1
|
Jeantet L, Hadetskyi V, Vigon V, Korysko F, Paranthoen N, Chevallier D. Estimation of the Maternal Investment of Sea Turtles by Automatic Identification of Nesting Behavior and Number of Eggs Laid from a Tri-Axial Accelerometer. Animals (Basel) 2022; 12:ani12040520. [PMID: 35203228 PMCID: PMC8868198 DOI: 10.3390/ani12040520] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2022] [Revised: 02/13/2022] [Accepted: 02/16/2022] [Indexed: 11/16/2022] Open
Abstract
Simple Summary During the reproduction period, female sea turtles come several times onto the beaches to lay their eggs. Monitoring of the nesting populations is therefore important to estimate the state of a population and its future. However, measuring the clutch size and frequency of sea turtles is tedious work that requires rigorous monitoring of the nesting site throughout the breeding season. In order to support the fieldwork, we propose an automatic method to remotely record the behavior on land of the sea turtles from animal-attached sensors; an accelerometer. The proposed method estimates, with an accuracy of 95%, the behaviors on land of sea turtles and the number of eggs laid. This automatic method should therefore help researchers monitor nesting sea turtle populations and contribute to improving global knowledge on the demographic status of these threatened species. Abstract Monitoring reproductive outputs of sea turtles is difficult, as it requires a large number of observers patrolling extended beaches every night throughout the breeding season with the risk of missing nesting individuals. We introduce the first automatic method to remotely record the reproductive outputs of green turtles (Chelonia mydas) using accelerometers. First, we trained a fully convolutional neural network, the V-net, to automatically identify the six behaviors shown during nesting. With an accuracy of 0.95, the V-net succeeded in detecting the Egg laying process with a precision of 0.97. Then, we estimated the number of laid eggs from the predicted Egg laying sequence and obtained the outputs with a mean relative error of 7% compared to the observed numbers in the field. Based on deployment of non-invasive and miniature loggers, the proposed method should help researchers monitor nesting sea turtle populations. Furthermore, its use can be coupled with the deployment of accelerometers at sea during the intra-nesting period, from which behaviors can also be estimated. The knowledge of the behavior of sea turtle on land and at sea during the entire reproduction period is essential to improve our knowledge of this threatened species.
Collapse
Affiliation(s)
- Lorène Jeantet
- Institut Pluridisciplinaire Hubert Curien, CNRS–Unistra, 67087 Strasbourg, France;
- Correspondence:
| | - Vadym Hadetskyi
- UFR Math-Info, Université de Strasbourg, 7 rue Descartes, CEDEX, 67081 Strasbourg, France; (V.H.); (V.V.)
| | - Vincent Vigon
- UFR Math-Info, Université de Strasbourg, 7 rue Descartes, CEDEX, 67081 Strasbourg, France; (V.H.); (V.V.)
| | - François Korysko
- Office Français de la Biodiversité, Direction des Outre-mer, Délégation Guyane, 44 rue Pasteur, BP 10808, 97338 Cayenne, France; (F.K.); (N.P.)
| | - Nicolas Paranthoen
- Office Français de la Biodiversité, Direction des Outre-mer, Délégation Guyane, 44 rue Pasteur, BP 10808, 97338 Cayenne, France; (F.K.); (N.P.)
| | - Damien Chevallier
- Institut Pluridisciplinaire Hubert Curien, CNRS–Unistra, 67087 Strasbourg, France;
- BOREA Research Unit, National Museum of Natural History (MNHN), UMR CNRS 7208, Sorbonne Université, French Institute for Research and Development (IRD 207), University of Caen Normandie, University of Antilles, CEDEX 05, 75231 Paris, France
| |
Collapse
|
2
|
Lauderdale LK, Shorter KA, Zhang D, Gabaldon J, Mellen JD, Walsh MT, Granger DA, Miller LJ. Bottlenose dolphin habitat and management factors related to activity and distance traveled in zoos and aquariums. PLoS One 2021; 16:e0250687. [PMID: 34460858 PMCID: PMC8405030 DOI: 10.1371/journal.pone.0250687] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/26/2020] [Accepted: 04/08/2021] [Indexed: 11/19/2022] Open
Abstract
High-resolution non-invasive cetacean tagging systems can be used to investigate the influence of habitat characteristics and management factors on behavior by quantifying activity levels and distance traveled by bottlenose dolphins (Tursiops truncatus and Tursiops aduncus) in accredited zoos and aquariums. Movement Tags (MTags), a bio-logging device, were used to record a suite of kinematic and environmental information outside of formal training sessions as part of a larger study titled "Towards understanding the welfare of cetaceans in zoos and aquariums" (colloquially called the Cetacean Welfare Study). The purpose of the present study was to explore if and how habitat characteristics, environmental enrichment programs, and training programs were related to the distance traveled and energy expenditure of dolphins in accredited zoos and aquariums. Bottlenose dolphins in accredited zoos and aquariums wore MTags one day per week for two five-week data collection periods. Overall dynamic body acceleration (ODBA), a proxy for energy expenditure, and average distance traveled per hour (ADT) of 60 dolphins in 31 habitats were examined in relation to demographic, habitat, and management factors. Participating facilities were accredited by the Alliance for Marine Mammal Parks and/or Aquariums and the Association of Zoos & Aquariums. Two factors were found to be related to ADT while six factors were associated with ODBA. The results showed that enrichment programs were strongly related to both ODBA and ADT. Scheduling predictable training session times was also positively associated with ADT. The findings suggested that habitat characteristics had a relatively weak association with ODBA and were not related to ADT. In combination, the results suggested that management practices were more strongly related to activity levels than habitat characteristics.
Collapse
Affiliation(s)
- Lisa K. Lauderdale
- Conservation Science and Animal Welfare Research, Chicago Zoological Society – Brookfield Zoo, Brookfield, Illinois, United States of America
| | - K. Alex Shorter
- Department of Mechanical Engineering, University of Michigan, Ann Arbor, Michigan, United States of America
| | - Ding Zhang
- Department of Mechanical Engineering, University of Michigan, Ann Arbor, Michigan, United States of America
| | - Joaquin Gabaldon
- Robotics Institute, University of Michigan, Ann Arbor, Michigan, United States of America
| | - Jill D. Mellen
- Biology Department, Portland State University, Portland, Oregon, United States of America
| | - Michael T. Walsh
- Department of Comparative, Diagnostic & Population Medicine, College of Veterinary Medicine, University of Florida, Gainesville, Florida, United States of America
| | - Douglas A. Granger
- Institute for Interdisciplinary Salivary Bioscience Research, University of California, Irvine, California, United States of America
| | - Lance J. Miller
- Conservation Science and Animal Welfare Research, Chicago Zoological Society – Brookfield Zoo, Brookfield, Illinois, United States of America
| |
Collapse
|
3
|
Brandes S, Sicks F, Berger A. Behaviour Classification on Giraffes ( Giraffa camelopardalis) Using Machine Learning Algorithms on Triaxial Acceleration Data of Two Commonly Used GPS Devices and Its Possible Application for Their Management and Conservation. SENSORS (BASEL, SWITZERLAND) 2021; 21:2229. [PMID: 33806750 PMCID: PMC8005050 DOI: 10.3390/s21062229] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/17/2021] [Revised: 03/15/2021] [Accepted: 03/18/2021] [Indexed: 01/08/2023]
Abstract
Averting today's loss of biodiversity and ecosystem services can be achieved through conservation efforts, especially of keystone species. Giraffes (Giraffa camelopardalis) play an important role in sustaining Africa's ecosystems, but are 'vulnerable' according to the IUCN Red List since 2016. Monitoring an animal's behavior in the wild helps to develop and assess their conservation management. One mechanism for remote tracking of wildlife behavior is to attach accelerometers to animals to record their body movement. We tested two different commercially available high-resolution accelerometers, e-obs and Africa Wildlife Tracking (AWT), attached to the top of the heads of three captive giraffes and analyzed the accuracy of automatic behavior classifications, focused on the Random Forests algorithm. For both accelerometers, behaviors of lower variety in head and neck movements could be better predicted (i.e., feeding above eye level, mean prediction accuracy e-obs/AWT: 97.6%/99.7%; drinking: 96.7%/97.0%) than those with a higher variety of body postures (such as standing: 90.7-91.0%/75.2-76.7%; rumination: 89.6-91.6%/53.5-86.5%). Nonetheless both devices come with limitations and especially the AWT needs technological adaptations before applying it on animals in the wild. Nevertheless, looking at the prediction results, both are promising accelerometers for behavioral classification of giraffes. Therefore, these devices when applied to free-ranging animals, in combination with GPS tracking, can contribute greatly to the conservation of giraffes.
Collapse
Affiliation(s)
- Stefanie Brandes
- Institut für Biochemie und Biologie, University of Potsdam, Am Neuen Palais 10, 14469 Potsdam, Germany;
- Leibniz-Institute for Zoo- and Wildlife Research, Alfred-Kowalke-Straße 17, 10315 Berlin, Germany
| | - Florian Sicks
- Tierpark Berlin-Friedrichsfelde GmbH, Am Tierpark 125, 10319 Berlin, Germany;
| | - Anne Berger
- Leibniz-Institute for Zoo- and Wildlife Research, Alfred-Kowalke-Straße 17, 10315 Berlin, Germany
| |
Collapse
|
4
|
Kadar JP, Ladds MA, Day J, Lyall B, Brown C. Assessment of Machine Learning Models to Identify Port Jackson Shark Behaviours Using Tri-Axial Accelerometers. SENSORS 2020; 20:s20247096. [PMID: 33322308 PMCID: PMC7763149 DOI: 10.3390/s20247096] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/15/2020] [Revised: 12/08/2020] [Accepted: 12/09/2020] [Indexed: 01/08/2023]
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.
Collapse
Affiliation(s)
- Julianna P. Kadar
- Department of Biological Sciences, Faculty of Science and Engineering, Macquarie University, Sydney, NSW 2109, Australia;
- Correspondence:
| | - Monique A. Ladds
- Marine Ecosystems Team, Wellington University, Wellington 6012, New Zealand;
| | - Joanna Day
- Taronga Institute of Science and Learning, Taronga Conservation Society Australia, Sydney, NSW 2088, Australia;
| | - Brianne Lyall
- Royal (Dick) School of Veterinary Studies, The University of Edinburgh, Easter Bush Veterinary Centre, Midlothian EH25 9RG, UK;
| | - Culum Brown
- Department of Biological Sciences, Faculty of Science and Engineering, Macquarie University, Sydney, NSW 2109, Australia;
| |
Collapse
|
5
|
Lyons MP, von Holle B, Caffrey MA, Weishampel JF. Quantifying the impacts of future sea level rise on nesting sea turtles in the southeastern United States. ECOLOGICAL APPLICATIONS : A PUBLICATION OF THE ECOLOGICAL SOCIETY OF AMERICA 2020; 30:e02100. [PMID: 32086969 PMCID: PMC7379276 DOI: 10.1002/eap.2100] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/15/2019] [Revised: 12/19/2019] [Accepted: 01/24/2020] [Indexed: 06/10/2023]
Abstract
Sandy beaches, a necessary habitat for nesting sea turtles, are increasingly under threat as they become squeezed between human infrastructure and shorelines that are changing as a result of rising sea levels. Forecasting where shifting sandy beaches will be obstructed and how that directly impacts coastal nesting species is necessary for successful conservation and management. Predicting changes to coastal nesting areas is difficult because of a lack of consensus on the physical attributes used by females in nesting site choice. In this study, we leveraged long-term data sets of nesting localities for two sea turtle species, loggerhead sea turtle, Caretta caretta, and green sea turtle, Chelonia mydas, within four barrier island National Seashores in the southeastern United States to predict future nesting beach area based on where these species currently nest in relation to mean high water. We predicted the future location of nesting areas based on a sea level rise scenario for 2100 and quantified how impervious surfaces will inhibit future beach movement, which will impact both the total available nesting area and the percentage of nesting area predicted to flood following a hurricane-related storm surge. Contrary to our expectations, those barrier islands with the greatest levels of human infrastructure were not projected to experience the greatest percentage of sea turtle nesting area loss due to sea level rise or storm surge events. Notably, loss of nesting beach areas will not have equal impacts across the four Seashores; the Seashore projected to have the least amount of total nesting area lost and percentage nesting area lost currently has the highest nesting densities of our two study species, suggesting that even low levels of beach loss could have substantial impacts on future nesting densities and disproportionate impacts on the population growth of these species. Our novel method of estimating current and future nesting beach area can be broadly applied to studies requiring a bounded area that encompasses the part of a beach used by nesting coastal species and will be useful in comparing future global nesting densities and population trajectories under projected future sea level rise and storm surge activity.
Collapse
Affiliation(s)
- Marta P. Lyons
- Department of BiologyUniversity of Central FloridaOrlandoFlorida32816USA
| | | | | | - John F. Weishampel
- Department of BiologyUniversity of Central FloridaOrlandoFlorida32816USA
| |
Collapse
|
6
|
DeSantis DL, Mata-Silva V, Johnson JD, Wagler AE. Integrative Framework for Long-Term Activity Monitoring of Small and Secretive Animals: Validation With a Cryptic Pitviper. Front Ecol Evol 2020. [DOI: 10.3389/fevo.2020.00169] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/13/2022] Open
|
7
|
Burns TJ, Thomson RR, McLaren RA, Rawlinson J, McMillan E, Davidson H, Kennedy MW. Buried treasure-marine turtles do not 'disguise' or 'camouflage' their nests but avoid them and create a decoy trail. ROYAL SOCIETY OPEN SCIENCE 2020; 7:200327. [PMID: 32537227 PMCID: PMC7277256 DOI: 10.1098/rsos.200327] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/27/2020] [Accepted: 04/06/2020] [Indexed: 06/11/2023]
Abstract
After laying their eggs and refilling the egg chamber, sea turtles scatter sand extensively around the nest site. This is presumed to camouflage the nest, or optimize local conditions for egg development, but a consensus on its function is lacking. We quantified activity and mapped the movements of hawksbill (Eretmochelys imbricata) and leatherback (Dermochelys coriacea) turtles during sand-scattering. For leatherbacks, we also recorded activity at each sand-scattering position. For hawksbills, we recorded breathing rates during nesting as an indicator of metabolic investment and compared with published values for leatherbacks. Temporal and inferred metabolic investment in sand-scattering was substantial for both species. Neither species remained near the nest while sand-scattering, instead moving to several other positions to scatter sand, changing direction each time, progressively displacing themselves from the nest site. Movement patterns were highly diverse between individuals, but activity at each sand-scattering position changed little between completion of egg chamber refilling and return to the sea. Our findings are inconsistent with sand-scattering being to directly camouflage the nest, or primarily for modifying the nest-proximal environment. Instead, they are consistent with the construction of a series of dispersed decoy nests that may reduce the discovery of nests by predators.
Collapse
|
8
|
Lindborg R, Neidhardt E, Smith JR, Schwartz B, Hernandez V, Savage A, Witherington B. An Ethogram Describing the Nesting Behavior of Green Sea Turtles (Chelonia mydas). HERPETOLOGICA 2019. [DOI: 10.1655/d-18-00015] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Affiliation(s)
- Rebekah Lindborg
- Disney's Animal, Science and Environment, Disney's Animal Kingdomt Theme Park, P.O. Box 10000, Lake Buena Vista, FL 32830, USA
| | - Emily Neidhardt
- Disney's Animal, Science and Environment, Disney's Animal Kingdomt Theme Park, P.O. Box 10000, Lake Buena Vista, FL 32830, USA
| | - J. Rachel Smith
- Disney's Animal, Science and Environment, Disney's Animal Kingdomt Theme Park, P.O. Box 10000, Lake Buena Vista, FL 32830, USA
| | - Benjamin Schwartz
- Disney's Animal, Science and Environment, Disney's Animal Kingdomt Theme Park, P.O. Box 10000, Lake Buena Vista, FL 32830, USA
| | - Vivian Hernandez
- Disney's Animal, Science and Environment, Disney's Animal Kingdomt Theme Park, P.O. Box 10000, Lake Buena Vista, FL 32830, USA
| | - Anne Savage
- Disney's Animal, Science and Environment, Disney's Animal Kingdomt Theme Park, P.O. Box 10000, Lake Buena Vista, FL 32830, USA
| | - Blair Witherington
- Disney's Animal, Science and Environment, Disney's Animal Kingdomt Theme Park, P.O. Box 10000, Lake Buena Vista, FL 32830, USA
| |
Collapse
|
9
|
Salleh SM, Nishizawa H, Ishihara T, Sah SAM, Chowdhury AJK. Importance of Sand Particle Size and Temperature for Nesting Success of Green Turtles in Penang Island, Malaysia. CHELONIAN CONSERVATION AND BIOLOGY 2018. [DOI: 10.2744/ccb-1266.1] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
Affiliation(s)
- Sarahaizad Mohd Salleh
- School of Biological Sciences, Universiti Sains Malaysia, 11800, Penang, Malaysia []
- Center for Marine and Coastal Studies (CEMACS), Universiti Sains Malaysia, 11800, Penang, Malaysia
- Department of Marine Science, Kulliyyah of Science, International Islamic University Malaysia, 25200 Kuantan, Pahang, Malaysia []
| | - Hideaki Nishizawa
- Graduate School of Informatics, Kyoto University, Yoshida Honmachi, Sakyo-ku, Kyoto 606-8501, Japan []
| | | | - Shahrul Anuar Mohd Sah
- School of Biological Sciences, Universiti Sains Malaysia, 11800, Penang, Malaysia []
- Center for Marine and Coastal Studies (CEMACS), Universiti Sains Malaysia, 11800, Penang, Malaysia
| | - Ahmed Jalal Khan Chowdhury
- Department of Marine Science, Kulliyyah of Science, International Islamic University Malaysia, 25200 Kuantan, Pahang, Malaysia []
| |
Collapse
|
10
|
Jeantet L, Dell'Amico F, Forin-Wiart MA, Coutant M, Bonola M, Etienne D, Gresser J, Regis S, Lecerf N, Lefebvre F, de Thoisy B, Le Maho Y, Brucker M, Châtelain N, Laesser R, Crenner F, Handrich Y, Wilson R, Chevallier D. Combined use of two supervised learning algorithms to model sea turtle behaviours from tri-axial acceleration data. ACTA ACUST UNITED AC 2018; 221:jeb.177378. [PMID: 29661804 DOI: 10.1242/jeb.177378] [Citation(s) in RCA: 15] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2018] [Accepted: 04/08/2018] [Indexed: 11/20/2022]
Abstract
Accelerometers are becoming ever more important sensors in animal-attached technology, providing data that allow determination of body posture and movement and thereby helping to elucidate behaviour in animals that are difficult to observe. We sought to validate the identification of sea turtle behaviours from accelerometer signals by deploying tags on the carapace of a juvenile loggerhead (Caretta caretta), an adult hawksbill (Eretmochelys imbricata) and an adult green turtle (Chelonia mydas) at Aquarium La Rochelle, France. We recorded tri-axial acceleration at 50 Hz for each species for a full day while two fixed cameras recorded their behaviours. We identified behaviours from the acceleration data using two different supervised learning algorithms, Random Forest and Classification And Regression Tree (CART), treating the data from the adult animals as separate from the juvenile data. We achieved a global accuracy of 81.30% for the adult hawksbill and green turtle CART model and 71.63% for the juvenile loggerhead, identifying 10 and 12 different behaviours, respectively. Equivalent figures were 86.96% for the adult hawksbill and green turtle Random Forest model and 79.49% for the juvenile loggerhead, for the same behaviours. The use of Random Forest combined with CART algorithms allowed us to understand the decision rules implicated in behaviour discrimination, and thus remove or group together some 'confused' or under--represented behaviours in order to get the most accurate models. This study is the first to validate accelerometer data to identify turtle behaviours and the approach can now be tested on other captive sea turtle species.
Collapse
Affiliation(s)
- L Jeantet
- DEPE-IPHC, UMR 7178, CNRS, 23 rue Becquerel, 67087 Strasbourg cedex 2, France
| | - F Dell'Amico
- Aquarium La Rochelle, quai Louis Prunier, 17000 La Rochelle, France
| | - M-A Forin-Wiart
- DEPE-IPHC, UMR 7178, CNRS, 23 rue Becquerel, 67087 Strasbourg cedex 2, France
| | - M Coutant
- Aquarium La Rochelle, quai Louis Prunier, 17000 La Rochelle, France
| | - M Bonola
- DEPE-IPHC, UMR 7178, CNRS, 23 rue Becquerel, 67087 Strasbourg cedex 2, France
| | - D Etienne
- Direction de l'Environnement, de l'Aménagement et du Logement Martinique, BP 7217, 97274 Schoelcher cedex, Martinique
| | - J Gresser
- Office de l'Eau Martinique, 7 avenue Condorcet, BP 32, 97201 Fort-de-France, Martinique
| | - S Regis
- DEPE-IPHC, UMR 7178, CNRS, 23 rue Becquerel, 67087 Strasbourg cedex 2, France
| | - N Lecerf
- DEPE-IPHC, UMR 7178, CNRS, 23 rue Becquerel, 67087 Strasbourg cedex 2, France
| | - F Lefebvre
- DEPE-IPHC, UMR 7178, CNRS, 23 rue Becquerel, 67087 Strasbourg cedex 2, France
| | - B de Thoisy
- Institut Pasteur de la Guyane, 23 avenue Pasteur, BP 6010, Cayenne cedex, Guyane
| | - Y Le Maho
- DEPE-IPHC, UMR 7178, CNRS, 23 rue Becquerel, 67087 Strasbourg cedex 2, France
| | - M Brucker
- DEPE-IPHC, UMR 7178, CNRS, 23 rue Becquerel, 67087 Strasbourg cedex 2, France
| | - N Châtelain
- DEPE-IPHC, UMR 7178, CNRS, 23 rue Becquerel, 67087 Strasbourg cedex 2, France
| | - R Laesser
- DEPE-IPHC, UMR 7178, CNRS, 23 rue Becquerel, 67087 Strasbourg cedex 2, France
| | - F Crenner
- DEPE-IPHC, UMR 7178, CNRS, 23 rue Becquerel, 67087 Strasbourg cedex 2, France
| | - Y Handrich
- DEPE-IPHC, UMR 7178, CNRS, 23 rue Becquerel, 67087 Strasbourg cedex 2, France
| | - R Wilson
- Biological Sciences, Institute of Environmental Sustainability, Swansea University, Swansea SA2 8PP, UK
| | - D Chevallier
- DEPE-IPHC, UMR 7178, CNRS, 23 rue Becquerel, 67087 Strasbourg cedex 2, France
| |
Collapse
|
11
|
Sur M, Suffredini T, Wessells SM, Bloom PH, Lanzone M, Blackshire S, Sridhar S, Katzner T. Improved supervised classification of accelerometry data to distinguish behaviors of soaring birds. PLoS One 2017; 12:e0174785. [PMID: 28403159 PMCID: PMC5389810 DOI: 10.1371/journal.pone.0174785] [Citation(s) in RCA: 19] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2016] [Accepted: 03/15/2017] [Indexed: 12/04/2022] Open
Abstract
Soaring birds can balance the energetic costs of movement by switching between flapping, soaring and gliding flight. Accelerometers can allow quantification of flight behavior and thus a context to interpret these energetic costs. However, models to interpret accelerometry data are still being developed, rarely trained with supervised datasets, and difficult to apply. We collected accelerometry data at 140Hz from a trained golden eagle (Aquila chrysaetos) whose flight we recorded with video that we used to characterize behavior. We applied two forms of supervised classifications, random forest (RF) models and K-nearest neighbor (KNN) models. The KNN model was substantially easier to implement than the RF approach but both were highly accurate in classifying basic behaviors such as flapping (85.5% and 83.6% accurate, respectively), soaring (92.8% and 87.6%) and sitting (84.1% and 88.9%) with overall accuracies of 86.6% and 92.3% respectively. More detailed classification schemes, with specific behaviors such as banking and straight flights were well classified only by the KNN model (91.24% accurate; RF = 61.64% accurate). The RF model maintained its accuracy of classifying basic behavior classification accuracy of basic behaviors at sampling frequencies as low as 10Hz, the KNN at sampling frequencies as low as 20Hz. Classification of accelerometer data collected from free ranging birds demonstrated a strong dependence of predicted behavior on the type of classification model used. Our analyses demonstrate the consequence of different approaches to classification of accelerometry data, the potential to optimize classification algorithms with validated flight behaviors to improve classification accuracy, ideal sampling frequencies for different classification algorithms, and a number of ways to improve commonly used analytical techniques and best practices for classification of accelerometry data.
Collapse
Affiliation(s)
- Maitreyi Sur
- Department of Biological Sciences, Boise State University, Boise, Idaho, United States of America
- * E-mail:
| | - Tony Suffredini
- Sky Patrol Abatement, Simi Valley, California, United States of America
| | - Stephen M. Wessells
- U.S. Geological Survey Henderson, Henderson, Nevada, United States of America
| | - Peter H. Bloom
- Bloom Biological, Santa Ana, California, United States of America
| | - Michael Lanzone
- Cellular Tracking Technologies, Rio Grande, New Jersey, United States of America
| | - Sheldon Blackshire
- Cellular Tracking Technologies, Rio Grande, New Jersey, United States of America
| | - Srisarguru Sridhar
- Department of Computer Science, Boise State University, Boise, Idaho, United States of America
| | - Todd Katzner
- U.S. Geological Survey, Forest and Rangeland Ecosystem Science Center, Boise, Idaho, United States of America
| |
Collapse
|
12
|
Ladds MA, Thompson AP, Slip DJ, Hocking DP, Harcourt RG. Seeing It All: Evaluating Supervised Machine Learning Methods for the Classification of Diverse Otariid Behaviours. PLoS One 2016; 11:e0166898. [PMID: 28002450 PMCID: PMC5176164 DOI: 10.1371/journal.pone.0166898] [Citation(s) in RCA: 22] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2016] [Accepted: 11/04/2016] [Indexed: 12/02/2022] Open
Abstract
Constructing activity budgets for marine animals when they are at sea and cannot be directly observed is challenging, but recent advances in bio-logging technology offer solutions to this problem. Accelerometers can potentially identify a wide range of behaviours for animals based on unique patterns of acceleration. However, when analysing data derived from accelerometers, there are many statistical techniques available which when applied to different data sets produce different classification accuracies. We investigated a selection of supervised machine learning methods for interpreting behavioural data from captive otariids (fur seals and sea lions). We conducted controlled experiments with 12 seals, where their behaviours were filmed while they were wearing 3-axis accelerometers. From video we identified 26 behaviours that could be grouped into one of four categories (foraging, resting, travelling and grooming) representing key behaviour states for wild seals. We used data from 10 seals to train four predictive classification models: stochastic gradient boosting (GBM), random forests, support vector machine using four different kernels and a baseline model: penalised logistic regression. We then took the best parameters from each model and cross-validated the results on the two seals unseen so far. We also investigated the influence of feature statistics (describing some characteristic of the seal), testing the models both with and without these. Cross-validation accuracies were lower than training accuracy, but the SVM with a polynomial kernel was still able to classify seal behaviour with high accuracy (>70%). Adding feature statistics improved accuracies across all models tested. Most categories of behaviour -resting, grooming and feeding—were all predicted with reasonable accuracy (52–81%) by the SVM while travelling was poorly categorised (31–41%). These results show that model selection is important when classifying behaviour and that by using animal characteristics we can strengthen the overall accuracy.
Collapse
Affiliation(s)
- Monique A. Ladds
- Marine Predator Research Group, Department of Biological Sciences, Macquarie University, North Ryde, New South Wales, Australia
- * E-mail:
| | - Adam P. Thompson
- Digital Network, Australian Broadcasting Corporation (ABC), Sydney, New South Wales, Australia
| | - David J. Slip
- Marine Predator Research Group, Department of Biological Sciences, Macquarie University, North Ryde, New South Wales, Australia
- Taronga Conservation Society Australia, Bradley's Head Road, Mosman, New South Wales, Australia
| | - David P. Hocking
- School of Biological Sciences, Monash University, Melbourne, Australia
- Geosciences, Museum Victoria, Melbourne, Australia
| | - Robert G. Harcourt
- Marine Predator Research Group, Department of Biological Sciences, Macquarie University, North Ryde, New South Wales, Australia
| |
Collapse
|
13
|
Graf PM, Wilson RP, Qasem L, Hackländer K, Rosell F. The Use of Acceleration to Code for Animal Behaviours; A Case Study in Free-Ranging Eurasian Beavers Castor fiber. PLoS One 2015; 10:e0136751. [PMID: 26317623 PMCID: PMC4552556 DOI: 10.1371/journal.pone.0136751] [Citation(s) in RCA: 56] [Impact Index Per Article: 6.2] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/19/2015] [Accepted: 08/07/2015] [Indexed: 11/18/2022] Open
Abstract
Recent technological innovations have led to the development of miniature, accelerometer-containing electronic loggers which can be attached to free-living animals. Accelerometers provide information on both body posture and dynamism which can be used as descriptors to define behaviour. We deployed tri-axial accelerometer loggers on 12 free-ranging Eurasian beavers Castor fiber in the county of Telemark, Norway, and on four captive beavers (two Eurasian beavers and two North American beavers C. canadensis) to corroborate acceleration signals with observed behaviours. By using random forests for classifying behavioural patterns of beavers from accelerometry data, we were able to distinguish seven behaviours; standing, walking, swimming, feeding, grooming, diving and sleeping. We show how to apply the use of acceleration to determine behaviour, and emphasise the ease with which this non-invasive method can be implemented. Furthermore, we discuss the strengths and weaknesses of this, and the implementation of accelerometry on animals, illustrating limitations, suggestions and solutions. Ultimately, this approach may also serve as a template facilitating studies on other animals with similar locomotor modes and deliver new insights into hitherto unknown aspects of behavioural ecology.
Collapse
Affiliation(s)
- Patricia M. Graf
- Faculty of Arts and Sciences, Department of Environmental Sciences, Telemark University College, Bø i Telemark, Norway
- Department of Integrative Biology and Biodiversity Research, Institute of Wildlife Biology and Game Management, University of Natural Resources and Life Sciences, Vienna, Vienna, Austria
- * E-mail:
| | - Rory P. Wilson
- Swansea Moving Animal Research Team, Biosciences, College of Science, Swansea University, Singleton Park, Swansea, Wales, United Kingdom
| | - Lama Qasem
- Swansea Moving Animal Research Team, Biosciences, College of Science, Swansea University, Singleton Park, Swansea, Wales, United Kingdom
| | - Klaus Hackländer
- Department of Integrative Biology and Biodiversity Research, Institute of Wildlife Biology and Game Management, University of Natural Resources and Life Sciences, Vienna, Vienna, Austria
| | - Frank Rosell
- Faculty of Arts and Sciences, Department of Environmental Sciences, Telemark University College, Bø i Telemark, Norway
| |
Collapse
|
14
|
Bom RA, Bouten W, Piersma T, Oosterbeek K, van Gils JA. Optimizing acceleration-based ethograms: the use of variable-time versus fixed-time segmentation. MOVEMENT ECOLOGY 2014; 2:6. [PMID: 25520816 PMCID: PMC4267607 DOI: 10.1186/2051-3933-2-6] [Citation(s) in RCA: 19] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/16/2014] [Accepted: 03/11/2014] [Indexed: 05/10/2023]
Abstract
BACKGROUND Animal-borne accelerometers measure body orientation and movement and can thus be used to classify animal behaviour. To univocally and automatically analyse the large volume of data generated, we need classification models. An important step in the process of classification is the segmentation of acceleration data, i.e. the assignment of the boundaries between different behavioural classes in a time series. So far, analysts have worked with fixed-time segments, but this may weaken the strength of the derived classification models because transitions of behaviour do not necessarily coincide with boundaries of the segments. Here we develop random forest automated supervised classification models either built on variable-time segments generated with a so-called 'change-point model', or on fixed-time segments, and compare for eight behavioural classes the classification performance. The approach makes use of acceleration data measured in eight free-ranging crab plovers Dromas ardeola. RESULTS Useful classification was achieved by both the variable-time and fixed-time approach for flying (89% vs. 91%, respectively), walking (88% vs. 87%) and body care (68% vs. 72%). By using the variable-time segment approach, significant gains in classification performance were obtained for inactive behaviours (95% vs. 92%) and for two major foraging activities, i.e. handling (84% vs. 77%) and searching (78% vs. 67%). Attacking a prey and pecking were never accurately classified by either method. CONCLUSION Acceleration-based behavioural classification can be optimized using a variable-time segmentation approach. After implementing variable-time segments to our sample data, we achieved useful levels of classification performance for almost all behavioural classes. This enables behaviour, including motion, to be set in known spatial contexts, and the measurement of behavioural time-budgets of free-living birds with unprecedented coverage and precision. The methods developed here can be easily adopted in other studies, but we emphasize that for each species and set of questions, the presented string of work steps should be run through.
Collapse
Affiliation(s)
- Roeland A Bom
- />Department of Marine Ecology, Royal Netherlands Institute for Sea Research (NIOZ), 1790 AB Den Burg, P.O. Box 59, Texel, The Netherlands
| | - Willem Bouten
- />Computational Geo-Ecology, Institute for Biodiversity and Ecosystem Dynamics (IBED), University of Amsterdam, P.O. Box 94248, 1090 GE Amsterdam, The Netherlands
| | - Theunis Piersma
- />Department of Marine Ecology, Royal Netherlands Institute for Sea Research (NIOZ), 1790 AB Den Burg, P.O. Box 59, Texel, The Netherlands
- />Chair in Global Flyway Ecology, Animal Ecology Group, Centre for Ecological and Evolutionary Studies, University of Groningen, PO Box 11103, 9700 CC Groningen, The Netherlands
| | - Kees Oosterbeek
- />SOVON Dutch Centre for Field Ornithology, Coastal Ecology Team, 1790 AB Den Burg, Texel, The Netherlands
| | - Jan A van Gils
- />Department of Marine Ecology, Royal Netherlands Institute for Sea Research (NIOZ), 1790 AB Den Burg, P.O. Box 59, Texel, The Netherlands
| |
Collapse
|