Anomaly detection with data quality early warning systems in ATLAS

dc.contributor.advisorYacoob, Sahal
dc.contributor.advisorKeaveney James
dc.contributor.authorMsutwana, Senzo
dc.date.accessioned2024-05-27T08:30:26Z
dc.date.available2024-05-27T08:30:26Z
dc.date.issued2023
dc.date.updated2024-05-22T08:41:20Z
dc.description.abstractIn this dissertation, the implementation of a Data-Quality Early Warning System (DQEWS) is explored. We use unsupervised Machine Learning (ML) methods to evaluate Data-Quality (DQ) in the ATLAS detector. We do so by observing and quantifying the evolution of Luminosity-Block (LB) data from Inner Detector (ID) tracking information, with a single LB towards the beginning of a run used as the reference. In this way, we obtain a trajectory that describes how the recorded LB data drift over the course of a run. Within the scope of this project thus far, the following will be shown. The version of the DQEWS algorithm defined as of the presentation of the results shown in this dissertation is shown to sufficiently flag good LBs as 'good', and bad LBs as 'bad' under the condition that the flagging criteria are evaluated on LB datasets that lie within a similar range of instantaneous luminosity as the LB datasets used to construct the criteria
dc.identifier.apacitationMsutwana, S. (2023). <i>Anomaly detection with data quality early warning systems in ATLAS</i>. (). ,Faculty of Science ,Department of Physics. Retrieved from http://hdl.handle.net/11427/39703en_ZA
dc.identifier.chicagocitationMsutwana, Senzo. <i>"Anomaly detection with data quality early warning systems in ATLAS."</i> ., ,Faculty of Science ,Department of Physics, 2023. http://hdl.handle.net/11427/39703en_ZA
dc.identifier.citationMsutwana, S. 2023. Anomaly detection with data quality early warning systems in ATLAS. . ,Faculty of Science ,Department of Physics. http://hdl.handle.net/11427/39703en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Msutwana, Senzo AB - In this dissertation, the implementation of a Data-Quality Early Warning System (DQEWS) is explored. We use unsupervised Machine Learning (ML) methods to evaluate Data-Quality (DQ) in the ATLAS detector. We do so by observing and quantifying the evolution of Luminosity-Block (LB) data from Inner Detector (ID) tracking information, with a single LB towards the beginning of a run used as the reference. In this way, we obtain a trajectory that describes how the recorded LB data drift over the course of a run. Within the scope of this project thus far, the following will be shown. The version of the DQEWS algorithm defined as of the presentation of the results shown in this dissertation is shown to sufficiently flag good LBs as 'good', and bad LBs as 'bad' under the condition that the flagging criteria are evaluated on LB datasets that lie within a similar range of instantaneous luminosity as the LB datasets used to construct the criteria DA - 2023 DB - OpenUCT DP - University of Cape Town KW - Physics LK - https://open.uct.ac.za PY - 2023 T1 - Anomaly detection with data quality early warning systems in ATLAS TI - Anomaly detection with data quality early warning systems in ATLAS UR - http://hdl.handle.net/11427/39703 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/39703
dc.identifier.vancouvercitationMsutwana S. Anomaly detection with data quality early warning systems in ATLAS. []. ,Faculty of Science ,Department of Physics, 2023 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/39703en_ZA
dc.language.rfc3066eng
dc.publisher.departmentDepartment of Physics
dc.publisher.facultyFaculty of Science
dc.subjectPhysics
dc.titleAnomaly detection with data quality early warning systems in ATLAS
dc.typeThesis / Dissertation
dc.type.qualificationlevelMasters
dc.type.qualificationlevelMSc
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
thesis_sci_2023_msutwana senzo.pdf
Size:
9.6 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.72 KB
Format:
Item-specific license agreed upon to submission
Description:
Collections