Assessing the use of machine learning for monitoring baboon raiding behaviours. Photo Credit: Gaëlle Fehlmann.
While undertaking my Master's of Research at Swansea University I was a member of the SHOAL Group and my thesis ("The applicability of animal-attached tri-axial accelerometers and machine learning techniques for inferring the behaviour of wild social primates") explored the use of remote sensing (namely the accelerometer) in the automated classification of behaviours in the Chacma Baboon. Here I annotated footage of the wild population of baboons, identified a range of potentially informative behaviours, and assessed the utility of a diverse number of machine learning algorithms in the accurate and reliable classification of these behaviours.
Baboon diagram and photo. Photo Credit: Gaëlle Fehlmann.
This work formed a foundation which was then further refined by the SHOAL group team (particularly the PhD student whose project it was: Dr. Gaelle Fehlmann) after the completion of my masters. The paper resulting from this (Fehlmann et al., 2017) presents a validated end-to-end methodology for the use of collar-mounted accelerometers, alongside random forest models of classification, for the remote identification of baboon behaviours. This method is presented in detail to inspire future work exploring novel questions of primate behavioural ecology without requiring extensive, disruptive observation, handling and/or habituation of wild primates. The works' focus on grooming behaviours underlines the potential of this, and similar methods, for the future assessment of social interactions and networks within groups. This adds to a wealth of literature exploring the exciting prospect of the use of diverse biotelemetry sensors and methodologies to capture longitudinal datasets that could better allow researchers the ability to model complex social group interactions, roles, and decision making.
Background: The use of accelerometers in bio-logging devices has proved to be a powerful tool for the quantification of animal behaviour. While bio-logging techniques are being used on wide range of species, to date they have only been seldom used with non-human primates. This is likely due to three main factors: the long tradition of direct field observations, a difficulty of attaching bio-logging devices to wild primates and the challenge of deciphering acceleration signals in species’ with remarkable locomotor and behavioural diversity. Here, we overcome these aforementioned obstacles and provide methodology for identification of behaviours from accelerometer data of wild chacma baboons (Papio ursinus) in Cape Town, South Africa. Results: We apply machine learning techniques to process complex accelerometer data, collected by bespoke tracking collars to quantify a range of behaviours (focusing on locomotion and foraging behaviour). We successfully identify six broad state behaviours that represent 93.3% of the time budget of the baboons. Resting, walking, running and foraging were all identified with high recall and precision representing the first classification of multiple behavioural states from accelerometer data for a wild primate. Conclusion: Our ‘end to end’ process—from collar design and build to the collection and quantification of acceleration data—provides advantages over gathering data by traditional observation, not least because it affords data collection without the presence of an observer which may affect an animal’s behaviour. Furthermore, our methodology and findings open new possibilities for the fine-scale study of movement and foraging ecology in wild primates, and in particular our baboon study population which is in conflict with people.
@article{fehlmann2017identification,title={Identification of behaviours from accelerometer data in a wild social primate},author={Fehlmann, Gaelle and O’Riain, M Justin and Hopkins, Phil W and O’Sullivan, Jack and Holton, Mark D and Shepard, Emily LC and King, Andrew J},journal={Animal Biotelemetry},volume={5},pages={1--11},year={2017},publisher={BioMed Central},doi={10.1186/s40317-017-0121-3},url={https://doi.org/10.1186/s40317-017-0121-3},dimensions={true},}
