Search

The application of supervised machine learning methods to identify behavioural modes from inertial measurements of bio-loggers has become a standard tool in behavioural ecology. Several design choices can affect the accuracy of identifying the behavioural modes. One such choice is the inclusion or exclusion of segments consisting of more than a single behaviour (mixed segments) in the machine learning model training data. Currently, the common practice is to ignore such segments during model training. In this paper we tested the hypothesis that including mixed segments in model training will improve accuracy, as the model would perform better in identifying them in the test data. We test this hypothesis using a series of data simulations on four datasets of accelerometer data coupled with behaviour observations, obtained from four study species (Damaraland mole-rats, meerkats, olive baboons, polar bears). Results show that when a substantial proportion of the test data are mixed behaviour segments (above ~ 10%), including mixed segments in machine learning model training improves the accuracy of classification. These results were consistent across the four study species, and robust to changes in segment length, sample size, and degree of mixture within the mixed segments. However, we also find that in some cases (particularly in baboons) models trained with mixed segments show reduced accuracy in classifying test data containing only single behaviour (pure) segments, compared to models trained without mixed segments. Based on these results, we recommend that when the classification model is expected to deal with a substantial proportion of mixed behaviour segments (> 10%), it is beneficial to include them in model training, otherwise, it is unnecessary but also not harmful. The exception is when there is a basis to assume that the training data contains a higher rate of mixed segments than the actual (unobserved) data to be classified—such a situation may occur particularly when training data are collected in captivity and used to classify data from the wild. In this case, excess inclusion of mixed segments in training data should probably be avoided. [ABSTRACT FROM AUTHOR]

Many animals return to their home areas (i.e., ‘homing’) after translocation to sites further away. Such translocations have traditionally been used in behavioral ecology to understand the orientation and migration behavior of animals. The movement itself can then be followed by marking and recapturing animals or by tracking, for example, using GPS systems. Most detailed studies investigating this behavior have been conducted in smaller vertebrates (e.g., birds, amphibians, and mice), whereas information on larger mammals, such as red deer, is sparse. We conducted GPS-assisted translocation experiments with red deer at two sites in the Czech Republic. Individuals were translocated over a distance of approximately 11 km and their home journey was tracked. Circular statistics were used to test for significant homeward orientation at distances of 100, 500, 1000, and 5000 m from the release site. In addition, we applied Lavielle trajectory segmentation to identify the different phases of homing behavior. Thirty-one out of 35 translocations resulted in successful homing, with a median time of 4.75 days (range 1.23–100 days). Animals were significantly oriented towards home immediately after release and again when they came closer to home; however, they did not show a significant orientation at the distances in between. We were able to identify three homing phases, an initial ‘exploratory phase’, followed by a ‘homing phase’ which sometimes was again followed by an ‘arrival phase’. The ‘homing phase’ was characterized by the straightest paths and fastest movements. However, the variation between translocation events was considerable. We showed good homing abilities of red deer after translocation. Our results demonstrate the feasibility of conducting experiments with environmental manipulations (e.g., to impede the use of sensory cues) close to the release site. The homing behavior of red deer is comparable to that of other species, and might represent general homing behavior patterns in animals. Follow-up studies should further dissect and investigate the drivers of the individual variations observed and try to identify the sensory cues used during homing. [ABSTRACT FROM AUTHOR]

Sleep serves vital physiological functions, yet how sleep in wild animals is influenced by environmental conditions is poorly understood. Here we use high-resolution biologgers to investigate sleep in wild animals over ecologically relevant time scales and quantify variability between individuals under changing conditions. We developed a robust classification for accelerometer data and measured multiple dimensions of sleep in the wild boar ( Sus scrofa ) over an annual cycle. In support of the hypothesis that environmental conditions determine thermoregulatory challenges, which regulate sleep, we show that sleep quantity, efficiency and quality are reduced on warmer days, sleep is less fragmented in longer and more humid days, while greater snow cover and rainfall promote sleep quality. Importantly, this longest and most detailed analysis of sleep in wild animals to date reveals large inter- and intra-individual variation. Specifically, short-sleepers sleep up to 46% less than long-sleepers but do not compensate for their short sleep through greater plasticity or quality, suggesting they may pay higher costs of sleep deprivation. Given the major role of sleep in health, our results suggest that global warming and the associated increase in extreme climatic events are likely to negatively impact sleep, and consequently health, in wildlife, particularly in nocturnal animals.