No abstract

Background: Semi-automating the analyses of accelerometry data makes it possible to synthesize large data sets. However, when constructing activity budgets from accelerometry data, there are many methods to extract, analyse and report data and results. For instance, machine learning is a robust approach to classifying data. We used a new method, super learning, that combines base learners (different machine learning methods) in an optimal manner to achieve overall improved accuracy. Other facets of super learning include the number of behavioural categories to predict, the number of epochs (sample window size) used to split data for training and testing and the parameters on which to train the models. Results:The super learner accurately classified behaviour categories with higher accuracy and lower variance than comparative models. For all models tested, using four behaviours, in comparison with six, achieved higher rates of accuracy. The number of epochs chosen also affected the accuracy with smaller epochs (7 and 13) performing better than longer epochs (25 and 75). Conclusions:Correct model selection, training and testing are imperative to creating reliable and valid classification models. To do so means model fitting must use a wide array of selection criteria. We evaluated a number of these including model, number of behaviours to classify and epoch length and then used a parameter grid search to implement the models. We found that all criteria tested contributed to the models' overall accuracies. Fewer behaviour categories and shorter epoch length improved the performance of all models tested. The super learner classified behaviours with higher accuracy and lower variance than other models tested. However, when using this model, users need to consider the additional human and computational time required for implementation. Machine learning is a powerful method for classifying the behaviour of animals from accelerometers. Care and consideration of the modelling parameters evaluated in this study are essential when using this type of statistical analysis.

Extreme weather events in Australia are common and a large proportion of the population are exposed to such events. Therefore, there is great interest as to how these events impact Australia's society and economy, which requires understanding the current and historical impact of disasters. Despite global efforts to record and cost disaster impacts, no standardised method of collecting and recording data retrospectively yet exists. The lack of standardisation in turn results in a range of different estimates of economic impacts. This paper examines five examples of aggregate disaster loss and impacts of natural disasters in Australia, and comparisons between them reveal significant 2 data shortcomings. The reliability of data sources, and the methodology employed to analyse them can have significant impacts on conclusions regarding the overall cost of disasters, the relative costs of different hazards (disaster types), and the distribution of losses across Australian states. We highlight difficulties with time series comparisons, further complicated by the interdependencies of the databases. We reiterate the need for consistent and comparable data collection and analysis, to respond to the increasing frequency and severity of disasters in Australia.

Constructing activity budgets for marine animals when they are at sea and cannot be directly observed is challenging, but recent advances in bio-logging technology offer solutions to this problem. Accelerometers can potentially identify a wide range of behaviours for animals based on unique patterns of acceleration. However, when analysing data derived from accelerometers, there are many statistical techniques available which when applied to different data sets produce different classification accuracies. We investigated a selection of supervised machine learning methods for interpreting behavioural data from captive otariids (fur seals and sea lions). We conducted controlled experiments with 12 seals, where their behaviours were filmed while they were wearing 3-axis accelerometers. From video we identified 26 behaviours that could be grouped into one of four categories (foraging, resting, travelling and grooming) representing key behaviour states for wild seals. We used data from 10 seals to train four predictive classification models: stochastic gradient boosting (GBM), random forests, support vector machine using four different kernels and a baseline model: penalised logistic regression. We then took the best parameters from each model and cross-validated the results on the two seals unseen so far. We also investigated the influence of feature statistics (describing some characteristic of the seal), testing the models both with and without these. Cross-validation accuracies were lower than training accuracy, but the SVM with a polynomial kernel was still able to classify seal behaviour with high accuracy (>70%). Adding feature statistics improved accuracies across all models tested. Most categories of behaviour -resting, grooming and feeding—were all predicted with reasonable accuracy (52–81%) by the SVM while travelling was poorly categorised (31–41%). These results show that model selection is important when classifying behaviour and that by using animal characteristics we can strengthen the overall accuracy.

Pinnipeds generally target relatively small prey that can be swallowed whole, yet often include larger prey in their diet. To eat large prey, they must first process it into pieces small enough to swallow. In this study we explored the range of prey‐processing behaviors used by Australian sea lions (Neophoca cinerea) when presented with large prey during captive feeding trials. The most common methods were chewing using the teeth, shaking prey at the surface, and tearing prey held between the teeth and forelimbs. Although pinnipeds do not masticate their food, we found that sea lions used chewing to create weak points in large prey to aid further processing and to prepare secured pieces of prey for swallowing. Shake feeding matches the processing behaviors observed in fur seals, but use of forelimbs for “hold and tear” feeding has not been previously reported for other otariids. When performing this processing method, prey was torn by being stretched between the teeth and forelimbs, where it was secured by being squeezed between the palms of their flippers. These results show that Australian sea lions use a broad repertoire of behaviors for prey processing, which matches the wide range of prey species in their diet.