Seeing It All: Evaluating Supervised Machine Learning Methods for the Classification of Diverse Otariid Behaviours

From land to ocean: One month for southern elephant seal pups to acquire aquatic skills prior to their first departure to sea

Weaned southern elephant seals (SES) quickly transition from terrestrial to aquatic life after a 5- to 6-week post-weaning period. At sea, juveniles and adult elephant seals present extreme, continuous diving behaviour. Previous studies have highlighted the importance of the post-weaning period for weanlings to prepare for the physiological challenges of their future sea life. However, very little is known about how their body condition during this period may influence the development of their behaviour and brain activities. To characterise changes in the behavioural and brain activity of weanlings prior to ocean departure, we implemented a multi-logger approach combining measurements of movements (related to behaviour), pressure (related to diving), and brain electrical activity. As pups age, the amount of time allocated to resting decreases in favour of physical activity. Most resting (9.6 ± 1.2 h/day) takes place during daytime, with periods of slow-wave sleep representing 4.9 ± 0.9 h/day during the first 2 weeks. Furthermore, an increasing proportion of physical activity transitions from land to shore. Additionally, pups in poorer condition (lean group) are more active earlier than those in better condition (corpulent group). Finally, at weaning, clear circadian activity with two peaks at dawn and dusk is observed, and this pattern remains unchanged during the 4 weeks on land. This circadian pattern matches the one observed in adults at sea, with more prey catches at dawn and dusk, raising the question of whether it is endogenous or triggered by the mother during lactation.

Quantifying allo-grooming in wild chacma baboons (Papio ursinus) using tri-axial acceleration data and machine learning

Quantification of activity budgets is pivotal for understanding how animals respond to changes in their environment. Social grooming is a key activity that underpins various social processes with consequences for health and fitness. Traditional methods use direct (focal) observations to calculate grooming rates, providing systematic but sparse data. Accelerometers, in contrast, can quantify activity budgets continuously but have not been used to quantify social grooming. We test whether grooming can be accurately identified using machine learning (random forest model) trained on labelled acceleration data from wild chacma baboons (Papio ursinus). We successfully identified giving and receiving grooming with high precision (81% and 91%) and recall (87% and 79%). Giving grooming was associated with a distinct rhythmical signal along the surge axis. Receiving grooming had similar acceleration signals to resting, and thus was more difficult to assign. We applied our machine learning model to n = 680 collar data days from n = 12 baboons and found that grooming rates obtained from accelerometers were significantly and positively correlated with direct observation rates for giving but not receiving grooming. The ability to collect continuous grooming data in wild populations will allow researchers to re-examine and expand upon long-standing questions regarding the formation and function of grooming bonds.

Characterizing the suckling behavior by video and 3D-accelerometry in humpback whale calves on a breeding ground

Getting maternal milk through nursing is vital for all newborn mammals. Despite its importance, nursing has been poorly documented in humpback whales (Megaptera novaeangliae). Nursing is difficult to observe underwater without disturbing the whales and is usually impossible to observe from a ship. We attempted to observe nursing from the calf's perspective by placing CATS cam tags on three humpback whale calves in the Sainte Marie channel, Madagascar, Indian Ocean, during the breeding seasons. CATS cam tags are animal-borne multi-sensor tags equipped with a video camera, a hydrophone, and several auxiliary sensors (including a 3-axis accelerometer, a 3-axis magnetometer, and a depth sensor). The use of multi-sensor tags minimized potential disturbance from human presence. A total of 10.52 h of video recordings were collected with the corresponding auxiliary data. Video recordings were manually analyzed and correlated with the auxiliary data, allowing us to extract different kinematic features including the depth rate, speed, Fluke Stroke Rate (FSR), Overall Body Dynamic Acceleration (ODBA), pitch, roll, and roll rate. We found that suckling events lasted 18.8 ± 8.8 s on average (N = 34) and were performed mostly during dives. Suckling events represented 1.7% of the total observation time. During suckling, the calves were visually estimated to be at a 30-45° pitch angle relative to the midline of their mother's body and were always observed rolling either to the right or to the left. In our auxiliary dataset, we confirmed that suckling behavior was primarily characterized by a high average absolute roll and additionally we also found that it was likely characterized by a high average FSR and a low average speed. Kinematic features were used for supervised machine learning in order to subsequently detect suckling behavior automatically. Our study is a proof of method on which future investigations can build upon. It opens new opportunities for further investigation of suckling behavior in humpback whales and the baleen whale species.

Remote Recognition of Moving Behaviors for Captive Harbor Seals Using a Smart-Patch System via Bluetooth Communication

Animal telemetry has been recognized as a core platform for exploring animal species due to future opportunities in terms of its contribution toward marine fisheries and living resources. Herein, biologging systems with pressure sensors are successfully implemented via open-source hardware platforms, followed by immediate application to captive harbor seals (HS). Remotely captured output voltage signals in real-time mode via Bluetooth communication were reproducibly and reliably recorded on the basis of hours using a smartphone built with data capturing software with graphic user interface (GUI). Output voltages, corresponding to typical behaviors on the captive HS, such as stopping (A), rolling (B), flapping (C), and sliding (D), are clearly obtained, and their analytical interpretation on captured electrical signals are fully validated via a comparison study with consecutively captured images for each motion of the HS. Thus, the biologging system with low cost and light weight, which is fully compatible with a conventional smartphone, is expected to potentially contribute toward future anthology of seal animals.

Assessment of Machine Learning Models to Identify Port Jackson Shark Behaviours Using Tri-Axial Accelerometers

Movement ecology has traditionally focused on the movements of animals over large time scales, but, with advancements in sensor technology, the focus can become increasingly fine scale. Accelerometers are commonly applied to quantify animal behaviours and can elucidate fine-scale (<2 s) behaviours. Machine learning methods are commonly applied to animal accelerometry data; however, they require the trial of multiple methods to find an ideal solution. We used tri-axial accelerometers (10 Hz) to quantify four behaviours in Port Jackson sharks (Heterodontus portusjacksoni): two fine-scale behaviours (<2 s)-(1) vertical swimming and (2) chewing as proxy for foraging, and two broad-scale behaviours (>2 s-mins)-(3) resting and (4) swimming. We used validated data to calculate 66 summary statistics from tri-axial accelerometry and assessed the most important features that allowed for differentiation between the behaviours. One and two second epoch testing sets were created consisting of 10 and 20 samples from each behaviour event, respectively. We developed eight machine learning models to assess their overall accuracy and behaviour-specific accuracy (one classification tree, five ensemble learners and two neural networks). The support vector machine model classified the four behaviours better when using the longer 2 s time epoch (F-measure 89%; macro-averaged F-measure: 90%). Here, we show that this support vector machine (SVM) model can reliably classify both fine- and broad-scale behaviours in Port Jackson sharks.

Behavioural inference from signal processing using animal-borne multi-sensor loggers: a novel solution to extend the knowledge of sea turtle ecology

The identification of sea turtle behaviours is a prerequisite to predicting the activities and time-budget of these animals in their natural habitat over the long term. However, this is hampered by a lack of reliable methods that enable the detection and monitoring of certain key behaviours such as feeding. This study proposes a combined approach that automatically identifies the different behaviours of free-ranging sea turtles through the use of animal-borne multi-sensor recorders (accelerometer, gyroscope and time-depth recorder), validated by animal-borne video-recorder data. We show here that the combination of supervised learning algorithms and multi-signal analysis tools can provide accurate inferences of the behaviours expressed, including feeding and scratching behaviours that are of crucial ecological interest for sea turtles. Our procedure uses multi-sensor miniaturized loggers that can be deployed on free-ranging animals with minimal disturbance. It provides an easily adaptable and replicable approach for the long-term automatic identification of the different activities and determination of time-budgets in sea turtles. This approach should also be applicable to a broad range of other species and could significantly contribute to the conservation of endangered species by providing detailed knowledge of key animal activities such as feeding, travelling and resting.

Augmenting biologging with supervised machine learning to study in situ behavior of the medusa Chrysaora fuscescens

Zooplankton play critical roles in marine ecosystems, yet their fine-scale behavior remains poorly understood because of the difficulty in studying individuals in situ. Here, we combine biologging with supervised machine learning (ML) to propose a pipeline for studying in situ behavior of larger zooplankton such as jellyfish. We deployed the ITAG, a biologging package with high-resolution motion sensors designed for soft-bodied invertebrates, on eight Chrysaora fuscescens in Monterey Bay, using the tether method for retrieval. By analyzing simultaneous video footage of the tagged jellyfish, we developed ML methods to: (1) identify periods of tag data corrupted by the tether method, which may have compromised prior research findings, and (2) classify jellyfish behaviors. Our tools yield characterizations of fine-scale jellyfish activity and orientation over long durations, and we conclude that it is essential to develop behavioral classifiers on in situ rather than laboratory data.

Summary: High-resolution motion sensors paired with supervised machine learning can be used to infer fine-scale in situ behavior of zooplankton over long durations.

Prediction of Hemodialysis Timing Based on LVW Feature Selection and Ensemble Learning

We propose an improved model based on LVW embedded model feature extractor and ensemble learning for improving prediction accuracy of hemodialysis timing in this paper. Due to this drawback caused by feature extraction models, we adopt an enhanced LVW embedded model to search the feature subset by stochastic strategy, which can find the best feature combination that are most beneficial to learner performance. In the model application, we present an improved integrated learners for model fusion to reduce errors caused by overfitting problem of the single classifier. We run several state-of-the-art Q&A methods as contrastive experiments. The experimental results show that the ensemble learning model based on LVW has better generalization ability (97.04%) and lower standard error (± 0.04). We adopt the model to make high-precision predictions of hemodialysis timing, and the experimental results have shown that our framework significantly outperforms several strong baselines. Our model provides strong clinical decision support for physician diagnosis and has important clinical implications.

ShapeGTB: the role of local DNA shape in prioritization of functional variants in human promoters with machine learning

Motivation

The identification of functional sequence variations in regulatory DNA regions is one of the major challenges of modern genetics. Here, we report results of a combined multifactor analysis of properties characterizing functional sequence variants located in promoter regions of genes.

Results

We demonstrate that GC-content of the local sequence fragments and local DNA shape features play significant role in prioritization of functional variants and outscore features related to histone modifications, transcription factors binding sites, or evolutionary conservation descriptors. Those observations allowed us to build specialized machine learning classifier identifying functional single nucleotide polymorphisms within promoter regions—ShapeGTB. We compared our method with more general tools predicting pathogenicity of all non-coding variants. ShapeGTB outperformed them by a wide margin (average precision 0.93 vs. 0.47–0.55). On the external validation set based on ClinVar database it displayed worse performance but was still competitive with other methods (average precision 0.47 vs. 0.23–0.42). Such results suggest unique characteristics of mutations located within promoter regions and are a promising signal for the development of more accurate variant prioritization tools in the future.

Using accelerometers to develop time-energy budgets of wild fur seals from captive surrogates

Background

Accurate time-energy budgets summarise an animal's energy expenditure in a given environment, and are potentially a sensitive indicator of how an animal responds to changing resources. Deriving accurate time-energy budgets requires an estimate of time spent in different activities and of the energetic cost of that activity. Bio-loggers (e.g., accelerometers) may provide a solution for monitoring animals such as fur seals that make long-duration foraging trips. Using low resolution to record behaviour may aid in the transmission of data, negating the need to recover the device.

Methods

This study used controlled captive experiments and previous energetic research to derive time-energy budgets of juvenile Australian fur seals (Arctocephalus pusillus) equipped with tri-axial accelerometers. First, captive fur seals and sea lions were equipped with accelerometers recording at high (20 Hz) and low (1 Hz) resolutions, and their behaviour recorded. Using this data, machine learning models were trained to recognise four states-foraging, grooming, travelling and resting. Next, the energetic cost of each behaviour, as a function of location (land or water), season and digestive state (pre- or post-prandial) was estimated. Then, diving and movement data were collected from nine wild juvenile fur seals wearing accelerometers recording at high- and low- resolutions. Models developed from captive seals were applied to accelerometry data from wild juvenile Australian fur seals and, finally, their time-energy budgets were reconstructed.

Results

Behaviour classification models built with low resolution (1 Hz) data correctly classified captive seal behaviours with very high accuracy (up to 90%) and recorded without interruption. Therefore, time-energy budgets of wild fur seals were constructed with these data. The reconstructed time-energy budgets revealed that juvenile fur seals expended the same amount of energy as adults of similar species. No significant differences in daily energy expenditure (DEE) were found across sex or season (winter or summer), but fur seals rested more when their energy expenditure was expected to be higher. Juvenile fur seals used behavioural compensatory techniques to conserve energy during activities that were expected to have high energetic outputs (such as diving).

Discussion

As low resolution accelerometry (1 Hz) was able to classify behaviour with very high accuracy, future studies may be able to transmit more data at a lower rate, reducing the need for tag recovery. Reconstructed time-energy budgets demonstrated that juvenile fur seals appear to expend the same amount of energy as their adult counterparts. Through pairing estimates of energy expenditure with behaviour this study demonstrates the potential to understand how fur seals expend energy, and where and how behavioural compensations are made to retain constant energy expenditure over a short (dive) and long (season) period.

Proxies of energy expenditure for marine mammals: an experimental test of "the time trap"

Direct measures of energy expenditure are difficult to obtain in marine mammals, and accelerometry may be a useful proxy. Recently its utility has been questioned as some analyses derived their measure of activity level by calculating the sum of accelerometry-based values and then comparing this summation to summed (total) energy expenditure (the so-called “time trap”). To test this hypothesis, we measured oxygen consumption of captive fur seals and sea lions wearing accelerometers during submerged swimming and calculated total and rate of energy expenditure. We compared these values with two potential proxies of energy expenditure derived from accelerometry data: flipper strokes and dynamic body acceleration (DBA). Total number of strokes, total DBA, and submergence time all predicted total oxygen consumption \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$({\boldsymbol{sV}}{{\boldsymbol{O}}}_{{\boldsymbol{2}}}$$\end{document}(sVO2 ml kg⁻¹). However, both total DBA and total number of strokes were correlated with submergence time. Neither stroke rate nor mean DBA could predict the rate of oxygen consumption (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$s\mathop{{\boldsymbol{V}}}\limits^{{\boldsymbol{.}}}{{\boldsymbol{O}}}_{{\boldsymbol{2}}}$$\end{document}sV.O2 ml min⁻¹ kg⁻¹). The relationship of total DBA and total strokes with total oxygen consumption is apparently a result of introducing a constant (time) into both sides of the relationship. This experimental evidence supports the conclusion that proxies derived from accelerometers cannot estimate the energy expenditure of marine mammals.