Assessment of Machine Learning Models to Identify Port Jackson Shark Behaviours Using Tri-Axial Accelerometers.

Julianna P Kadar,Joanna Day,Brianne Lyall,Culum Brown,Monique A Ladds

doi:10.3390/s20247096

Abstract

Movement ecology has traditionally focused on the movements of animals over large time scales, but, with advancements in sensor technology, the focus can become increasingly fine scale. Accelerometers are commonly applied to quantify animal behaviours and can elucidate fine-scale (<2 s) behaviours. Machine learning methods are commonly applied to animal accelerometry data; however, they require the trial of multiple methods to find an ideal solution. We used tri-axial accelerometers (10 Hz) to quantify four behaviours in Port Jackson sharks (Heterodontus portusjacksoni): two fine-scale behaviours (<2 s)—(1) vertical swimming and (2) chewing as proxy for foraging, and two broad-scale behaviours (>2 s–mins)—(3) resting and (4) swimming. We used validated data to calculate 66 summary statistics from tri-axial accelerometry and assessed the most important features that allowed for differentiation between the behaviours. One and two second epoch testing sets were created consisting of 10 and 20 samples from each behaviour event, respectively. We developed eight machine learning models to assess their overall accuracy and behaviour-specific accuracy (one classification tree, five ensemble learners and two neural networks). The support vector machine model classified the four behaviours better when using the longer 2 s time epoch (F-measure 89%; macro-averaged F-measure: 90%). Here, we show that this support vector machine (SVM) model can reliably classify both fine- and broad-scale behaviours in Port Jackson sharks.

Highlights

Sensors have been applied widely to animals to understand the movements and behaviours of previously unobservable species or events
Chewing and vertical swimming behaviours contained the least number of examples owing to their rare, temporally fine-scale occurrence and difficulty to capture on video footage
As accelerometers continue to be applied and as the technology improves, we stand to gain ever larger datasets that will require the advancement of machine learning techniques

Summary

Introduction

Sensors have been applied widely to animals to understand the movements and behaviours of previously unobservable species or events. We define fine-scale movements as those that occur over very brief periods of time: less than two seconds, and broad-scale behaviours occurring over greater than 2 s to mins. Many of these fine-scale movements have applied significance yet are difficult to observe in wild marine animals without the Sensors 2020, 20, 7096; doi:10.3390/s20247096 www.mdpi.com/journal/sensors. Through identifying and quantifying fine-scale movements, we can increase our understanding of how each movement contributes to individual fitness as well as addressing broader questions such as examining collective species impacts on their surrounding ecosystems [4].

Objectives

Methods

Results

Discussion

Conclusion