 schema:isPartOf sg:journal.1136696
    71 schema:name A hybrid method for increasing the speed of SVM training using belief function theory and boundary region
    72 schema:pagination 1-18
    73 schema:productId N865b9c1baefa49dfb6094bdad4968249
    74 Nb4ceec2695414c249f812447cef045c3
    75 Nde6dcef8e92745c2a77111d09d3418f2
    76 schema:sameAs https://app.dimensions.ai/details/publication/pub.1112779028
    77 https://doi.org/10.1007/s13042-019-00944-3
    78 schema:sdDatePublished 2019-04-11T11:51
    79 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    80 schema:sdPublisher Nd9786f47ce594b2392ecf701a12a2cea
    81 schema:url https://link.springer.com/10.1007%2Fs13042-019-00944-3
    82 sgo:license sg:explorer/license/
    83 sgo:sdDataset articles
    84 rdf:type schema:ScholarlyArticle
    85 N14cb78b81abb4292bbf0ec28cc848a9d schema:affiliation https://www.grid.ac/institutes/grid.444813.e
    86 schema:familyName Hamidzadeh
    87 schema:givenName Javad
    88 rdf:type schema:Person
    89 N2183b614c01749bdb41d90e3712e2009 schema:name Department of Computer Engineering, Salman Institute of Higher Education, Mashhad, Iran
    90 rdf:type schema:Organization
    91 N5d8792fcdb654c69af51c7a1598787a7 rdf:first N14cb78b81abb4292bbf0ec28cc848a9d
    92 rdf:rest rdf:nil
    93 N865b9c1baefa49dfb6094bdad4968249 schema:name dimensions_id
    94 schema:value pub.1112779028
    95 rdf:type schema:PropertyValue
    96 Na684f9cdfbd64042bde4b185aec224c8 schema:affiliation N2183b614c01749bdb41d90e3712e2009
    97 schema:familyName Moslemnejad
    98 schema:givenName Somaye
    99 rdf:type schema:Person
    100 Nb4ceec2695414c249f812447cef045c3 schema:name readcube_id
    101 schema:value bbfa903eebeb1ffd5c3ebbbe5fe8cf3d63dc916b58c9d6df1be6680b05f1ef8a
    102 rdf:type schema:PropertyValue
    103 Nd9786f47ce594b2392ecf701a12a2cea schema:name Springer Nature - SN SciGraph project
    104 rdf:type schema:Organization
    105 Nde6dcef8e92745c2a77111d09d3418f2 schema:name doi
    106 schema:value 10.1007/s13042-019-00944-3
    107 rdf:type schema:PropertyValue
    108 Ne12d151731904345a317c130e769444c rdf:first Na684f9cdfbd64042bde4b185aec224c8
    109 rdf:rest N5d8792fcdb654c69af51c7a1598787a7
    110 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    111 schema:name Information and Computing Sciences
    112 rdf:type schema:DefinedTerm
    113 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    114 schema:name Artificial Intelligence and Image Processing
    115 rdf:type schema:DefinedTerm
    116 sg:journal.1136696 schema:issn 1868-8071
    117 1868-808X
    118 schema:name International Journal of Machine Learning and Cybernetics
    119 rdf:type schema:Periodical
    120 sg:pub.10.1007/978-1-4757-2440-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027312764
    121 https://doi.org/10.1007/978-1-4757-2440-0
    122 rdf:type schema:CreativeWork
    123 sg:pub.10.1007/978-3-540-77974-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045724697
    124 https://doi.org/10.1007/978-3-540-77974-2
    125 rdf:type schema:CreativeWork
    126 sg:pub.10.1007/bf00994018 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025150743
    127 https://doi.org/10.1007/bf00994018
    128 rdf:type schema:CreativeWork
    129 sg:pub.10.1007/s13042-014-0239-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1049760626
    130 https://doi.org/10.1007/s13042-014-0239-z
    131 rdf:type schema:CreativeWork
    132 sg:pub.10.1007/s13042-014-0265-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1012905067
    133 https://doi.org/10.1007/s13042-014-0265-x
    134 rdf:type schema:CreativeWork
    135 sg:pub.10.1007/s13042-016-0494-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017204591
    136 https://doi.org/10.1007/s13042-016-0494-2
    137 rdf:type schema:CreativeWork
    138 sg:pub.10.1007/s13042-017-0741-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092619156
    139 https://doi.org/10.1007/s13042-017-0741-1
    140 rdf:type schema:CreativeWork
    141 https://app.dimensions.ai/details/publication/pub.1045724697 schema:CreativeWork
    142 https://doi.org/10.1016/0004-3702(94)90026-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1049557093
    143 rdf:type schema:CreativeWork
    144 https://doi.org/10.1016/0020-0190(73)90020-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041132033
    145 rdf:type schema:CreativeWork
    146 https://doi.org/10.1016/j.asoc.2015.03.033 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022830071
    147 rdf:type schema:CreativeWork
    148 https://doi.org/10.1016/j.asoc.2016.06.014 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029241520
    149 rdf:type schema:CreativeWork
    150 https://doi.org/10.1016/j.asoc.2017.05.021 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085431177
    151 rdf:type schema:CreativeWork
    152 https://doi.org/10.1016/j.asoc.2017.07.038 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090857977
    153 rdf:type schema:CreativeWork
    154 https://doi.org/10.1016/j.epsr.2017.03.030 schema:sameAs https://app.dimensions.ai/details/publication/pub.1084931678
    155 rdf:type schema:CreativeWork
    156 https://doi.org/10.1016/j.ijar.2015.05.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038737160
    157 rdf:type schema:CreativeWork
    158 https://doi.org/10.1016/j.ijleo.2015.06.010 schema:sameAs https://app.dimensions.ai/details/publication/pub.1011468980
    159 rdf:type schema:CreativeWork
    160 https://doi.org/10.1016/j.ins.2017.08.033 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091147411
    161 rdf:type schema:CreativeWork
    162 https://doi.org/10.1016/j.knosys.2013.08.005 schema:sameAs https://app.dimensions.ai/details/publication/pub.1006934373
    163 rdf:type schema:CreativeWork
    164 https://doi.org/10.1016/j.knosys.2014.11.013 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040326146
    165 rdf:type schema:CreativeWork
    166 https://doi.org/10.1016/j.knosys.2015.08.007 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029920728
    167 rdf:type schema:CreativeWork
    168 https://doi.org/10.1016/j.knosys.2016.07.029 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024723303
    169 rdf:type schema:CreativeWork
    170 https://doi.org/10.1016/j.knosys.2016.10.031 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052402903
    171 rdf:type schema:CreativeWork
    172 https://doi.org/10.1016/j.neucom.2013.01.058 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035330761
    173 rdf:type schema:CreativeWork
    174 https://doi.org/10.1016/j.neucom.2013.05.040 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030252933
    175 rdf:type schema:CreativeWork
    176 https://doi.org/10.1016/j.neucom.2014.03.037 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040916121
    177 rdf:type schema:CreativeWork
    178 https://doi.org/10.1016/j.neucom.2014.04.078 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042786159
    179 rdf:type schema:CreativeWork
    180 https://doi.org/10.1016/j.neucom.2014.07.038 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019937018
    181 rdf:type schema:CreativeWork
    182 https://doi.org/10.1016/j.neucom.2014.08.033 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053183317
    183 rdf:type schema:CreativeWork
    184 https://doi.org/10.1016/j.neucom.2015.11.081 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027980512
    185 rdf:type schema:CreativeWork
    186 https://doi.org/10.1016/j.neucom.2015.12.046 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022484674
    187 rdf:type schema:CreativeWork
    188 https://doi.org/10.1016/j.neunet.2011.10.006 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021018868
    189 rdf:type schema:CreativeWork
    190 https://doi.org/10.1016/j.neunet.2015.03.013 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045354958
    191 rdf:type schema:CreativeWork
    192 https://doi.org/10.1016/j.neunet.2017.06.008 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090448589
    193 rdf:type schema:CreativeWork
    194 https://doi.org/10.1016/j.patcog.2012.09.003 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017777088
    195 rdf:type schema:CreativeWork
    196 https://doi.org/10.1016/j.patcog.2014.11.005 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038571142
    197 rdf:type schema:CreativeWork
    198 https://doi.org/10.1016/j.patcog.2016.04.008 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041528745
    199 rdf:type schema:CreativeWork
    200 https://doi.org/10.1016/j.patcog.2016.07.004 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030830976
    201 rdf:type schema:CreativeWork
    202 https://doi.org/10.1016/j.patcog.2017.06.003 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085857833
    203 rdf:type schema:CreativeWork
    204 https://doi.org/10.1016/j.patcog.2017.09.035 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091914310
    205 rdf:type schema:CreativeWork
    206 https://doi.org/10.1016/j.patcog.2018.05.023 schema:sameAs https://app.dimensions.ai/details/publication/pub.1104264473
    207 rdf:type schema:CreativeWork
    208 https://doi.org/10.1016/j.physa.2017.04.113 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085181105
    209 rdf:type schema:CreativeWork
    210 https://doi.org/10.1016/j.proeng.2011.08.366 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050090745
    211 rdf:type schema:CreativeWork
    212 https://doi.org/10.1016/j.tcs.2017.08.014 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091328218
    213 rdf:type schema:CreativeWork
    214 https://doi.org/10.1016/j.ymssp.2016.04.001 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040475132
    215 rdf:type schema:CreativeWork
    216 https://doi.org/10.1080/03081078308960825 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044845053
    217 rdf:type schema:CreativeWork
    218 https://doi.org/10.1109/21.376493 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061122112
    219 rdf:type schema:CreativeWork
    220 https://doi.org/10.1109/72.788640 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061219233
    221 rdf:type schema:CreativeWork
    222 https://doi.org/10.1109/access.2017.2697408 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085284787
    223 rdf:type schema:CreativeWork
    224 https://doi.org/10.1109/tii.2016.2643689 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061633044
    225 rdf:type schema:CreativeWork
    226 https://doi.org/10.1109/tnn.2006.873281 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061717015
    227 rdf:type schema:CreativeWork
    228 https://doi.org/10.1109/tnn.2006.878123 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061717067
    229 rdf:type schema:CreativeWork
    230 https://doi.org/10.1109/tnn.2009.2020908 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061717555
    231 rdf:type schema:CreativeWork
    232 https://doi.org/10.1109/tnnls.2012.2187307 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061718070
    233 rdf:type schema:CreativeWork
    234 https://doi.org/10.1109/tpds.2017.2731764 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090973146
    235 rdf:type schema:CreativeWork
    236 https://doi.org/10.1109/tsmc.2015.2421883 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061794346
    237 rdf:type schema:CreativeWork
    238 https://doi.org/10.1109/tsmc.2017.2759090 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093129769
    239 rdf:type schema:CreativeWork
    240 https://doi.org/10.1109/tsmca.2005.853483 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061795115
    241 rdf:type schema:CreativeWork
    242 https://doi.org/10.1145/1961189.1961199 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013637525
    243 rdf:type schema:CreativeWork
    244 https://doi.org/10.1162/089976602753633402 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008605532
    245 rdf:type schema:CreativeWork
    246 https://www.grid.ac/institutes/grid.444813.e schema:alternateName Sadjad University of Technology
    247 schema:name Faculty of Computer Engineering and Information Technology, Sadjad University of Technology, Mashhad, Iran
    248 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...