Search

Showing total 543 results
Start Over Search Limiters Available in Library Collection Topic machine learning Publication Year Range Last 10 years Publisher springer berlin heidelberg
543 results

105. Development and application of a machine learning algorithm for classification of elasmobranch behaviour from accelerometry data

Author

Samuel H. Gruber, Alexander C. Hansell, Lauran R. Brewster, Michael Elliott, Ian G. Cowx, Jonathan J. Dale, Nicholas M. Whitney, Tristan L. Guttridge, and Adrian C. Gleiss

Subjects
0106 biological sciences, Original Paper, Ecology, biology, Artificial neural network, business.industry, 010604 marine biology & hydrobiology, Aquatic Science, biology.organism_classification, Logistic regression, Headshaking, Accelerometer, Machine learning, computer.software_genre, 010603 evolutionary biology, 01 natural sciences, Random forest, Negaprion brevirostris, 14. Life underwater, Gradient boosting, Artificial intelligence, business, computer, Classifier (UML), Ecology, Evolution, Behavior and Systematics
Abstract

Discerning behaviours of free-ranging animals allows for quantification of their activity budget, providing important insight into ecology. Over recent years, accelerometers have been used to unveil the cryptic lives of animals. The increased ability of accelerometers to store large quantities of high resolution data has prompted a need for automated behavioural classification. We assessed the performance of several machine learning (ML) classifiers to discern five behaviours performed by accelerometer-equipped juvenile lemon sharks (Negaprion brevirostris) at Bimini, Bahamas (25°44′N, 79°16′W). The sharks were observed to exhibit chafing, burst swimming, headshaking, resting and swimming in a semi-captive environment and these observations were used to ground-truth data for ML training and testing. ML methods included logistic regression, an artificial neural network, two random forest models, a gradient boosting model and a voting ensemble (VE) model, which combined the predictions of all other (base) models to improve classifier performance. The macro-averaged F-measure, an indicator of classifier performance, showed that the VE model improved overall classification (F-measure 0.88) above the strongest base learner model, gradient boosting (0.86). To test whether the VE model provided biologically meaningful results when applied to accelerometer data obtained from wild sharks, we investigated headshaking behaviour, as a proxy for prey capture, in relation to the variables: time of day, tidal phase and season. All variables were significant in predicting prey capture, with predations most likely to occur during early evening and less frequently during the dry season and high tides. These findings support previous hypotheses from sporadic visual observations. Electronic supplementary material The online version of this article (10.1007/s00227-018-3318-y) contains supplementary material, which is available to authorized users.

Published
2018