Instance selection improves geometric mean accuracy: a study on imbalanced data classification View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-02-06

AUTHORS

Ludmila I. Kuncheva, Álvar Arnaiz-González, José-Francisco Díez-Pastor, Iain A. D. Gunn

ABSTRACT

A natural way of handling imbalanced data is to attempt to equalise the class frequencies and train the classifier of choice on balanced data. For two-class imbalanced problems, the classification success is typically measured by the geometric mean (GM) of the true positive and true negative rates. Here we prove that GM can be improved upon by instance selection, and give the theoretical conditions for such an improvement. We demonstrate that GM is non-monotonic with respect to the number of retained instances, which discourages systematic instance selection. We also show that balancing the distribution frequencies is inferior to a direct maximisation of GM. To verify our theoretical findings, we carried out an experimental study of 12 instance selection methods for imbalanced data, using 66 standard benchmark data sets. The results reveal possible room for new instance selection methods for imbalanced data. More... »

PAGES

1-14

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s13748-019-00172-4

DOI

http://dx.doi.org/10.1007/s13748-019-00172-4

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1111949773


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": {
          "alternateName": "Bangor University", 
          "id": "https://www.grid.ac/institutes/grid.7362.0", 
          "name": [
            "School of Computer Science, Bangor University, Dean Street, LL57 2NJ, Bangor, Gwynedd, Wales, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kuncheva", 
        "givenName": "Ludmila I.", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Burgos", 
          "id": "https://www.grid.ac/institutes/grid.23520.36", 
          "name": [
            "Escuela Polit\u00e9cnica Superior, Universidad de Burgos, Avda. de Cantabria s/n, 09006, Burgos, Spain"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Arnaiz-Gonz\u00e1lez", 
        "givenName": "\u00c1lvar", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Burgos", 
          "id": "https://www.grid.ac/institutes/grid.23520.36", 
          "name": [
            "Escuela Polit\u00e9cnica Superior, Universidad de Burgos, Avda. de Cantabria s/n, 09006, Burgos, Spain"
          ], 
          "type": "Organization"
        }, 
        "familyName": "D\u00edez-Pastor", 
        "givenName": "Jos\u00e9-Francisco", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Middlesex University", 
          "id": "https://www.grid.ac/institutes/grid.15822.3c", 
          "name": [
            "Department of Computer Science, Middlesex University, NW4 4BT, London, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Gunn", 
        "givenName": "Iain A. D.", 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/j.knosys.2011.05.002", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1000986200"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.knosys.2015.04.022", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1001878442"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.asoc.2015.08.060", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1002326914"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/1471-2164-10-s1-i1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1003847639", 
          "https://doi.org/10.1186/1471-2164-10-s1-i1"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1006/jcss.1997.1504", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004338842"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-48229-6_9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005002170", 
          "https://doi.org/10.1007/3-540-48229-6_9"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-48229-6_9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005002170", 
          "https://doi.org/10.1007/3-540-48229-6_9"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s13748-016-0094-0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005418935", 
          "https://doi.org/10.1007/s13748-016-0094-0"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s13748-016-0094-0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005418935", 
          "https://doi.org/10.1007/s13748-016-0094-0"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1093/bioinformatics/btm344", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009424564"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10044-003-0192-z", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1010264089", 
          "https://doi.org/10.1007/s10044-003-0192-z"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1007730.1007733", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1012245555"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.ins.2015.07.025", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1014363299"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-30115-8_7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1016314455", 
          "https://doi.org/10.1007/978-3-540-30115-8_7"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-30115-8_7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1016314455", 
          "https://doi.org/10.1007/978-3-540-30115-8_7"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.jag.2014.07.002", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018484044"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.patcog.2016.03.012", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1027681220"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1007626913721", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030839762", 
          "https://doi.org/10.1023/a:1007626913721"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10115-007-0114-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1032043586", 
          "https://doi.org/10.1007/s10115-007-0114-2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10115-007-0114-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1032043586", 
          "https://doi.org/10.1007/s10115-007-0114-2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1007730.1007738", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1034710737"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0031-3203(02)00257-1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1036892377"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0031-3203(02)00257-1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1036892377"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1007730.1007735", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1037852366"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.patcog.2013.05.006", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042192423"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.eswa.2014.02.026", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1043853697"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsmc.1976.4309452", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044229856"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/evco.2009.17.3.275", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044453908"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neucom.2013.01.050", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045082749"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0167-8655(94)90127-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052101887"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0167-8655(94)90127-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052101887"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/089976698300017197", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053132543"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/34.574797", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061156543"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tfuzz.2010.2042721", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061606343"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tfuzz.2014.2336263", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061606889"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tit.1967.1053964", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061646286"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tit.1968.1054155", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061646472"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2011.142", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061744037"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsmc.1972.4309137", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061792625"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsmca.2009.2020804", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061795507"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsmca.2009.2027131", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061795530"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsmca.2009.2029559", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061795540"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsmcc.2010.2103939", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061798312"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsmcc.2011.2161285", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061798360"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsmcc.2012.2226152", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061798471"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/grc.2006.1635905", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094017132"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/grc.2006.1635905", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094017132"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cube.2013.31", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095595473"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s13748-018-0148-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1101884126", 
          "https://doi.org/10.1007/s13748-018-0148-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s13748-018-0148-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1101884126", 
          "https://doi.org/10.1007/s13748-018-0148-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s13748-018-0148-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1101884126", 
          "https://doi.org/10.1007/s13748-018-0148-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s13748-018-0148-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1101884126", 
          "https://doi.org/10.1007/s13748-018-0148-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://app.dimensions.ai/details/publication/pub.1108232028", 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-98074-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1108232028", 
          "https://doi.org/10.1007/978-3-319-98074-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-98074-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1108232028", 
          "https://doi.org/10.1007/978-3-319-98074-4"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-02-06", 
    "datePublishedReg": "2019-02-06", 
    "description": "A natural way of handling imbalanced data is to attempt to equalise the class frequencies and train the classifier of choice on balanced data. For two-class imbalanced problems, the classification success is typically measured by the geometric mean (GM) of the true positive and true negative rates. Here we prove that GM can be improved upon by instance selection, and give the theoretical conditions for such an improvement. We demonstrate that GM is non-monotonic with respect to the number of retained instances, which discourages systematic instance selection. We also show that balancing the distribution frequencies is inferior to a direct maximisation of GM. To verify our theoretical findings, we carried out an experimental study of 12 instance selection methods for imbalanced data, using 66 standard benchmark data sets. The results reveal possible room for new instance selection methods for imbalanced data.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s13748-019-00172-4", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1136525", 
        "issn": [
          "2192-6352", 
          "2192-6360"
        ], 
        "name": "Progress in Artificial Intelligence", 
        "type": "Periodical"
      }
    ], 
    "name": "Instance selection improves geometric mean accuracy: a study on imbalanced data classification", 
    "pagination": "1-14", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "f2e97b73b1035b8bd45e0ea386bdc88318da0405f851072ab8a4dcd366239cb5"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s13748-019-00172-4"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1111949773"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s13748-019-00172-4", 
      "https://app.dimensions.ai/details/publication/pub.1111949773"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T09:02", 
    "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/v90/0000000331_0000000331/records_105422_00000000.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://link.springer.com/10.1007%2Fs13748-019-00172-4"
  }
]
 

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/s13748-019-00172-4'

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/s13748-019-00172-4'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s13748-019-00172-4'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s13748-019-00172-4'


 

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

218 TRIPLES      21 PREDICATES      68 URIs      16 LITERALS      5 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s13748-019-00172-4 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N1791af5286b940e9b4c684ed09e71592
4 schema:citation sg:pub.10.1007/3-540-48229-6_9
5 sg:pub.10.1007/978-3-319-98074-4
6 sg:pub.10.1007/978-3-540-30115-8_7
7 sg:pub.10.1007/s10044-003-0192-z
8 sg:pub.10.1007/s10115-007-0114-2
9 sg:pub.10.1007/s13748-016-0094-0
10 sg:pub.10.1007/s13748-018-0148-6
11 sg:pub.10.1023/a:1007626913721
12 sg:pub.10.1186/1471-2164-10-s1-i1
13 https://app.dimensions.ai/details/publication/pub.1108232028
14 https://doi.org/10.1006/jcss.1997.1504
15 https://doi.org/10.1016/0167-8655(94)90127-9
16 https://doi.org/10.1016/j.asoc.2015.08.060
17 https://doi.org/10.1016/j.eswa.2014.02.026
18 https://doi.org/10.1016/j.ins.2015.07.025
19 https://doi.org/10.1016/j.jag.2014.07.002
20 https://doi.org/10.1016/j.knosys.2011.05.002
21 https://doi.org/10.1016/j.knosys.2015.04.022
22 https://doi.org/10.1016/j.neucom.2013.01.050
23 https://doi.org/10.1016/j.patcog.2013.05.006
24 https://doi.org/10.1016/j.patcog.2016.03.012
25 https://doi.org/10.1016/s0031-3203(02)00257-1
26 https://doi.org/10.1093/bioinformatics/btm344
27 https://doi.org/10.1109/34.574797
28 https://doi.org/10.1109/cube.2013.31
29 https://doi.org/10.1109/grc.2006.1635905
30 https://doi.org/10.1109/tfuzz.2010.2042721
31 https://doi.org/10.1109/tfuzz.2014.2336263
32 https://doi.org/10.1109/tit.1967.1053964
33 https://doi.org/10.1109/tit.1968.1054155
34 https://doi.org/10.1109/tpami.2011.142
35 https://doi.org/10.1109/tsmc.1972.4309137
36 https://doi.org/10.1109/tsmc.1976.4309452
37 https://doi.org/10.1109/tsmca.2009.2020804
38 https://doi.org/10.1109/tsmca.2009.2027131
39 https://doi.org/10.1109/tsmca.2009.2029559
40 https://doi.org/10.1109/tsmcc.2010.2103939
41 https://doi.org/10.1109/tsmcc.2011.2161285
42 https://doi.org/10.1109/tsmcc.2012.2226152
43 https://doi.org/10.1145/1007730.1007733
44 https://doi.org/10.1145/1007730.1007735
45 https://doi.org/10.1145/1007730.1007738
46 https://doi.org/10.1162/089976698300017197
47 https://doi.org/10.1162/evco.2009.17.3.275
48 schema:datePublished 2019-02-06
49 schema:datePublishedReg 2019-02-06
50 schema:description A natural way of handling imbalanced data is to attempt to equalise the class frequencies and train the classifier of choice on balanced data. For two-class imbalanced problems, the classification success is typically measured by the geometric mean (GM) of the true positive and true negative rates. Here we prove that GM can be improved upon by instance selection, and give the theoretical conditions for such an improvement. We demonstrate that GM is non-monotonic with respect to the number of retained instances, which discourages systematic instance selection. We also show that balancing the distribution frequencies is inferior to a direct maximisation of GM. To verify our theoretical findings, we carried out an experimental study of 12 instance selection methods for imbalanced data, using 66 standard benchmark data sets. The results reveal possible room for new instance selection methods for imbalanced data.
51 schema:genre research_article
52 schema:inLanguage en
53 schema:isAccessibleForFree false
54 schema:isPartOf sg:journal.1136525
55 schema:name Instance selection improves geometric mean accuracy: a study on imbalanced data classification
56 schema:pagination 1-14
57 schema:productId N2e9dfa1d3e3f4a23b3d2b805ccc26d2c
58 N568e175529b74a9eb92234a2867eb5d9
59 N90bb5e8687eb4e78b99d39d742ae4342
60 schema:sameAs https://app.dimensions.ai/details/publication/pub.1111949773
61 https://doi.org/10.1007/s13748-019-00172-4
62 schema:sdDatePublished 2019-04-11T09:02
63 schema:sdLicense https://scigraph.springernature.com/explorer/license/
64 schema:sdPublisher N0d04ba78cf8c48a3bd7d702eac763bfb
65 schema:url https://link.springer.com/10.1007%2Fs13748-019-00172-4
66 sgo:license sg:explorer/license/
67 sgo:sdDataset articles
68 rdf:type schema:ScholarlyArticle
69 N0b9192324a544333a017538e2d257bfb rdf:first Naae0a4e124944d6586522e3cea42e64b
70 rdf:rest N59b64e42c5bf4db38ed8de8bf1986511
71 N0d04ba78cf8c48a3bd7d702eac763bfb schema:name Springer Nature - SN SciGraph project
72 rdf:type schema:Organization
73 N1791af5286b940e9b4c684ed09e71592 rdf:first Nd01777ac4bd040abb90bac3de85a98cc
74 rdf:rest N0b9192324a544333a017538e2d257bfb
75 N2e9dfa1d3e3f4a23b3d2b805ccc26d2c schema:name doi
76 schema:value 10.1007/s13748-019-00172-4
77 rdf:type schema:PropertyValue
78 N3d4773376c6b4ffd8cf2cde5ad462591 rdf:first Ndbf328ba626f42858cb62f12cda830fa
79 rdf:rest rdf:nil
80 N568e175529b74a9eb92234a2867eb5d9 schema:name readcube_id
81 schema:value f2e97b73b1035b8bd45e0ea386bdc88318da0405f851072ab8a4dcd366239cb5
82 rdf:type schema:PropertyValue
83 N59b64e42c5bf4db38ed8de8bf1986511 rdf:first N7ba2a9b666f742708758f904454d670b
84 rdf:rest N3d4773376c6b4ffd8cf2cde5ad462591
85 N7ba2a9b666f742708758f904454d670b schema:affiliation https://www.grid.ac/institutes/grid.23520.36
86 schema:familyName Díez-Pastor
87 schema:givenName José-Francisco
88 rdf:type schema:Person
89 N90bb5e8687eb4e78b99d39d742ae4342 schema:name dimensions_id
90 schema:value pub.1111949773
91 rdf:type schema:PropertyValue
92 Naae0a4e124944d6586522e3cea42e64b schema:affiliation https://www.grid.ac/institutes/grid.23520.36
93 schema:familyName Arnaiz-González
94 schema:givenName Álvar
95 rdf:type schema:Person
96 Nd01777ac4bd040abb90bac3de85a98cc schema:affiliation https://www.grid.ac/institutes/grid.7362.0
97 schema:familyName Kuncheva
98 schema:givenName Ludmila I.
99 rdf:type schema:Person
100 Ndbf328ba626f42858cb62f12cda830fa schema:affiliation https://www.grid.ac/institutes/grid.15822.3c
101 schema:familyName Gunn
102 schema:givenName Iain A. D.
103 rdf:type schema:Person
104 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
105 schema:name Information and Computing Sciences
106 rdf:type schema:DefinedTerm
107 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
108 schema:name Artificial Intelligence and Image Processing
109 rdf:type schema:DefinedTerm
110 sg:journal.1136525 schema:issn 2192-6352
111 2192-6360
112 schema:name Progress in Artificial Intelligence
113 rdf:type schema:Periodical
114 sg:pub.10.1007/3-540-48229-6_9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005002170
115 https://doi.org/10.1007/3-540-48229-6_9
116 rdf:type schema:CreativeWork
117 sg:pub.10.1007/978-3-319-98074-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1108232028
118 https://doi.org/10.1007/978-3-319-98074-4
119 rdf:type schema:CreativeWork
120 sg:pub.10.1007/978-3-540-30115-8_7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1016314455
121 https://doi.org/10.1007/978-3-540-30115-8_7
122 rdf:type schema:CreativeWork
123 sg:pub.10.1007/s10044-003-0192-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1010264089
124 https://doi.org/10.1007/s10044-003-0192-z
125 rdf:type schema:CreativeWork
126 sg:pub.10.1007/s10115-007-0114-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032043586
127 https://doi.org/10.1007/s10115-007-0114-2
128 rdf:type schema:CreativeWork
129 sg:pub.10.1007/s13748-016-0094-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005418935
130 https://doi.org/10.1007/s13748-016-0094-0
131 rdf:type schema:CreativeWork
132 sg:pub.10.1007/s13748-018-0148-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101884126
133 https://doi.org/10.1007/s13748-018-0148-6
134 rdf:type schema:CreativeWork
135 sg:pub.10.1023/a:1007626913721 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030839762
136 https://doi.org/10.1023/a:1007626913721
137 rdf:type schema:CreativeWork
138 sg:pub.10.1186/1471-2164-10-s1-i1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003847639
139 https://doi.org/10.1186/1471-2164-10-s1-i1
140 rdf:type schema:CreativeWork
141 https://app.dimensions.ai/details/publication/pub.1108232028 schema:CreativeWork
142 https://doi.org/10.1006/jcss.1997.1504 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004338842
143 rdf:type schema:CreativeWork
144 https://doi.org/10.1016/0167-8655(94)90127-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052101887
145 rdf:type schema:CreativeWork
146 https://doi.org/10.1016/j.asoc.2015.08.060 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002326914
147 rdf:type schema:CreativeWork
148 https://doi.org/10.1016/j.eswa.2014.02.026 schema:sameAs https://app.dimensions.ai/details/publication/pub.1043853697
149 rdf:type schema:CreativeWork
150 https://doi.org/10.1016/j.ins.2015.07.025 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014363299
151 rdf:type schema:CreativeWork
152 https://doi.org/10.1016/j.jag.2014.07.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018484044
153 rdf:type schema:CreativeWork
154 https://doi.org/10.1016/j.knosys.2011.05.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000986200
155 rdf:type schema:CreativeWork
156 https://doi.org/10.1016/j.knosys.2015.04.022 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001878442
157 rdf:type schema:CreativeWork
158 https://doi.org/10.1016/j.neucom.2013.01.050 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045082749
159 rdf:type schema:CreativeWork
160 https://doi.org/10.1016/j.patcog.2013.05.006 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042192423
161 rdf:type schema:CreativeWork
162 https://doi.org/10.1016/j.patcog.2016.03.012 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027681220
163 rdf:type schema:CreativeWork
164 https://doi.org/10.1016/s0031-3203(02)00257-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036892377
165 rdf:type schema:CreativeWork
166 https://doi.org/10.1093/bioinformatics/btm344 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009424564
167 rdf:type schema:CreativeWork
168 https://doi.org/10.1109/34.574797 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061156543
169 rdf:type schema:CreativeWork
170 https://doi.org/10.1109/cube.2013.31 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095595473
171 rdf:type schema:CreativeWork
172 https://doi.org/10.1109/grc.2006.1635905 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094017132
173 rdf:type schema:CreativeWork
174 https://doi.org/10.1109/tfuzz.2010.2042721 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061606343
175 rdf:type schema:CreativeWork
176 https://doi.org/10.1109/tfuzz.2014.2336263 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061606889
177 rdf:type schema:CreativeWork
178 https://doi.org/10.1109/tit.1967.1053964 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061646286
179 rdf:type schema:CreativeWork
180 https://doi.org/10.1109/tit.1968.1054155 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061646472
181 rdf:type schema:CreativeWork
182 https://doi.org/10.1109/tpami.2011.142 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061744037
183 rdf:type schema:CreativeWork
184 https://doi.org/10.1109/tsmc.1972.4309137 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061792625
185 rdf:type schema:CreativeWork
186 https://doi.org/10.1109/tsmc.1976.4309452 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044229856
187 rdf:type schema:CreativeWork
188 https://doi.org/10.1109/tsmca.2009.2020804 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061795507
189 rdf:type schema:CreativeWork
190 https://doi.org/10.1109/tsmca.2009.2027131 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061795530
191 rdf:type schema:CreativeWork
192 https://doi.org/10.1109/tsmca.2009.2029559 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061795540
193 rdf:type schema:CreativeWork
194 https://doi.org/10.1109/tsmcc.2010.2103939 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061798312
195 rdf:type schema:CreativeWork
196 https://doi.org/10.1109/tsmcc.2011.2161285 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061798360
197 rdf:type schema:CreativeWork
198 https://doi.org/10.1109/tsmcc.2012.2226152 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061798471
199 rdf:type schema:CreativeWork
200 https://doi.org/10.1145/1007730.1007733 schema:sameAs https://app.dimensions.ai/details/publication/pub.1012245555
201 rdf:type schema:CreativeWork
202 https://doi.org/10.1145/1007730.1007735 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037852366
203 rdf:type schema:CreativeWork
204 https://doi.org/10.1145/1007730.1007738 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034710737
205 rdf:type schema:CreativeWork
206 https://doi.org/10.1162/089976698300017197 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053132543
207 rdf:type schema:CreativeWork
208 https://doi.org/10.1162/evco.2009.17.3.275 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044453908
209 rdf:type schema:CreativeWork
210 https://www.grid.ac/institutes/grid.15822.3c schema:alternateName Middlesex University
211 schema:name Department of Computer Science, Middlesex University, NW4 4BT, London, UK
212 rdf:type schema:Organization
213 https://www.grid.ac/institutes/grid.23520.36 schema:alternateName University of Burgos
214 schema:name Escuela Politécnica Superior, Universidad de Burgos, Avda. de Cantabria s/n, 09006, Burgos, Spain
215 rdf:type schema:Organization
216 https://www.grid.ac/institutes/grid.7362.0 schema:alternateName Bangor University
217 schema:name School of Computer Science, Bangor University, Dean Street, LL57 2NJ, Bangor, Gwynedd, Wales, UK
218 rdf:type schema:Organization
 




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


...