Detection of Non-Contemporaneous Activity in an Electronic System Using Unsupervised Machine Learning

Miller, Chris (2023) Detection of Non-Contemporaneous Activity in an Electronic System Using Unsupervised Machine Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Some industries, such as the pharmaceutical industry require their employees to record manufacturing related activities in real-time as imposed by the global regulatory agencies. Deficient electronic system design means that these international requirements can be violated, therefore questioning the integrity of the manufactured products. An external solution is therefore required to identify these non-contemporaneous and therefore anomalous activities.

The objective of this research project is therefore to build an information and communications technology (ICT) solution that can be used to identify these potentially anomalous activities. Synthetic datasets that mimic this use case are initially created as there are no real-world datasets available. These datasets are then used as inputs for the K means clustering (KM), Isolation Forest (IF), Restricted Boltzmann Machines (RBM), and Adaptive Resonance Theory (ART) unsupervised methods, and the statistical methods of the interquartile range (IQR) and Z-score (ZS), to identify potential anomalous activities. The developed models are evaluated, and the best-performing method is integrated into the final ICT solution.

Based on the evaluation of the experiments completed in this research project the RBM method was integrated successfully into the final ICT solution due to its consistent performance and ability to be fine-tuned by the anomaly investigators.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Hasanuzzaman, Mohammed UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HD Industries. Land use. Labor > HD28 Management. Industrial Management > Business Communication Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HD Industries. Land use. Labor > HD28 Management. Industrial Management > Total Quality Management
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	22 May 2023 10:47
Last Modified:	22 May 2023 10:47
URI:	https://norma.ncirl.ie/id/eprint/6619

Actions (login required)

View Item