A novel biomechanical approach for animal behaviour recognition using accelerometers

The environment to the rescue: can physics help predict predator-prey interactions?

Understanding the factors that determine the occurrence and strength of ecological interactions under specific abiotic and biotic conditions is fundamental since many aspects of ecological community stability and ecosystem functioning depend on patterns of interactions among species. Current approaches to mapping food webs are mostly based on traits, expert knowledge, experiments, and/or statistical inference. However, they do not offer clear mechanisms explaining how trophic interactions are affected by the interplay between organism characteristics and aspects of the physical environment, such as temperature, light intensity or viscosity. Hence, they cannot yet predict accurately how local food webs will respond to anthropogenic pressures, notably to climate change and species invasions. Herein, we propose a framework that synthesises recent developments in food-web theory, integrating body size and metabolism with the physical properties of ecosystems. We advocate for combination of the movement paradigm with a modular definition of the predation sequence, because movement is central to predator-prey interactions, and a generic, modular model is needed to describe all the possible variation in predator-prey interactions. Pending sufficient empirical and theoretical knowledge, our framework will help predict the food-web impacts of well-studied physical factors, such as temperature and oxygen availability, as well as less commonly considered variables such as wind, turbidity or electrical conductivity. An improved predictive capability will facilitate a better understanding of ecosystem responses to a changing world.

The sociality of sleep in animal groups

Group-living animals sleep together, yet most research treats sleep as an individual process. Here, we argue that social interactions during the sleep period contribute in important, but largely overlooked, ways to animal groups' social dynamics, while patterns of social interaction and the structure of social connections within animal groups play important, but poorly understood, roles in shaping sleep behavior. Leveraging field-appropriate methods, such as direct and video-based observation, and increasingly common on-animal motion sensors (e.g., accelerometers), behavioral indicators can be tracked to measure sleep in multiple individuals in a group of animals simultaneously. Sleep proximity networks and sleep timing networks can then be used to investigate the collective dynamics of sleep in wild group-living animals.

Classification of Behaviour in Conventional and Slow-Growing Strains of Broiler Chickens Using Tri-Axial Accelerometers

Behavioural states such as walking, sitting and standing are important in indicating welfare, including lameness in broiler chickens. However, manual behavioural observations of individuals are often limited by time constraints and small sample sizes. Three-dimensional accelerometers have the potential to collect information on animal behaviour. We applied a random forest algorithm to process accelerometer data from broiler chickens. Data from three broiler strains at a range of ages (from 25 to 49 days old) were used to train and test the algorithm, and unlike other studies, the algorithm was further tested on an unseen broiler strain. When tested on unseen birds from the three training broiler strains, the random forest model classified behaviours with very good accuracy (92%) and specificity (94%) and good sensitivity (88%) and precision (88%). With the new, unseen strain, the model classified behaviours with very good accuracy (94%), sensitivity (91%), specificity (96%) and precision (91%). We therefore successfully used a random forest model to automatically detect three broiler behaviours across four different strains and different ages using accelerometers. These findings demonstrated that accelerometers can be used to automatically record behaviours to supplement biomechanical and behavioural research and support in the reduction principle of the 3Rs.

How to treat mixed behavior segments in supervised machine learning of behavioural modes from inertial measurement data

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.

Dynamic Leadership Mechanism in Homing Pigeon Flocks

In recent years, an increasing number of studies have focused on exploring the principles and mechanisms underlying the emergence of collective intelligence in biological populations, aiming to provide insights for human society and the engineering field. Pigeon flock behavior garners significant attention as a subject of study. Collective homing flight is a commonly observed behavioral pattern in pigeon flocks. The study analyzes GPS data during the homing process and utilizes acceleration information, which better reflects the flock's movement tendencies during turns, to describe the leadership relationships within the group. By examining the evolution of acceleration during turning, the study unveils a dynamic leadership mechanism before and after turns, employing a more intricate dynamic model to depict the flock's motion. Specifically, during stable flight, pigeon flocks tend to rely on fixed leaders to guide homing flight, whereas during turns, individuals positioned in the direction of the flock's turn experience a notable increase in their leadership status. These findings suggest the existence of a dynamic leadership mechanism within pigeon flocks, enabling adaptability and stability under diverse flight conditions. From an engineering perspective, this leadership mechanism may offer novel insights for coordinating industrial multi-robot systems and controlling drone formations.

Accelerometer-based predictions of behaviour elucidate factors affecting the daily activity patterns of spotted hyenas

Animal activity patterns are highly variable and influenced by internal and external factors, including social processes. Quantifying activity patterns in natural settings can be challenging, as it is difficult to monitor animals over long time periods. Here, we developed and validated a machine-learning-based classifier to identify behavioural states from accelerometer data of wild spotted hyenas (Crocuta crocuta), social carnivores that live in large fission-fusion societies. By combining this classifier with continuous collar-based accelerometer data from five hyenas, we generated a complete record of activity patterns over more than one month. We used these continuous behavioural sequences to investigate how past activity, individual idiosyncrasies, and social synchronization influence hyena activity patterns. We found that hyenas exhibit characteristic crepuscular-nocturnal daily activity patterns. Time spent active was independent of activity level on previous days, suggesting that hyenas do not show activity compensation. We also found limited evidence for an effect of individual identity on activity, and showed that pairs of hyenas who synchronized their activity patterns must have spent more time together. This study sheds light on the patterns and drivers of activity in spotted hyena societies, and also provides a useful tool for quantifying behavioural sequences from accelerometer data.

Combining accelerometry with allometry for estimating daily energy expenditure in joules when in-lab calibration is unavailable

BACKGROUND

All behaviour requires energy, and measuring energy expenditure in standard units (joules) is key to linking behaviour to ecological processes. Animal-borne accelerometers are commonly used to infer proxies of energy expenditure, termed 'dynamic body acceleration' (DBA). However, converting acceleration proxies (m/s2) to standard units (watts) involves costly in-lab respirometry measurements, and there is a lack of viable substitutes for empirical calibration relationships when these are unavailable.

METHODS

We used past allometric work quantifying energy expenditure during resting and locomotion as a function of body mass to calibrate DBA. We used the resulting 'power calibration equation' to estimate daily energy expenditure (DEE) using two models: (1) locomotion data-based linear calibration applied to the waking period, and Kleiber's law applied to the sleeping period (ACTIWAKE), and (2) locomotion and resting data-based linear calibration applied to the 24-h period (ACTIREST24). Since both models require locomotion speed information, we developed an algorithm to estimate speed from accelerometer, gyroscope, and behavioural annotation data. We applied these methods to estimate DEE in free-ranging meerkats (Suricata suricatta), and compared model estimates with published DEE measurements made using doubly labelled water (DLW) on the same meerkat population.

RESULTS

ACTIWAKE's DEE estimates did not differ significantly from DLW (t(19) = - 1.25; P = 0.22), while ACTIREST24's estimates did (t(19) = - 2.38; P = 0.028). Both models underestimated DEE compared to DLW: ACTIWAKE by 14% and ACTIREST by 26%. The inter-individual spread in model estimates of DEE (s.d. 1-2% of mean) was lower than that in DLW (s.d. 33% of mean).

CONCLUSIONS

We found that linear locomotion-based calibration applied to the waking period, and a 'flat' resting metabolic rate applied to the sleeping period can provide realistic joule estimates of DEE in terrestrial mammals. The underestimation and lower spread in model estimates compared to DLW likely arise because the accelerometer only captures movement-related energy expenditure, whereas DLW is an integrated measure. Our study offers new tools to incorporate body mass (through allometry), and changes in behavioural time budgets and intra-behaviour changes in intensity (through DBA) in acceleration-based field assessments of daily energy expenditure.

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.

The role of individual variability on the predictive performance of machine learning applied to large bio-logging datasets

Animal-borne tagging (bio-logging) generates large and complex datasets. In particular, accelerometer tags, which provide information on behaviour and energy expenditure of wild animals, produce high-resolution multi-dimensional data, and can be challenging to analyse. We tested the performance of commonly used artificial intelligence tools on datasets of increasing volume and dimensionality. By collecting bio-logging data across several sampling seasons, datasets are inherently characterized by inter-individual variability. Such information should be considered when predicting behaviour. We integrated both unsupervised and supervised machine learning approaches to predict behaviours in two penguin species. The classified behaviours obtained from the unsupervised approach Expectation Maximisation were used to train the supervised approach Random Forest. We assessed agreement between the approaches, the performance of Random Forest on unknown data and the implications for the calculation of energy expenditure. Consideration of behavioural variability resulted in high agreement (> 80%) in behavioural classifications and minimal differences in energy expenditure estimates. However, some outliers with < 70% of agreement, highlighted how behaviours characterized by signal similarity are confused. We advise the broad bio-logging community, approaching these large datasets, to be cautious when upscaling predictions, as this might lead to less accurate estimates of behaviour and energy expenditure.

Affordable RFID loggers for monitoring animal movement, activity, and behaviour

Effective conservation management strategies require accurate information on the movement patterns and behaviour of wild animals. To collect these data, researchers are increasingly turning to remote sensing technology such as radio-frequency identification (RFID). RFID technology is a powerful tool that has been widely implemented in ecological research to identify and monitor unique individuals, but it bears a substantial price tag, restricting this technology to generously-funded disciplines and projects. To overcome this price hurdle, we provide detailed step-by-step instructions to source the components for, and construct portable RFID loggers in house, at a fraction of the cost (~5%) of commercial RFID units. Here, we assess the performance of these RFID loggers in the field and describe their application in two studies of Australian mammal species; monitoring nest-box use in the Northern quolls (Dasyurus hallucatus) and observing the foraging habits of quenda (Isoodon fusciventer) at feeding stations. The RFID loggers performed well, identifying quenda in >80% of visits, and facilitating the collection of individual-level behavioural data including common metrics such as emergence time, latency to approach, and foraging effort. While the technology itself is not novel, by lowering the cost per unit, our loggers enabled greater sample sizes, increasing statistical power from 0.09 to 0.75 in the quoll study. Further, we outline and provide solutions to the limitations of this design. Our RFID loggers proved an innovative method for collecting accurate behavioural and movement data. With their ability to successfully identify individuals, the RFID loggers described here can act as an alternative or complementary tool to camera traps. These RFID loggers can also be applied in a wide variety of projects which range from monitoring animal welfare or demographic traits to studies of anti-predator responses and animal personality, making them a valuable addition to the modern ecologists’ toolkit.

Identification of reindeer fine-scale foraging behaviour using tri-axial accelerometer data

Animal behavioural responses to the environment ultimately affect their survival. Monitoring animal fine-scale behaviour may improve understanding of animal functional response to the environment and provide an important indicator of the welfare of both wild and domesticated species. In this study, we illustrate the application of collar-attached acceleration sensors for investigating reindeer fine-scale behaviour. Using data from 19 reindeer, we tested the supervised machine learning algorithms Random forests, Support vector machines, and hidden Markov models to classify reindeer behaviour into seven classes: grazing, browsing low from shrubs or browsing high from trees, inactivity, walking, trotting, and other behaviours. We implemented leave-one-subject-out cross-validation to assess generalizable results on new individuals. Our main results illustrated that hidden Markov models were able to classify collar-attached accelerometer data into all our pre-defined behaviours of reindeer with reasonable accuracy while Random forests and Support vector machines were biased towards dominant classes. Random forests using 5-s windows had the highest overall accuracy (85%), while hidden Markov models were able to best predict individual behaviours and handle rare behaviours such as trotting and browsing high. We conclude that hidden Markov models provide a useful tool to remotely monitor reindeer and potentially other large herbivore species behaviour. These methods will allow us to quantify fine-scale behavioural processes in relation to environmental events.

Discrete element models for understanding the biomechanics of fossorial animals

The morphological features of fossorial animals have continuously evolved in response to the demands of survival. However, existing methods for animal burrowing mechanics are not capable of addressing the large deformation of substrate. The discrete element method (DEM) is able to overcome this limitation. In this study, we used DEM to develop a general model to simulate the motion of an animal body part and its interaction with the substrate. The DEM also allowed us to easily change the forms of animal body parts to examine how those different forms affected the biomechanical functions. These capabilities of the DEM were presented through a case study of modeling the burrowing process of North American Badger. In the case study, the dynamics (forces, work, and soil displacements) of burrowing were predicted for different forms of badger claw and manus, using the model. Results showed that when extra digits are added to a manus, the work required for a badger to dig increases considerably, while the mass of soil dug only increases gradually. According to the proposed efficiency index (ratio of the amount of soil dug to the work required), the modern manus with 5 digits has indeed biomechanical advantage for their fossorial lifestyle, and the current claw curvature (25.3 mm in radius) is indeed optimal. The DEM is able to predict biomechanical relationships between functions and forms for any fossorial animals. Results can provide biomechanical evidences for explaining how the selective pressures for functions influence the morphological evolution in fossorial animals.

Studies of the Behavioral Sequences: The Neuroethological Morphology Concept Crossing Ethology and Functional Morphology

Simple Summary

Behavioral sequences analysis is a relevant method for quantifying the behavioral repertoire of animals to respond to the classical Tinbergen’s four questions. Research in ethology and functional morphology intercepts at the level of analysis of behaviors through the recording and interpretation of data from of movement sequence studies with various types of imaging and sensor systems. We propose the concept of Neuroethological morphology to build a holistic framework for understanding animal behavior. This concept integrates ethology (including behavioral ecology and neuroethology) with functional morphology (including biomechanics and physics) to provide a heuristic approach in behavioral biology.

Abstract

Postures and movements have been one of the major modes of human expression for understanding and depicting organisms in their environment. In ethology, behavioral sequence analysis is a relevant method to describe animal behavior and to answer Tinbergen’s four questions testing the causes of development, mechanism, adaptation, and evolution of behaviors. In functional morphology (and in biomechanics), the analysis of behavioral sequences establishes the motor pattern and opens the discussion on the links between “form” and “function”. We propose here the concept of neuroethological morphology in order to build a holistic framework for understanding animal behavior. This concept integrates ethology with functional morphology, and physics. Over the past hundred years, parallel developments in both disciplines have been rooted in the study of the sequential organization of animal behavior. This concept allows for testing genetic, epigenetic, and evo-devo predictions of phenotypic traits between structures, performances, behavior, and fitness in response to environmental constraints. Based on a review of the literature, we illustrate this concept with two behavioral cases: (i) capture behavior in squamates, and (ii) the ritualistic throat display in lizards.

Machine learned daily life history classification using low frequency tracking data and automated modelling pipelines: application to North American waterfowl

BACKGROUND

Identifying animal behaviors, life history states, and movement patterns is a prerequisite for many animal behavior analyses and effective management of wildlife and habitats. Most approaches classify short-term movement patterns with high frequency location or accelerometry data. However, patterns reflecting life history across longer time scales can have greater relevance to species biology or management needs, especially when available in near real-time. Given limitations in collecting and using such data to accurately classify complex behaviors in the long-term, we used hourly GPS data from 5 waterfowl species to produce daily activity classifications with machine-learned models using "automated modelling pipelines".

METHODS

Automated pipelines are computer-generated code that complete many tasks including feature engineering, multi-framework model development, training, validation, and hyperparameter tuning to produce daily classifications from eight activity patterns reflecting waterfowl life history or movement states. We developed several input features for modeling grouped into three broad categories, hereafter "feature sets": GPS locations, habitat information, and movement history. Each feature set used different data sources or data collected across different time intervals to develop the "features" (independent variables) used in models.

RESULTS

Automated modelling pipelines rapidly developed easily reproducible data preprocessing and analysis steps, identification and optimization of the best performing model and provided outputs for interpreting feature importance. Unequal expression of life history states caused unbalanced classes, so we evaluated feature set importance using a weighted F1-score to balance model recall and precision among individual classes. Although the best model using the least restrictive feature set (only 24 hourly relocations in a day) produced effective classifications (weighted F1 = 0.887), models using all feature sets performed substantially better (weighted F1 = 0.95), particularly for rarer but demographically more impactful life history states (i.e., nesting).

CONCLUSIONS

Automated pipelines generated models producing highly accurate classifications of complex daily activity patterns using relatively low frequency GPS and incorporating more classes than previous GPS studies. Near real-time classification is possible which is ideal for time-sensitive needs such as identifying reproduction. Including habitat and longer sequences of spatial information produced more accurate classifications but incurred slight delays in processing.

Ecological inference using data from accelerometers needs careful protocols

Accelerometers in animal-attached tags are powerful tools in behavioural ecology, they can be used to determine behaviour and provide proxies for movement-based energy expenditure. Researchers are collecting and archiving data across systems, seasons and device types. However, using data repositories to draw ecological inference requires a good understanding of the error introduced according to sensor type and position on the study animal and protocols for error assessment and minimisation.Using laboratory trials, we examine the absolute accuracy of tri-axial accelerometers and determine how inaccuracies impact measurements of dynamic body acceleration (DBA), a proxy for energy expenditure, in human participants. We then examine how tag type and placement affect the acceleration signal in birds, using pigeons Columba livia flying in a wind tunnel, with tags mounted simultaneously in two positions, and back- and tail-mounted tags deployed on wild kittiwakes Rissa tridactyla. Finally, we present a case study where two generations of tag were deployed using different attachment procedures on red-tailed tropicbirds Phaethon rubricauda foraging in different seasons.Bench tests showed that individual acceleration axes required a two-level correction to eliminate measurement error. This resulted in DBA differences of up to 5% between calibrated and uncalibrated tags for humans walking at a range of speeds. Device position was associated with greater variation in DBA, with upper and lower back-mounted tags varying by 9% in pigeons, and tail- and back-mounted tags varying by 13% in kittiwakes. The tropicbird study highlighted the difficulties of attributing changes in signal amplitude to a single factor when confounding influences tend to covary, as DBA varied by 25% between seasons.Accelerometer accuracy, tag placement and attachment critically affect the signal amplitude and thereby the ability of the system to detect biologically meaningful phenomena. We propose a simple method to calibrate accelerometers that can be executed under field conditions. This should be used prior to deployments and archived with resulting data. We also suggest a way that researchers can assess accuracy in previously collected data, and caution that variable tag placement and attachment can increase sensor noise and even generate trends that have no biological meaning.

An Information Theoretic Approach to Symbolic Learning in Synthetic Languages

An important aspect of using entropy-based models and proposed “synthetic languages”, is the seemingly simple task of knowing how to identify the probabilistic symbols. If the system has discrete features, then this task may be trivial; however, for observed analog behaviors described by continuous values, this raises the question of how we should determine such symbols. This task of symbolization extends the concept of scalar and vector quantization to consider explicit linguistic properties. Unlike previous quantization algorithms where the aim is primarily data compression and fidelity, the goal in this case is to produce a symbolic output sequence which incorporates some linguistic properties and hence is useful in forming language-based models. Hence, in this paper, we present methods for symbolization which take into account such properties in the form of probabilistic constraints. In particular, we propose new symbolization algorithms which constrain the symbols to have a Zipf–Mandelbrot–Li distribution which approximates the behavior of language elements. We introduce a novel constrained EM algorithm which is shown to effectively learn to produce symbols which approximate a Zipfian distribution. We demonstrate the efficacy of the proposed approaches on some examples using real world data in different tasks, including the translation of animal behavior into a possible human language understandable equivalent.

Great tits do not compensate over time for a radio-tag-induced reduction in escape-flight performance

The use of biologging and tracking devices is widespread in avian behavioral and ecological studies. Carrying these devices rarely has major behavioral or fitness effects in the wild, yet it may still impact animals in more subtle ways, such as during high power demanding escape maneuvers. Here, we tested whether or not great tits (Parus major) carrying a backpack radio-tag changed their body mass or flight behavior over time to compensate for the detrimental effect of carrying a tag. We tested 18 great tits, randomly assigned to a control (untagged) or one of two different types of a radio-tag as used in previous studies in the wild (0.9 g or 1.2 g; ~5% or ~6-7% of body mass, respectively), and determined their upward escape-flight performance 1, 7, 14, and 28 days after tagging. In between experiments, birds were housed in large free-flight aviaries. For each escape-flight, we used high-speed 3D videography to determine flight paths, escape-flight speed, wingbeat frequency, and actuator disk loading (ratio between the bird weight and aerodynamic thrust production capacity). Tagged birds flew upward with lower escape-flight speeds, caused by an increased actuator disk loading. During the 28-day period, all groups slightly increased their body mass and their in-flight wingbeat frequency. In addition, during this period, all groups of birds increased their escape-flight speed, but tagged birds did so at a lower rate than untagged birds. This suggests that birds may increase their escape-flight performance through skill learning; however, tagged birds still remained slower than controls. Our findings suggest that tagging a songbird can have a prolonged effect on the performance of rapid flight maneuvers. Given the absence of tag effects on reproduction and survival in most songbird radio-tagging studies, tagged birds in the wild might adjust their risk-taking behavior to avoid performing rapid flight maneuvers.

Digging into the behaviour of an active hunting predator: arctic fox prey caching events revealed by accelerometry

BACKGROUND

Biologging now allows detailed recording of animal movement, thus informing behavioural ecology in ways unthinkable just a few years ago. In particular, combining GPS and accelerometry allows spatially explicit tracking of various behaviours, including predation events in large terrestrial mammalian predators. Specifically, identification of location clusters resulting from prey handling allows efficient location of killing events. For small predators with short prey handling times, however, identifying predation events through technology remains unresolved. We propose that a promising avenue emerges when specific foraging behaviours generate diagnostic acceleration patterns. One such example is the caching behaviour of the arctic fox (Vulpes lagopus), an active hunting predator strongly relying on food storage when living in proximity to bird colonies.

METHODS

We equipped 16 Arctic foxes from Bylot Island (Nunavut, Canada) with GPS and accelerometers, yielding 23 fox-summers of movement data. Accelerometers recorded tri-axial acceleration at 50 Hz while we obtained a sample of simultaneous video recordings of fox behaviour. Multiple supervised machine learning algorithms were tested to classify accelerometry data into 4 behaviours: motionless, running, walking and digging, the latter being associated with food caching. Finally, we assessed the spatio-temporal concordance of fox digging and greater snow goose (Anser caerulescens antlanticus) nesting, to test the ecological relevance of our behavioural classification in a well-known study system dominated by top-down trophic interactions.

RESULTS

The random forest model yielded the best behavioural classification, with accuracies for each behaviour over 96%. Overall, arctic foxes spent 49% of the time motionless, 34% running, 9% walking, and 8% digging. The probability of digging increased with goose nest density and this result held during both goose egg incubation and brooding periods.

CONCLUSIONS

Accelerometry combined with GPS allowed us to track across space and time a critical foraging behaviour from a small active hunting predator, informing on spatio-temporal distribution of predation risk in an Arctic vertebrate community. Our study opens new possibilities for assessing the foraging behaviour of terrestrial predators, a key step to disentangle the subtle mechanisms structuring many predator-prey interactions and trophic networks.

R package for animal behavior classification from accelerometer data-rabc

Increasingly, animal behavior studies are enhanced through the use of accelerometry. To allow translation of raw accelerometer data to animal behaviors requires the development of classifiers. Here, we present the "rabc" (r for animal behavior classification) package to assist researchers with the interactive development of such animal behavior classifiers in a supervised classification approach. The package uses datasets consisting of accelerometer data with their corresponding animal behaviors (e.g., for triaxial accelerometer data along the x, y and z axes arranged as "x, y, z, x, y, z,…, behavior"). Using an example dataset collected on white stork (Ciconia ciconia), we illustrate the workflow of this package, including accelerometer data visualization, feature calculation, feature selection, feature visualization, extreme gradient boost model training, validation, and, finally, a demonstration of the behavior classification results.

Behavioural change during dispersal and its relationship to survival and reproduction in a cooperative breeder

The ability of dispersing individuals to adjust their behaviour to changing conditions is instrumental in overcoming challenges and reducing dispersal costs, consequently increasing overall dispersal success. Understanding how dispersers' behaviour and physiology change during the dispersal process, and how they differ from resident individuals, can shed light on the mechanisms by which dispersers increase survival and maximise reproduction.

By analysing individual behaviour and concentrations of faecal glucocorticoid metabolites (fGCM), a stress‐associated biomarker, we sought to identify the proximate causes behind differences in survival and reproduction between dispersing and resident meerkats Suricata suricatta.

We used data collected on 67 dispersing and 108 resident females to investigate (a) which individual, social and environmental factors are correlated to foraging and vigilance, and whether the role of such factors differs among dispersal phases, and between dispersers and residents; (b) how time allocated to either foraging or vigilance correlated to survival in dispersers and residents and (c) the link between aggression and change in fGCM concentration, and their relationship with reproductive rates in dispersing groups and resident groups with either long‐established or newly established dominant females.

Time allocated to foraging increased across dispersal phases, whereas time allocated to vigilance decreased. Time allocated to foraging and vigilance correlated positively and negatively, respectively, with dispersers' group size. We did not find a group size effect for residents. High proportions of time allocated to foraging correlated with high survival, and more so in dispersers, suggesting that maintaining good physical condition may reduce mortality during dispersal. Furthermore, while subordinate individuals rarely reproduced in resident groups, the conception rate of subordinates in newly formed dispersing groups was equal to that of their dominant individuals. Mirroring conception rates, in resident groups, fGCM concentrations were lower in subordinates than in dominants, whereas in disperser groups, fGCM concentrations did not differ between subordinates and dominants.

Our results, which highlight the relationship between behavioural and physiological factors and demographic rates, provide insights into some of the mechanisms that individuals of a cooperative species can use to increase overall dispersal success.

Quantifying finer-scale behaviours using self-organising maps (SOMs) to link accelerometery signatures with behavioural patterns in free-roaming terrestrial animals

Collecting quantitative information on animal behaviours is difficult, especially from cryptic species or species that alter natural behaviours under observation. Using harness-mounted tri-axial accelerometers free-roaming domestic cats (Felis Catus) we developed a methodology that can precisely classify finer-scale behaviours. We further tested the effect of a prey-protector device designed to reduce prey capture. We aligned accelerometer traces collected at 50 Hz with video files (60 fps) and labelled 12 individual behaviours, then trained a supervised machine-learning algorithm using Kohonen super self-organising maps (SOM). The SOM was able to predict individual behaviours with a ~ 99.6% overall accuracy, which was slightly better than for random forest estimates using the same dataset (98.9%). There was a significant effect of sample size, with precision and sensitivity decreasing rapidly below 2000 1-s observations. We were also able to detect a behaviour specific reduction in the predictability when cats were fitted with the prey-protector device indicating it altered biomechanical gait. Our results can be applied in movement ecology, zoology and conservation, where habitat specific movement performance between predators or prey may be critical to managing species of conservation significance, or in veterinary and agricultural fields, where early detection of movement pathologies can improve animal welfare.

A new approach to assessing the space use behavior of macroinvertebrates by automated video tracking

Individual space and resource use are central issues in ecology and conservation. Recent technological advances such as automated tracking techniques are boosting ecological research in this field. However, the development of a robust method to track space and resource use is still challenging for at least one important ecosystem component: motile aquatic macroinvertebrates. The challenges are mostly related to the small body size and rapid movement of many macroinvertebrate species and to light scattering and wave signal interference in aquatic habitats.We developed a video tracking method designed to reliably assess space use behavior among individual aquatic macroinvertebrates under laboratory (microcosm) conditions. The approach involves the use of experimental apparatus integrating a near infrared backlight source, a Plexiglas multi-patch maze, multiple infrared cameras, and automated video analysis. It allows detection of the position of fast-moving (~ 3 cm/s) and translucent individuals of small size (~ 5 mm in length, ~1 mg in dry weight) on simulated resource patches distributed over an experimental microcosm (0.08 m2).To illustrate the adequacy of the proposed method, we present a case study regarding the size dependency of space use behavior in the model organism Gammarus insensibilis, focusing on individual patch selection, giving-up times, and cumulative space used.In the case study, primary data were collected on individual body size and individual locomotory behavior, for example, mean speed, acceleration, and step length. Individual entrance and departure times were recorded for each simulated resource patch in the experimental maze. Individual giving-up times were found to be characterized by negative size dependency, with patch departure occurring sooner in larger individuals than smaller ones, and individual cumulative space used (treated as the overall surface area of resource patches that individuals visited) was found to scale positively with body size.This approach to studying space use behavior can deepen our understanding of species coexistence, yielding insights into mechanistic models on larger spatial scales, for example, home range, with implications for ecological and evolutionary processes, as well as for the management and conservation of populations and ecosystems. Despite being specifically developed for aquatic macroinvertebrates, this method can also be applied to other small aquatic organisms such as juvenile fish and amphibians.

An evaluation of machine learning classifiers for next-generation, continuous-ethogram smart trackers

BACKGROUND

Our understanding of movement patterns and behaviours of wildlife has advanced greatly through the use of improved tracking technologies, including application of accelerometry (ACC) across a wide range of taxa. However, most ACC studies either use intermittent sampling that hinders continuity or continuous data logging relying on tracker retrieval for data downloading which is not applicable for long term study. To allow long-term, fine-scale behavioural research, we evaluated a range of machine learning methods for their suitability for continuous on-board classification of ACC data into behaviour categories prior to data transmission.

METHODS

We tested six supervised machine learning methods, including linear discriminant analysis (LDA), decision tree (DT), support vector machine (SVM), artificial neural network (ANN), random forest (RF) and extreme gradient boosting (XGBoost) to classify behaviour using ACC data from three bird species (white stork Ciconia ciconia, griffon vulture Gyps fulvus and common crane Grus grus) and two mammals (dairy cow Bos taurus and roe deer Capreolus capreolus).

RESULTS

Using a range of quality criteria, SVM, ANN, RF and XGBoost performed well in determining behaviour from ACC data and their good performance appeared little affected when greatly reducing the number of input features for model training. On-board runtime and storage-requirement tests showed that notably ANN, RF and XGBoost would make suitable on-board classifiers.

CONCLUSIONS

Our identification of using feature reduction in combination with ANN, RF and XGBoost as suitable methods for on-board behavioural classification of continuous ACC data has considerable potential to benefit movement ecology and behavioural research, wildlife conservation and livestock husbandry.

Behaviour Classification on Giraffes (Giraffa camelopardalis) Using Machine Learning Algorithms on Triaxial Acceleration Data of Two Commonly Used GPS Devices and Its Possible Application for Their Management and Conservation

Averting today's loss of biodiversity and ecosystem services can be achieved through conservation efforts, especially of keystone species. Giraffes (Giraffa camelopardalis) play an important role in sustaining Africa's ecosystems, but are 'vulnerable' according to the IUCN Red List since 2016. Monitoring an animal's behavior in the wild helps to develop and assess their conservation management. One mechanism for remote tracking of wildlife behavior is to attach accelerometers to animals to record their body movement. We tested two different commercially available high-resolution accelerometers, e-obs and Africa Wildlife Tracking (AWT), attached to the top of the heads of three captive giraffes and analyzed the accuracy of automatic behavior classifications, focused on the Random Forests algorithm. For both accelerometers, behaviors of lower variety in head and neck movements could be better predicted (i.e., feeding above eye level, mean prediction accuracy e-obs/AWT: 97.6%/99.7%; drinking: 96.7%/97.0%) than those with a higher variety of body postures (such as standing: 90.7-91.0%/75.2-76.7%; rumination: 89.6-91.6%/53.5-86.5%). Nonetheless both devices come with limitations and especially the AWT needs technological adaptations before applying it on animals in the wild. Nevertheless, looking at the prediction results, both are promising accelerometers for behavioral classification of giraffes. Therefore, these devices when applied to free-ranging animals, in combination with GPS tracking, can contribute greatly to the conservation of giraffes.

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.

The molecular basis of socially mediated phenotypic plasticity in a eusocial paper wasp

Phenotypic plasticity, the ability to produce multiple phenotypes from a single genotype, represents an excellent model with which to examine the relationship between gene expression and phenotypes. Analyses of the molecular foundations of phenotypic plasticity are challenging, however, especially in the case of complex social phenotypes. Here we apply a machine learning approach to tackle this challenge by analyzing individual-level gene expression profiles of Polistes dominula paper wasps following the loss of a queen. We find that caste-associated gene expression profiles respond strongly to queen loss, and that this change is partly explained by attributes such as age but occurs even in individuals that appear phenotypically unaffected. These results demonstrate that large changes in gene expression may occur in the absence of outwardly detectable phenotypic changes, resulting here in a socially mediated de-differentiation of individuals at the transcriptomic level but not at the levels of ovarian development or behavior.

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.

Optimal support vector machine and hybrid tracking model for behaviour recognition in highly dense crowd videos

Purpose

Object detection models have gained considerable popularity as they aid in lot of applications, like monitoring, video surveillance, etc. Object detection through the video tracking faces lot of challenges, as most of the videos obtained as the real time stream are affected due to the environmental factors.

Design/methodology/approach

This research develops a system for crowd tracking and crowd behaviour recognition using hybrid tracking model. The input for the proposed crowd tracking system is high density crowd videos containing hundreds of people. The first step is to detect human through visual recognition algorithms. Here, a priori knowledge of location point is given as input to visual recognition algorithm. The visual recognition algorithm identifies the human through the constraints defined within Minimum Bounding Rectangle (MBR). Then, the spatial tracking model based tracks the path of the human object movement in the video frame, and the tracking is carried out by extraction of color histogram and texture features. Also, the temporal tracking model is applied based on NARX neural network model, which is effectively utilized to detect the location of moving objects. Once the path of the person is tracked, the behaviour of every human object is identified using the Optimal Support Vector Machine which is newly developed by combing SVM and optimization algorithm, namely MBSO. The proposed MBSO algorithm is developed through the integration of the existing techniques, like BSA and MBO.

Findings

The dataset for the object tracking is utilized from Tracking in high crowd density dataset. The proposed OSVM classifier has attained improved performance with the values of 0.95 for accuracy.

Originality/value

This paper presents a hybrid high density video tracking model, and the behaviour recognition model. The proposed hybrid tracking model tracks the path of the object in the video through the temporal tracking and spatial tracking. The features train the proposed OSVM classifier based on the weights selected by the proposed MBSO algorithm. The proposed MBSO algorithm can be regarded as the modified version of the BSO algorithm.

Transforming the Adaptation Physiology of Farm Animals through Sensors

Despite recent scientific advancements, there is a gap in the use of technology to measure signals, behaviors, and processes of adaptation physiology of farm animals. Sensors present exciting opportunities for sustained, real-time, non-intrusive measurement of farm animal behavioral, mental, and physiological parameters with the integration of nanotechnology and instrumentation. This paper critically reviews the sensing technology and sensor data-based models used to explore biological systems such as animal behavior, energy metabolism, epidemiology, immunity, health, and animal reproduction. The use of sensor technology to assess physiological parameters can provide tremendous benefits and tools to overcome and minimize production losses while making positive contributions to animal welfare. Of course, sensor technology is not free from challenges; these devices are at times highly sensitive and prone to damage from dirt, dust, sunlight, color, fur, feathers, and environmental forces. Rural farmers unfamiliar with the technologies must be convinced and taught to use sensor-based technologies in farming and livestock management. While there is no doubt that demand will grow for non-invasive sensor-based technologies that require minimum contact with animals and can provide remote access to data, their true success lies in the acceptance of these technologies by the livestock industry.

Parasitic mites alter chicken behaviour and negatively impact animal welfare

The northern fowl mite, Ornithonyssus sylviarum, is one of the most common and damaging ectoparasites of poultry. As an obligate blood feeding mite, the northern fowl mite can cause anaemia, slower growth, and decreased egg production of parasitized birds. However, the impact of mites or other ectoparasites on hen behaviour or welfare is not well studied. Here, we use activity sensors (three-axis accelerometers) affixed to individual birds to continuously record hen movement before, during, and after infestation with mites. Movements recorded by sensors were identified to specific bird behaviours through a previously trained algorithm, with frequency of these behaviours recorded for individual birds. Hen welfare was also determined before, during, and after mite infestation of hens using animal-based welfare metrics. Northern fowl mites significantly increased hen preening behaviour and resulted in increased skin lesions of infested birds.

The Design of an Automated System for the Analysis of the Activity and Emotional Patterns of Dogs with Wearable Sensors Using Machine Learning

The safety and welfare of companion animals such as dogs has become a large challenge in the last few years. To assess the well-being of a dog, it is very important for human beings to understand the activity pattern of the dog, and its emotional behavior. A wearable, sensor-based system is suitable for such ends, as it will be able to monitor the dogs in real-time. However, the question remains unanswered as to what kind of data should be used to detect the activity patterns and emotional patterns, as does another: what should be the location of the sensors for the collection of data and how should we automate the system? Yet these questions remain unanswered, because to date, there is no such system that can address the above-mentioned concerns. The main purpose of this study was (1) to develop a system that can detect the activities and emotions based on the accelerometer and gyroscope signals and (2) to automate the system with robust machine learning techniques for implementing it for real-time situations. Therefore, we propose a system which is based on the data collected from 10 dogs, including nine breeds of various sizes and ages, and both genders. We used machine learning classification techniques for automating the detection and evaluation process. The ground truth fetched for the evaluation process was carried out by taking video recording data in frame per second and the wearable sensors data were collected in parallel with the video recordings. Evaluation of the system was performed using an ANN (artificial neural network), random forest, SVM (support vector machine), KNN (k nearest neighbors), and a naïve Bayes classifier. The robustness of our system was evaluated by taking independent training and validation sets. We achieved an accuracy of 96.58% while detecting the activity and 92.87% while detecting emotional behavior, respectively. This system will help the owners of dogs to track their behavior and emotions in real-life situations for various breeds in different scenarios.

Group size and social status affect scent marking in dispersing female meerkats

Many animal species use scent marks such as feces, urine, and glandular secretions to find mates, advertise their reproductive status, and defend an exclusive territory. Scent marking may be particularly important during dispersal, when individuals emigrate from their natal territory searching for mates and a new territory to settle and reproduce. In this study, we investigated the scent-marking behavior of 30 dispersing female meerkats (Suricata suricatta) during the three consecutive stages of dispersal—emigration, transience, and settlement. We expected marking patterns to differ between dispersal stages, depending on social circumstances such as presence of unrelated mates and social status of the individuals within each dispersing coalition and also to be influenced by water and food availability. We showed that defecation probability increased with group size during the settlement stage, when newly formed groups are expected to signal their presence to other resident groups. Urination probability was higher in subordinate than in dominant individuals during each of the three dispersal stages and it decreased overall as the dispersal process progressed. Urine may, thus, be linked to advertisement of the social status within a coalition. Anal marking probability did not change across dispersal stages but increased with the presence of unrelated males and was higher in dominants than in subordinates. We did not detect any effect of rain or foraging success on defecation and urination probability. Our results suggest that feces, urine, and anal markings serve different communication purposes (e.g., within and between-group communication) during the dispersal process.