Dataset Information

R package for animal behavior classification from accelerometer data-rabc.

ABSTRACT: Increasingly, animal behavior studies are enhanced through the use of accelerometry. To allow translation of raw accelerometer data to animal behaviors requires the development of classifiers. Here, we present the "rabc" (r for animal behavior classification) package to assist researchers with the interactive development of such animal behavior classifiers in a supervised classification approach. The package uses datasets consisting of accelerometer data with their corresponding animal behaviors (e.g., for triaxial accelerometer data along the x, y and z axes arranged as "x, y, z, x, y, z,…, behavior"). Using an example dataset collected on white stork (Ciconia ciconia), we illustrate the workflow of this package, including accelerometer data visualization, feature calculation, feature selection, feature visualization, extreme gradient boost model training, validation, and, finally, a demonstration of the behavior classification results.

SUBMITTER: Yu H

PROVIDER: S-EPMC8462134 | biostudies-literature | 2021 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

R package for animal behavior classification from accelerometer data-rabc.

Yu Hui H Klaassen Marcel M

Ecology and evolution 20210820 18

Increasingly, animal behavior studies are enhanced through the use of accelerometry. To allow translation of raw accelerometer data to animal behaviors requires the development of classifiers. Here, we present the "rabc" (r for animal behavior classification) package to assist researchers with the interactive development of such animal behavior classifiers in a supervised classification approach. The package uses datasets consisting of accelerometer data with their co ...[more]

PMID: 34594505

Similar Datasets

Project description:BackgroundStudies of animal behaviour, ecology and physiology are continuously benefitting from progressing biologging techniques, including the collection of accelerometer data to infer animal behaviours and energy expenditure. In one of the most recent technological advances in this space, on-board processing of raw accelerometer data into animal behaviours proves highly energy-, weight- and cost-efficient allowing for continuous behavioural data collection in addition to regular positional data in a wide range of animal tracking studies.MethodsWe implemented this latest development in collecting continuous behaviour records from 6 Pacific Black Ducks Anas superciliosa to evaluate some of this novel technique's potential advantages over tracking studies lacking behavioural data or recording accelerometer data intermittently only. We (i) compared the discrepancy of time-activity budgets between continuous records and behaviours sampled with different intervals, (ii) compared total daily distance flown using hourly GPS fixes with and without additional behavioural data and (iii) explored how behaviour records can provide additional insights for animal home range studies.ResultsUsing a total of 690 days of behaviour records across six individual ducks distinguishing eight different behaviours, we illustrated the improvement that is obtained in time-activity budget accuracy if continuous rather than interval-sampled accelerometer data is used. Notably, for rare behaviours such as flying and running, error ratios > 1 were common when sampling intervals exceeded 10 min. Using 72 days of hourly GPS fixes in combination with continuous behaviour records over the same period in one individual duck, we showed behaviour-based daily distance estimation is significantly higher (up to 540%) than the distance calculated from hourly sampled GPS fixes. Also, with the same 72 days of data for one individual duck, we showed how this individual used specific sites within its entire home range to satisfy specific needs (e.g. roosting and foraging).ConclusionWe showed that by using trackers allowing for continuous recording of animal behaviour, substantial improvements in the estimation of time-activity budgets and daily traveling distances can be made. With integrating behaviour into home-range estimation we also highlight that this novel tracking technique may not only improve estimations but also open new avenues in animal behaviour research, importantly improving our knowledge of an animal's state while it is roaming the landscape.

Project description:Identification and classification of behavior states in animal movement data can be complex, temporally biased, time-intensive, scale-dependent, and unstandardized across studies and taxa. Large movement datasets are increasingly common and there is a need for efficient methods of data exploration that adjust to the individual variability of each track. We present the Residence in Space and Time (RST) method to classify behavior patterns in movement data based on the concept that behavior states can be partitioned by the amount of space and time occupied in an area of constant scale. Using normalized values of Residence Time and Residence Distance within a constant search radius, RST is able to differentiate behavior patterns that are time-intensive (e.g., rest), time & distance-intensive (e.g., area restricted search), and transit (short time and distance). We use grey-headed albatross (Thalassarche chrysostoma) GPS tracks to demonstrate RST's ability to classify behavior patterns and adjust to the inherent scale and individuality of each track. Next, we evaluate RST's ability to discriminate between behavior states relative to other classical movement metrics. We then temporally sub-sample albatross track data to illustrate RST's response to less resolved data. Finally, we evaluate RST's performance using datasets from four taxa with diverse ecology, functional scales, ecosystems, and data-types. We conclude that RST is a robust, rapid, and flexible method for detailed exploratory analysis and meta-analyses of behavioral states in animal movement data based on its ability to integrate distance and time measurements into one descriptive metric of behavior groupings. Given the increasing amount of animal movement data collected, it is timely and useful to implement a consistent metric of behavior classification to enable efficient and comparative analyses. Overall, the application of RST to objectively explore and compare behavior patterns in movement data can enhance our fine- and broad- scale understanding of animal movement ecology.

Dataset Information

R package for animal behavior classification from accelerometer data-rabc.

Publications

R package for animal behavior classification from accelerometer data-rabc.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets