November 14, 2018 Thesis Open Access

tewodros hailu

DCAT Export

<?xml version='1.0' encoding='utf-8'?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#">
  <rdf:Description rdf:about="https://doi.org/10.20372/nadre:4488">
    <rdf:type rdf:resource="http://www.w3.org/ns/dcat#Dataset"/>
    <dct:type rdf:resource="http://purl.org/dc/dcmitype/Text"/>
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.20372/nadre:4488</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.20372/nadre:4488"/>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>tewodros hailu</foaf:name>
      </rdf:Description>
    </dct:creator>
    <dct:title>Network Traffic Classification Using Machine Learning: A Step Towards Over-the-Top Bypass Fraud Detection</dct:title>
    <dct:publisher>
      <foaf:Agent>
        <foaf:name>Zenodo</foaf:name>
      </foaf:Agent>
    </dct:publisher>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2018</dct:issued>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2018-11-14</dct:issued>
    <owl:sameAs rdf:resource="https://nadre.ethernet.edu.et/record/4488"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://nadre.ethernet.edu.et/record/4488</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.20372/nadre:4487"/>
    <dct:isPartOf rdf:resource="https://nadre.ethernet.edu.et/communities/aau"/>
    <dct:isPartOf rdf:resource="https://nadre.ethernet.edu.et/communities/zenodo"/>
    <dct:description>&lt;p&gt;Over-the-Top (OTT) bypass is a type of Interconnect Bypass fraud where regular&lt;br&gt; voice calls are rerouted through OTT network and terminated as an OTT call. These&lt;br&gt; calls are terminated using OTT applications which need user&amp;rsquo;s Mobile Station International&lt;br&gt; Subscriber Directory Number (MSISDN) for authentication. Detecting&lt;br&gt; OTT voice call packets through different network traffic classification techniques is&lt;br&gt; one subtask in the detection of this fraud.&lt;br&gt; In this thesis, performance of three machine learning algorithms; Adaptive Booster&lt;br&gt; (AdaBoost) + J48, Repeated Incremental Pruning to Produce Error Reduction (RIPPER),&lt;br&gt; and Support Vector Machine (SVM) is evaluated in detecting MSISDN-based OTT&lt;br&gt; packets taking Viber, Tango, and Telegram as a sample. Detection of OTT traffic&lt;br&gt; and voice call packets from the OTT traffic have been treated separately as classification&lt;br&gt; tasks. Ten cross-fold and separate test data validation techniques together&lt;br&gt; with 1.7 million labeled packets generated and captured in controlled laboratory&lt;br&gt; environment are used in the evaluation process.&lt;br&gt; AdaBoost + J48 achieved the best accuracy on both classification tasks compared to&lt;br&gt; the others while using ten cross-fold validation. However, an accuracy of 48.4%&lt;br&gt; obtained in detecting voice call packets while using separate test data validation&lt;br&gt; makes it less preferable in the classification task. Even if it takes longer time to&lt;br&gt; train SVM, it was the best performer (95.35% accurate) in detecting voice call packets&lt;br&gt; in separate test data validation. Considering accuracy attained by the algorithms&lt;br&gt; in separate test data validation technique together with the detection rate&lt;br&gt; of OTT voice call packets, SVM is preferable than the other two algorithms&lt;/p&gt;</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dcat:distribution>
      <dcat:Distribution>
        <dct:rights>
          <dct:RightsStatement rdf:about="http://www.opendefinition.org/licenses/cc-by">
            <rdfs:label>Creative Commons Attribution</rdfs:label>
          </dct:RightsStatement>
        </dct:rights>
        <dcat:accessURL rdf:resource="https://doi.org/10.20372/nadre:4488"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.20372/nadre:4488"/>
        <dcat:byteSize>647925</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://nadre.ethernet.edu.et/record/4488/files/f1042664640.pdf"/>
        <dcat:mediaType>application/pdf</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>