Improving the Annotation Efficiency for Animal Activity Recognition using Active Learning

Suzanne Spink*, Jacob W. Kamminga, Andreas Kamilaris

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

90 Downloads (Pure)

Abstract

Animal activity recognition (AAR) is essential for the conservation of endangered species and the well-being of livestock. Small resource-constraint devices using inertial measurement units can be attached to animals to automatically classify the performed activities such as running or eating based on their bodily motions. The IMU time-series data is enriched with ground-truth annotations by experts to train artificial intelligence models as classifiers. Annotating AAR data is tedious and time-consuming. Experts that can provide high-quality annotations are scarce and their time is costly. It is difficult for annotators to determine what data is essential to annotate, thus they tend to annotate large amounts of data to improve the performance of the trained classifiers. In this paper, we show that active learning (AL) increases annotation efficiency by selecting only the most informative data for annotation and algorithm training. We use real-world IMU data from four horses performing various activities. We compare five AL-based algorithms (three uncertainty sampling and two disagreement-based sampling (DBS)) with random sampling. Our results show that DBS increases the annotation efficiency, especially when the AAR problem is harder by increasing the number of classified activities from 6 to 8. Furthermore, we show that random sampling can be an effective method to improve annotation efficiency when the AAR task is not too difficult.
Original languageEnglish
Title of host publicationMeasuring Behavior 2022
Subtitle of host publication12th International Conference on Methods and Techniques in Behavioral Research, and 6th Seminar on Behavioral Methods
EditorsAndrew Spink, Jarosław Barski, Anne-Marie Brouwer, Gernot Riedel, Annesha Sil
Pages51-58
Number of pages8
Volume2
ISBN (Electronic)978-90-74821-94-0
DOIs
Publication statusPublished - 18 May 2022
Event12th International Conference on Methods and Techniques in Behavioral Research, MB 2022 - Krakow (Virtual), Poland
Duration: 18 May 202220 May 2022
Conference number: 12
https://www.measuringbehavior.org/

Conference

Conference12th International Conference on Methods and Techniques in Behavioral Research, MB 2022
Abbreviated titleMB 2022
Country/TerritoryPoland
CityKrakow (Virtual)
Period18/05/2220/05/22
Internet address

Keywords

  • Active learning
  • Activity recognition
  • Time series
  • IMU

Fingerprint

Dive into the research topics of 'Improving the Annotation Efficiency for Animal Activity Recognition using Active Learning'. Together they form a unique fingerprint.

Cite this