RESUMO
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.
RESUMO
A spring emergence of avian haemosporidian infections is nearly universal among temperate zone birds and is often described as a cost of reproductive effort. We take advantage of the opportunistic (i.e. aseasonal) breeding schedule of the red crossbill (Loxia curvirostra) to determine the relative contributions of season versus host physiology to the timing and intensity of Haemoproteus infections in the temperate zone. Despite breeding activity in both the winter and summer, Haemoproteus infections were highly seasonal--occurring largely from May through September--and measures of host physiology (i.e. reproductive condition and stress parameters) did not explain parasite prevalence. However, within the spring-summer peak, infection intensity (i.e. parasite density) was positively correlated with plasma levels of testosterone and free corticosterone and negatively correlated with corticosterone binding globulin capacity. These data are discussed in terms of the behavioral ecology of host and vector, and suggest that both seasonal increases in vector activity and relapse of latent (i.e. dormant) infections contribute to the spring emergence in birds. Relapse of latent infections does not appear to be induced by reproductive activity or increased allostatic (i.e. energy) load, but rather by a season-specific change in host or parasite physiology (e.g. melatonin or endogenous rhythms).
