Anomaly detection in a mobile data network

dc.contributor.advisorNgwenya, Mzabalazo
dc.contributor.authorSalzwedel, Jason Paul
dc.date.accessioned2020-02-20T11:10:31Z
dc.date.available2020-02-20T11:10:31Z
dc.date.issued2019
dc.date.updated2020-02-14T12:21:35Z
dc.description.abstractThe dissertation investigated the creation of an anomaly detection approach to identify anomalies in the SGW elements of a LTE network. Unsupervised techniques were compared and used to identify and remove anomalies in the training data set. This “cleaned” data set was then used to train an autoencoder in an semi-supervised approach. The resultant autoencoder was able to indentify normal observations. A subsequent data set was then analysed by the autoencoder. The resultant reconstruction errors were then compared to the ground truth events to investigate the effectiveness of the autoencoder’s anomaly detection capability.
dc.identifier.apacitationSalzwedel, J. P. (2019). <i>Anomaly detection in a mobile data network</i>. (). ,Faculty of Science ,Department of Statistical Sciences. Retrieved from http://hdl.handle.net/11427/31202en_ZA
dc.identifier.chicagocitationSalzwedel, Jason Paul. <i>"Anomaly detection in a mobile data network."</i> ., ,Faculty of Science ,Department of Statistical Sciences, 2019. http://hdl.handle.net/11427/31202en_ZA
dc.identifier.citationSalzwedel, J. 2019. Anomaly detection in a mobile data network.en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Salzwedel, Jason Paul AB - The dissertation investigated the creation of an anomaly detection approach to identify anomalies in the SGW elements of a LTE network. Unsupervised techniques were compared and used to identify and remove anomalies in the training data set. This “cleaned” data set was then used to train an autoencoder in an semi-supervised approach. The resultant autoencoder was able to indentify normal observations. A subsequent data set was then analysed by the autoencoder. The resultant reconstruction errors were then compared to the ground truth events to investigate the effectiveness of the autoencoder’s anomaly detection capability. DA - 2019 DB - OpenUCT DP - University of Cape Town KW - Statistics LK - https://open.uct.ac.za PY - 2019 T1 - Anomaly detection in a mobile data network TI - Anomaly detection in a mobile data network UR - http://hdl.handle.net/11427/31202 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/31202
dc.identifier.vancouvercitationSalzwedel JP. Anomaly detection in a mobile data network. []. ,Faculty of Science ,Department of Statistical Sciences, 2019 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/31202en_ZA
dc.language.rfc3066eng
dc.publisher.departmentDepartment of Statistical Sciences
dc.publisher.facultyFaculty of Science
dc.subjectStatistics
dc.titleAnomaly detection in a mobile data network
dc.typeMaster Thesis
dc.type.qualificationlevelMasters
dc.type.qualificationnameMSc
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
thesis_sci_2019_salzwedel_jason_paul.pdf
Size:
3.15 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
0 B
Format:
Item-specific license agreed upon to submission
Description:
Collections