Assessment of Machine Learning Models to Identify Port Jackson Shark Behaviours Using Tri-Axial Accelerometers
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) behaviour...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/24/7096 |
| _version_ | 1797545049084395520 |
|---|---|
| author | Julianna P. Kadar Monique A. Ladds Joanna Day Brianne Lyall Culum Brown |
| author_facet | Julianna P. Kadar Monique A. Ladds Joanna Day Brianne Lyall Culum Brown |
| author_sort | Julianna P. Kadar |
| collection | DOAJ |
| description | 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 (<i>Heterodontus portusjacksoni</i>): 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 (<i>F</i>-measure 89%; macro-averaged <i>F</i>-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. |
| first_indexed | 2024-03-10T14:10:07Z |
| format | Article |
| id | doaj.art-cd4463a0c1c2454dbc78b1fe28773b9b |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T14:10:07Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-cd4463a0c1c2454dbc78b1fe28773b9b2023-11-21T00:19:48ZengMDPI AGSensors1424-82202020-12-012024709610.3390/s20247096Assessment of Machine Learning Models to Identify Port Jackson Shark Behaviours Using Tri-Axial AccelerometersJulianna P. Kadar0Monique A. Ladds1Joanna Day2Brianne Lyall3Culum Brown4Department of Biological Sciences, Faculty of Science and Engineering, Macquarie University, Sydney, NSW 2109, AustraliaMarine Ecosystems Team, Wellington University, Wellington 6012, New ZealandTaronga Institute of Science and Learning, Taronga Conservation Society Australia, Sydney, NSW 2088, AustraliaRoyal (Dick) School of Veterinary Studies, The University of Edinburgh, Easter Bush Veterinary Centre, Midlothian EH25 9RG, UKDepartment of Biological Sciences, Faculty of Science and Engineering, Macquarie University, Sydney, NSW 2109, AustraliaMovement 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 (<i>Heterodontus portusjacksoni</i>): 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 (<i>F</i>-measure 89%; macro-averaged <i>F</i>-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.https://www.mdpi.com/1424-8220/20/24/7096machine learningaccelerometermodel selectionbenthicelasmobranchepoch |
| spellingShingle | Julianna P. Kadar Monique A. Ladds Joanna Day Brianne Lyall Culum Brown Assessment of Machine Learning Models to Identify Port Jackson Shark Behaviours Using Tri-Axial Accelerometers Sensors machine learning accelerometer model selection benthic elasmobranch epoch |
| title | Assessment of Machine Learning Models to Identify Port Jackson Shark Behaviours Using Tri-Axial Accelerometers |
| title_full | Assessment of Machine Learning Models to Identify Port Jackson Shark Behaviours Using Tri-Axial Accelerometers |
| title_fullStr | Assessment of Machine Learning Models to Identify Port Jackson Shark Behaviours Using Tri-Axial Accelerometers |
| title_full_unstemmed | Assessment of Machine Learning Models to Identify Port Jackson Shark Behaviours Using Tri-Axial Accelerometers |
| title_short | Assessment of Machine Learning Models to Identify Port Jackson Shark Behaviours Using Tri-Axial Accelerometers |
| title_sort | assessment of machine learning models to identify port jackson shark behaviours using tri axial accelerometers |
| topic | machine learning accelerometer model selection benthic elasmobranch epoch |
| url | https://www.mdpi.com/1424-8220/20/24/7096 |
| work_keys_str_mv | AT juliannapkadar assessmentofmachinelearningmodelstoidentifyportjacksonsharkbehavioursusingtriaxialaccelerometers AT moniquealadds assessmentofmachinelearningmodelstoidentifyportjacksonsharkbehavioursusingtriaxialaccelerometers AT joannaday assessmentofmachinelearningmodelstoidentifyportjacksonsharkbehavioursusingtriaxialaccelerometers AT briannelyall assessmentofmachinelearningmodelstoidentifyportjacksonsharkbehavioursusingtriaxialaccelerometers AT culumbrown assessmentofmachinelearningmodelstoidentifyportjacksonsharkbehavioursusingtriaxialaccelerometers |