University of Twente Student Theses


Smart Labelling

Spink, Suzanne J. (2021) Smart Labelling.

[img] PDF
Abstract:The AL algorithm is potentially much more cost-efficient and less time-consuming when labelling activities than with supervised learning. However, AL has only been applied to animal activity recognition (AAR) in a limited fashion. This thesis investigates the potential role active learning can play in the field of AAR, by finding the AL strategy which is the quickest in converging to the most adept performance for AAR. This is done by applying three uncertainty sampling algorithms and two disagreement based sampling algorithms to a DNN classifier, namely least certain, margin, uncertainty entropy, consensus entropy, and maximum disagreement. Comparing these to each other showed favouritism towards using least confident or maximum disagreement for their respective divisions. However, the differences were minor, where a bigger factor was the impact the initial training set sizes had and how many times the oracle was queried iteratively. For this data set, the optimal size was at 350 with an additional 18 iterations. This showed the great potential of AL over supervised learning, where it used 81 332 points previously, all manually annotated. Using AL, this would have saved a person more than a month in labelling time. However, the performance is lower.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Creative Technology BSc (50447)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page