Using accelerometers to remotely and automatically characterize behavior in small animals

ABSTRACT Activity budgets in wild animals are challenging to measure via direct observation because data collection is time consuming and observer effects are potentially confounding. Although tri-axial accelerometers are increasingly employed for this purpose, their application in small-bodied animals has been limited by weight restrictions. Additionally, accelerometers engender novel complications, as a system is needed to reliably map acceleration to behaviors. In this study, we describe newly developed, tiny acceleration-logging devices (1.5–2.5 g) and use them to characterize behavior in two chipmunk species. We collected paired accelerometer readings and behavioral observations from captive individuals. We then employed techniques from machine learning to develop an automatic system for coding accelerometer readings into behavioral categories. Finally, we deployed and recovered accelerometers from free-living, wild chipmunks. This is the first time to our knowledge that accelerometers have been used to generate behavioral data for small-bodied (<100 g), free-living mammals. Summary: Validation of the use of accelerometers for automated collection of behavioral data from two species of small-bodied, free-living animals.

[1]  B. Bahnak,et al.  The influence of environmental temperature and photoperiod on activity in the red squirrel,Tamiasciurus hudsonicus , 1977 .

[2]  Matthew Rutishauser,et al.  Movement, resting, and attack behaviors of wild pumas are revealed by tri-axial accelerometer measurements , 2015, Movement ecology.

[3]  Jane Hunter,et al.  Creating a behavioural classification module for acceleration data: using a captive surrogate for difficult to observe species , 2013, Journal of Experimental Biology.

[4]  Ben Taskar,et al.  Learning structured prediction models: a large margin approach , 2005, ICML.

[5]  Michael Scantlebury,et al.  Tri-axial accelerometers quantify behaviour in the Eurasian badger (Meles meles): towards an automated interpretation of field data , 2014, Animal Biotelemetry.

[6]  S. Wanless,et al.  Can Ethograms Be Automatically Generated Using Body Acceleration Data from Free-Ranging Birds? , 2009, PloS one.

[7]  E. V. van Loon,et al.  From Sensor Data to Animal Behaviour: An Oystercatcher Example , 2012, PloS one.

[8]  J. L. Parra,et al.  Impact of a Century of Climate Change on Small-Mammal Communities in Yosemite National Park, USA , 2008, Science.

[9]  Orr Spiegel,et al.  AcceleRater: a web application for supervised learning of behavioral modes from acceleration measurements , 2014, Movement ecology.

[10]  L. Wauters,et al.  Activity budget and foraging behaviour of red squirrels ( Sciurus vulgaris ) in coniferous and deciduous habitats , 1992 .

[11]  Stephen E. Levinson,et al.  Continuously variable duration hidden Markov models for automatic speech recognition , 1986 .

[12]  Christopher C Wilmers,et al.  The golden age of bio-logging: how animal-borne sensors are advancing the frontiers of ecology. , 2015, Ecology.

[13]  Dan Klein,et al.  An Empirical Analysis of Optimization for Max-Margin NLP , 2015, EMNLP.

[14]  D. Randall,et al.  Eckert Animal Physiology: Mechanisms and Adaptations , 1997 .

[15]  T. Poulson.  Altitudinal Zonation of Chipmunks (Eutamias): Adaptations to Aridity and High Temperature' , 1972 .

[16]  R. Palme,et al.  Contrasting stress responses of two co-occurring chipmunk species (Tamias alpinus and T. speciosus). , 2015, General and comparative endocrinology.

[17]  Jane Hunter,et al.  A Web-based semantic tagging and activity recognition system for species' accelerometry data , 2013, Ecol. Informatics.

[18]  R. Sikes,et al.  Guidelines of the American Society of Mammalogists for the Use of Wild Mammals in Research , 2007 .

[19]  Frederick Jelinek,et al.  Statistical methods for speech recognition , 1997 .

[20]  Katsufumi Sato,et al.  Ocean sunfish rewarm at the surface after deep excursions to forage for siphonophores. , 2015, The Journal of animal ecology.

[21]  Cécile Cornou,et al.  Sow-activity classification from acceleration patterns: A machine learning approach , 2013 .

[22]  John Shawe-Taylor,et al.  Movement Activity Based Classification of Animal Behaviour with an Application to Data from Cheetah (Acinonyx jubatus) , 2012, PloS one.

[23]  Ian Jonsen,et al.  Supervised accelerometry analysis can identify prey capture by penguins at sea , 2014, Journal of Experimental Biology.

[24]  L. Fuiman,et al.  Hunting behavior of a marine mammal beneath the antarctic fast Ice , 1999, Science.

[25]  J. L. Parra,et al.  The role of climate, habitat, and species co‐occurrence as drivers of change in small mammal distributions over the past century , 2011 .

[26]  Dwight Springthorpe,et al.  Increased activity correlates with reduced ability to mount immune defenses to endotoxin in zebra finches. , 2014, Journal of experimental zoology. Part A, Ecological genetics and physiology.

[27]  Thomas Hofmann,et al.  Support vector machine learning for interdependent and structured output spaces , 2004, ICML.

[28]  R. Kays,et al.  Terrestrial animal tracking as an eye on life and planet , 2015, Science.

[29]  K. R. Kramm,et al.  Photoperiodic control of circadian activity rhythms in diurnal rodents , 1980, International journal of biometeorology.

[30]  M. Kolehmainen,et al.  Cow behaviour pattern recognition using a three-dimensional accelerometer and support vector machines , 2009 .

[31]  M. C. Ferrari,et al.  Evolution and behavioural responses to human-induced rapid environmental change , 2011, Evolutionary applications.

[32]  Rory P. Wilson,et al.  Love Thy Neighbour: Automatic Animal Behavioural Classification of Acceleration Data Using the K-Nearest Neighbour Algorithm , 2014, PloS one.

[33]  L. Dubroca,et al.  Slowness and acceleration: a new method to quantify the activity budget of chelonians , 2008, Animal Behaviour.

[34]  Ran Nathan,et al.  Using tri-axial acceleration data to identify behavioral modes of free-ranging animals: general concepts and tools illustrated for griffon vultures , 2012, Journal of Experimental Biology.

[35]  Y. Ropert‐Coudert,et al.  The three-dimensional flight of red-footed boobies: adaptations to foraging in a tropical environment? , 2005, Proceedings of the Royal Society B: Biological Sciences.

[36]  Roland Kays,et al.  Observing the unwatchable through acceleration logging of animal behavior , 2013, Animal Biotelemetry.