Prying into the intimate secrets of animal lives; software beyond hardware for comprehensive annotation in ‘Daily Diary’ tags

Walker, James S.; Jones, Mark W.; Laramee, Robert S.; Holton, Mark D.; Shepard, Emily L. C.; Williams, Hannah J.; Scantlebury, David; Marks, Nikki J.; Magowan, Elizabeth; Maguire, I. E.; Bidder, Owen R.; Virgilio, Agustina di; Wilson, Rory P.

doi:10.1186/s40462-015-0056-3

Cited by 60 publications

(90 citation statements)

References 45 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1a) Ten adult males were fitted with SHOAL group in-house constructed collars (F2HKv2 collars, see Additional file 2, Baboon collar development). Each collar contained a triaxial accelerometer ('Daily Diary' sensor [31]) recording acceleration in each axis at 40 Hz which allows for the study of behaviours of most terrestrial animals whose fastest movements range between 0.5 s to 1 s. Baboons were cage-trapped in accordance with the local 'baboon management team'-approved protocol before being sedated by a certified veterinary surgeon and fitted with the collar. Collars weighed less than 3% of the body mass of the baboons and were approved for use by Swansea University Ethics Committee (Swansea University IP-1314-5).…”

Section: Study Site and Subjectsmentioning

confidence: 99%

“…1c) Footage was time-stamped to allow synchronisation with the accelerometer, and the signal was annotated using Framework4 [31]. We labelled behaviours at time steps of one second, relevant for most behaviours (mean duration of one behavioural bout (±SD) = 33 s ± 62 s, median = 12 s) [22,34], leading to a sample size of 33,619 s. This created a dataset with n = 18 labelled behaviours (Tables 1, 2) for a total of 9.3 h. All rare behaviours with less than 100 s of observations (representing in total 7.3% of their time budget) were discarded from further analysis, bringing the labelled sample down to 33,387 s, i.e.…”

Section: Video Data (Fig 1b)mentioning

confidence: 99%

“…This is particularly pertinent for datasets that extend over weeks or even months, which are typically extremely large. To infer behaviour from acceleration data, researchers manually annotate the signal by expert interpretation [3], or 'label' behaviours in the acceleration signals, ideally using time-matched behavioural observation, to teach machine learning algorithms [29][30][31]. The broad approaches can be applied across taxa, although the specific selection of variables is likely to vary with and reflect characteristic movement modes, behavioural categories and habitat types of a particular species or population.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Identification of behaviours from accelerometer data in a wild social primate

O’Riain²,

et al. 2017

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Study Site and Subjectsmentioning

confidence: 99%

Section: Video Data (Fig 1b)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identification of behaviours from accelerometer data in a wild social primate

O’Riain²,

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…Machine-learning algorithms [16,39,40], clustering techniques [41] and normalised correlation [42] have been used to identify behaviour from acceleration data in a range of species. Here, we used the k-nearest neighbour (KNN) cluster analysis to investigate the ability of such automated classification methods to distinguish between the four flight types with raw acceleration data alone.…”

Section: Classification By Accelerationmentioning

confidence: 99%

Can accelerometry be used to distinguish between flight types in soaring birds?

et al. 2015

View full text Add to dashboard Cite

Background: Accelerometry has been used to identify behaviours through the quantification of body posture and motion for a range of species moving in different media. This technique has not been applied to flight behaviours to the same degree, having only been used to distinguish flapping from soaring flight, even though identifying the type of soaring flight could provide important insights into the factors underlying movement paths in soaring birds. This may be due to the complexities of interpreting acceleration data, as movement in the aerial environment may be influenced by phenomena such as centripetal acceleration (pulling-g). This study used high-resolution movement data on the flight of free-living Andean condors (Vultur gryphus) and a captive Eurasian griffon vulture (Gyps fulvus) to examine the influence of gravitational, dynamic and centripetal acceleration in different flight types. Flight behaviour was categorised as thermal soaring, slope soaring, gliding and flapping, using changes in altitude and heading from magnetometry data. We examined the ability of the k-nearest neighbour (KNN) algorithm to distinguish between these behaviours using acceleration data alone. Results:Values of the vectorial static body acceleration (VeSBA) suggest that these birds experience relatively little centripetal acceleration in flight, though this varies between flight types. Centripetal acceleration appears to be of most influence during thermal soaring; consequently, it is not possible to derive bank angle from smoothed values of lateral acceleration. In contrast, the smoothed acceleration values in the dorso-ventral axis provide insight into body pitch, which varied linearly with airspeed. Classification of passive flight types via KNN was limited, with low accuracy and precision for soaring and gliding. Conclusion:The importance of soaring was evident in the high proportion of time each bird spent in this flight mode (52.17-84.00 %). Accelerometry alone was limited in its ability to distinguish between passive flight types, though smoothed values in the dorso-ventral axis did vary with airspeed. Other sensors, in particular the magnetometer, provided powerful methods of identifying flight behaviour and these data may be better suited for automated behavioural identification. This should provide further insight into the type and strength of updraughts available to soaring birds.

show abstract

“…Eight months of Bryce's research readings, taken at the rate of 32 per second, have added up to terabytes of data and require supercomputers for analysis, he says. Scientists have resorted to various means to interpret such massive datasets, aiming to identify animal energy expenditure and associated behaviors (4)(5)(6).…”

Section: Careful Correlationmentioning

confidence: 99%

SMART collars help track and conserve wildlife

Willoughby¹

2017

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

Caleb Bryce drops into a ravine and tucks into the shadows. The dry foliage bursts into confetti as a puma careens up the opposite bank, hounds wailing close behind. Bryce and other scientists leap in pursuit. The big cat skirts a meadow and vaults into a fir tree. Wide-eyed, she pants as saliva streams from her jaw. When a shot hits its mark, the puma jumps to ground and streaks away.This heated chase is part of efforts to tranquilize and study pumas. As the animals continue to encroach on towns and cities, there's an urgent need to understand their movements and behavior. In essence, scientists want to know what it takes for a large mammal to survive in a landscape shared more and more with people. To find out, they developed collars that do much more than pinpoint animal locations: they also track a complex suite of movements and measure energy expenditure. Their findings, and these seemingly simple collar advances, could help better conserve wildlife and protect humans worldwide.For decades, GPS tracking collars have revealed an animal's location, indicating the distance traveled between position readings, but not whether the animal moved directly or took side trips. And GPS collars alone don't indicate whether the animal ran or walked from point to point. These behaviors affect the energy an animal expends, which can be crucial to predicting and protecting its range. Species Movement, Acceleration, and Radio Tracking collars-SMART collarsaren't a conservation panacea, but they're proving to be a crucial tool in multiple arenas. Getting SMARTerIn 2014 eco-physiologist Terrie Williams, wildlife ecologist Christopher Wilmers, and computer engineer Gabriel Elkaim of the University of California, Santa Cruz (UCSC), designed and developed SMART SMART collars record an expanded suite of data compare with GPS collars, providing a potentially important tool for conserving wildlife and minimizing clashes with people. Image courtesy of Sebastian Kennerknecht (www.pumapix.com).

show abstract

Prying into the intimate secrets of animal lives; software beyond hardware for comprehensive annotation in ‘Daily Diary’ tags

Cited by 60 publications

References 45 publications

Identification of behaviours from accelerometer data in a wild social primate

Identification of behaviours from accelerometer data in a wild social primate

Can accelerometry be used to distinguish between flight types in soaring birds?

SMART collars help track and conserve wildlife

Contact Info

Product

Resources

About