Automatic Detection of Lemur Behaviors from Accelerometer Data
We study how sensory cues affect group communication and collective behaviors in ring-tailed lemurs. Analyzing large amounts of data manually is time-consuming. Our goal is to create machine learning models that automatically extract and classify relevant information, enhancing researchers' efficiency in data analysis and saving time and resources. The objective of this project is to create machine learning models that can automatically detect animal behaviors using triaxial accelerometers embedded in animal-mounted tags. Triaxial accelerometers measure dynamic output along three axes, allowing for the identification of changes in posture.
- Conducting an extensive literature review to gather and summarize current knowledge and advancements in automatic behavior detection in animals,
- Processing and analyzing ground truth data, which serves as a reference for behavior classification,
- Developing a comprehensive model for the automatic detection and classification of animal behaviors based on the triaxial accelerometer data.
- Preparing a scientific report that presents the project’s findings, methodologies, and results in a clear and concise manner.
- Documenting the developed algorithm and its implementation in a way that enables other researchers and practitioners to utilise it effectively.
Duration and Location:
Although we encourage students to be based in Göttingen, we are open to conducting the analyses and write-up remotely. Additionally, there is a unique opportunity to acquire hands-on data collection skills by participating in tagging and video recording of lemurs at Affenwald Straußberg. The project is anticipated to begin in the summer, yet the exact start time offers some flexibility.
- High motivation to work on an applied project and develop practical solutions.
- Python or R programming
- Machine Learning knowledge (e.g. ML lecture)
To apply please send an email to Dr Kaja Wierucka (email@example.com) and Richard Vogg (firstname.lastname@example.org) stating your interest in this research and detailing your relevant skills. We welcome diversity in all its forms.