Dataset Open Access

Synthetic Dataset for Outlier Detection

Koncar, Philipp


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.1171077</identifier>
  <creators>
    <creator>
      <creatorName>Koncar, Philipp</creatorName>
      <givenName>Philipp</givenName>
      <familyName>Koncar</familyName>
      <affiliation></affiliation>
    </creator>
  </creators>
  <titles>
    <title>Synthetic Dataset for Outlier Detection</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2018</publicationYear>
  <subjects>
    <subject>outlier detection</subject>
    <subject>synthetic</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2018-02-11</date>
  </dates>
  <resourceType resourceTypeGeneral="Dataset"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/1171077</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.1171076</relatedIdentifier>
  </relatedIdentifiers>
  <version>1.0</version>
  <rightsList>
    <rights rightsURI="http://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;This synthetically generated dataset can be used to evaluate outlier detection algorithms. It has 10 attributes and 1000 observations, of which 100 are&amp;nbsp;labeled as outliers. Two-dimensional combinations of attributes form differently shaped clusters.&lt;/p&gt;

&lt;ul&gt;
	&lt;li&gt;Attribute 0 &amp;amp; Attribute&amp;nbsp;1: Two circular clusters&lt;/li&gt;
	&lt;li&gt;Attribute&amp;nbsp;2 &amp;amp; Attribute&amp;nbsp;3: Two banana shaped clusters&lt;/li&gt;
	&lt;li&gt;Attribute&amp;nbsp;4 &amp;amp; Attribute&amp;nbsp;5: Three point clouds&lt;/li&gt;
	&lt;li&gt;Attribute&amp;nbsp;6 &amp;amp; Attribute&amp;nbsp;7: Two point clouds with variances&lt;/li&gt;
	&lt;li&gt;Attribute&amp;nbsp;8 &amp;amp; Attribute&amp;nbsp;9: Three anisotropic shaped clusters.&amp;nbsp;&lt;/li&gt;
&lt;/ul&gt;

&lt;p&gt;The &amp;quot;outlier&amp;quot; column states whether an observation is an outlier or not. Additionally, the .zip file contains 10 stratified randomized train test splits (70% train, 30% test).&lt;/p&gt;</description>
  </descriptions>
</resource>
1,319
134
views
downloads
All versions This version
Views 1,3191,321
Downloads 134134
Data volume 135.4 MB135.4 MB
Unique views 1,2691,271
Unique downloads 129129

Share

Cite as