The use of an unsupervised learning approach for characterizing latent behaviors in accelerometer data

The recent increase in data accuracy from high resolution accelerometers offers substantial potential for improved understanding and prediction of animal movements. However, current approaches used for analysing these multivariable datasets typically require existing knowledge of the behaviors of the animals to inform the behavioral classification process. These methods are thus not well‐suited for the many cases where limited knowledge of the different behaviors performed exist. Here, we introduce the use of an unsupervised learning algorithm. To illustrate the method's capability we analyse data collected using a combination of GPS and Accelerometers on two seabird species: razorbills (Alca torda) and common guillemots (Uria aalge). We applied the unsupervised learning algorithm Expectation Maximization to characterize latent behavioral states both above and below water at both individual and group level. The application of this flexible approach yielded significant new insights into the foraging strategies of the two study species, both above and below the surface of the water. In addition to general behavioral modes such as flying, floating, as well as descending and ascending phases within the water column, this approach allowed an exploration of previously unstudied and important behaviors such as searching and prey chasing/capture events. We propose that this unsupervised learning approach provides an ideal tool for the systematic analysis of such complex multivariable movement data that are increasingly being obtained with accelerometer tags across species. In particular, we recommend its application in cases where we have limited current knowledge of the behaviors performed and existing supervised learning approaches may have limited utility.

Behavioral classification of low-frequency acceleration and temperature data from a free-ranging small mammal

The miniaturization and affordability of new technology is driving a biologging revolution in wildlife ecology with use of animal-borne data logging devices. Among many new biologging technologies, accelerometers are emerging as key tools for continuously recording animal behavior. Yet a critical, but under-acknowledged consideration in biologging is the trade-off between sampling rate and sampling duration, created by battery- (or memory-) related sampling constraints. This is especially acute among small animals, causing most researchers to sample at high rates for very limited durations. Here, we show that high accuracy in behavioral classification is achievable when pairing low-frequency acceleration recordings with temperature. We conducted 84 hr of direct behavioral observations on 67 free-ranging red squirrels (200-300 g) that were fitted with accelerometers (2 g) recording tri-axial acceleration and temperature at 1 Hz. We then used a random forest algorithm and a manually created decision tree, with variable sampling window lengths, to associate observed behavior with logger recorded acceleration and temperature. Finally, we assessed the accuracy of these different classifications using an additional 60 hr of behavioral observations, not used in the initial classification. The accuracy of the manually created decision tree classification using observational data varied from 70.6% to 91.6% depending on the complexity of the tree, with increasing accuracy as complexity decreased. Short duration behavior like running had lower accuracy than long-duration behavior like feeding. The random forest algorithm offered similarly high overall accuracy, but the manual decision tree afforded the flexibility to create a hierarchical tree, and to adjust sampling window length for behavioral states with varying durations. Low frequency biologging of acceleration and temperature allows accurate behavioral classification of small animals over multi-month sampling durations. Nevertheless, low sampling rates impose several important limitations, especially related to assessing the classification accuracy of short duration behavior.

A comparison of techniques for classifying behavior from accelerometers for two species of seabird

The behavior of many wild animals remains a mystery, as it is difficult to quantify behavior of species that cannot be easily followed throughout their daily or seasonal movements. Accelerometers can solve some of these mysteries, as they collect activity data at a high temporal resolution (<1 s), can be relatively small (<1 g) so they minimally disrupt behavior, and are increasingly capable of recording data for long periods. Nonetheless, there is a need for increased validation of methods to classify animal behavior from accelerometers to promote widespread adoption of this technology in ecology. We assessed the accuracy of six different behavioral assignment methods for two species of seabird, thick-billed murres (Uria lomvia) and black-legged kittiwakes (Rissa tridactyla). We identified three behaviors using tri-axial accelerometers: standing, swimming, and flying, after classifying diving using a pressure sensor for murres. We evaluated six classification methods relative to independent classifications from concurrent GPS tracking data. We used four variables for classification: depth, wing beat frequency, pitch, and dynamic acceleration. Average accuracy for all methods was >98% for murres, and 89% and 93% for kittiwakes during incubation and chick rearing, respectively. Variable selection showed that classification accuracy did not improve with more than two (kittiwakes) or three (murres) variables. We conclude that simple methods of behavioral classification can be as accurate for classifying basic behaviors as more complex approaches, and that identifying suitable accelerometer metrics is more important than using a particular classification method when the objective is to develop a daily activity or energy budget. Highly accurate daily activity budgets can be generated from accelerometer data using multiple methods and a small number of accelerometer metrics; therefore, identifying a suitable behavioral classification method should not be a barrier to using accelerometers in studies of seabird behavior and ecology.

Mobile Phone-Based Measures of Activity, Step Count, and Gait Speed: Results From a Study of Older Ambulatory Adults in a Naturalistic Setting

BACKGROUND

Cellular mobile telephone technology shows much promise for delivering and evaluating healthcare interventions in cost-effective manners with minimal barriers to access. There is little data demonstrating that these devices can accurately measure clinically important aspects of individual functional status in naturalistic environments outside of the laboratory.

OBJECTIVE

The objective of this study was to demonstrate that data derived from ubiquitous mobile phone technology, using algorithms developed and previously validated by our lab in a controlled setting, can be employed to continuously and noninvasively measure aspects of participant (subject) health status including step counts, gait speed, and activity level, in a naturalistic community setting. A second objective was to compare our mobile phone-based data against current standard survey-based gait instruments and clinical physical performance measures in order to determine whether they measured similar or independent constructs.

METHODS

A total of 43 ambulatory, independently dwelling older adults were recruited from Nebraska Medicine, including 25 (58%, 25/43) healthy control individuals from our Engage Wellness Center and 18 (42%, 18/43) functionally impaired, cognitively intact individuals (who met at least 3 of 5 criteria for frailty) from our ambulatory Geriatrics Clinic. The following previously-validated surveys were obtained on study day 1: (1) Late Life Function and Disability Instrument (LLFDI); (2) Survey of Activities and Fear of Falling in the Elderly (SAFFE); (3) Patient Reported Outcomes Measurement Information System (PROMIS), short form version 1.0 Physical Function 10a (PROMIS-PF); and (4) PROMIS Global Health, short form version 1.1 (PROMIS-GH). In addition, clinical physical performance measurements of frailty (10 foot Get up and Go, 4 Meter walk, and Figure-of-8 Walk [F8W]) were also obtained. These metrics were compared to our mobile phone-based metrics collected from the participants in the community over a 24-hour period occurring within 1 week of the initial assessment.

RESULTS

We identified statistically significant differences between functionally intact and frail participants in mobile phone-derived measures of percent activity (P=.002, t test), active versus inactive status (P=.02, t test), average step counts (P<.001, repeated measures analysis of variance [ANOVA]) and gait speed (P<.001, t test). In functionally intact individuals, the above mobile phone metrics assessed aspects of functional status independent (Bland-Altman and correlation analysis) of both survey- and/or performance battery-based functional measures. In contrast, in frail individuals, the above mobile phone metrics correlated with submeasures of both SAFFE and PROMIS-GH.

CONCLUSIONS

Continuous mobile phone-based measures of participant community activity and mobility strongly differentiate between persons with intact functional status and persons with a frailty phenotype. These measures assess dimensions of functional status independent of those measured using current validated questionnaires and physical performance assessments to identify functional compromise. Mobile phone-based gait measures may provide a more readily accessible and less-time consuming measure of gait, while further providing clinicians with longitudinal gait measures that are currently difficult to obtain.

AI-Driven Framework for Enhanced and Automated Behavioral Analysis in Morris Water Maze Studies

The Morris Water Maze (MWM) is a widely used behavioral test to assess the spatial learning and memory of animals, particularly valuable in studying neurodegenerative disorders such as Alzheimer's disease. Traditional methods for analyzing MWM experiments often face limitations in capturing the complexity of animal behaviors. In this study, we present a novel AI-based automated framework to process and evaluate MWM test videos, aiming to enhance behavioral analysis through machine learning. Our pipeline involves video preprocessing, animal detection using convolutional neural networks (CNNs), trajectory tracking, and postprocessing to derive detailed behavioral features. We propose concentric circle segmentation of the pool next to the quadrant-based division, and we extract 32 behavioral metrics for each zone, which are employed in classification tasks to differentiate between younger and older animals. Several machine learning classifiers, including random forest and neural networks, are evaluated, with feature selection techniques applied to improve the classification accuracy. Our results demonstrate a significant improvement in classification performance, particularly through the integration of feature sets derived from concentric zone analyses. This automated approach offers a robust solution for MWM data processing, providing enhanced precision and reliability, which is critical for the study of neurodegenerative disorders.

Classifying behavior from short-interval biologging data: An example with GPS tracking of birds

Recent advances in digital data collection have spurred accumulation of immense quantities of data that have potential to lead to remarkable ecological insight, but that also present analytic challenges. In the case of biologging data from birds, common analytical approaches to classifying movement behaviors are largely inappropriate for these massive data sets.We apply a framework for using K-means clustering to classify bird behavior using points from short time interval GPS tracks. K-means clustering is a well-known and computationally efficient statistical tool that has been used in animal movement studies primarily for clustering segments of consecutive points. To illustrate the utility of our approach, we apply K-means clustering to six focal variables derived from GPS data collected at 1-11 s intervals from free-flying bald eagles (Haliaeetus leucocephalus) throughout the state of Iowa, USA. We illustrate how these data can be used to identify behaviors and life-stage- and age-related variation in behavior.After filtering for data quality, the K-means algorithm identified four clusters in >2 million GPS telemetry data points. These four clusters corresponded to three movement states: ascending, flapping, and gliding flight; and one non-moving state: perching. Mapping these states illustrated how they corresponded tightly to expectations derived from natural history observations; for example, long periods of ascending flight were often followed by long gliding descents, birds alternated between flapping and gliding flight.The K-means clustering approach we applied is both an efficient and effective mechanism to classify and interpret short-interval biologging data to understand movement behaviors. Furthermore, because it can apply to an abundance of very short, irregular, and high-dimensional movement data, it provides insight into small-scale variation in behavior that would not be possible with many other analytical approaches.

Design of an intelligent wearable device for real-time cattle health monitoring

In the realm of precision cattle health monitoring, this paper introduces the development and evaluation of a novel wearable continuous health monitoring device designed for cattle. The device integrates a sustainable solar-powered module, real-time signal acquisition and processing, and a storage module within an animal ergonomically designed curved casing for non-invasive cattle health monitoring. The curvature of the casing is tailored to better fit the contours of the cattle's neck, significantly enhancing signal accuracy, particularly in temperature signal acquisition. The core module is equipped with precision temperature sensors and inertial measurement units, utilizing the Arduino MKR ZERO board for data acquisition and processing. Field tests conducted on a cohort of ten cattle not only validated the accuracy of temperature sensing but also demonstrated the potential of machine learning, particularly the Support Vector Machine algorithm, for precise behavior classification and step counting, with an average accuracy of 97.27%. This study innovatively combines real-time temperature recognition, behavior classification, and step counting organically within a self-powered device. The results underscore the feasibility of this technology in enhancing cattle welfare and farm management efficiency, providing clear direction for future research to further enhance these devices for large-scale applications.

Development of a multisensor biologging collar and analytical techniques to describe high-resolution spatial behavior in free-ranging terrestrial mammals

Biologging has proven to be a powerful approach to investigate diverse questions related to movement ecology across a range of spatiotemporal scales and increasingly relies on multidisciplinary expertise. However, the variety of animal-borne equipment, coupled with little consensus regarding analytical approaches to interpret large, complex data sets presents challenges and makes comparison between studies and study species difficult. Here, we present a combined hardware and analytical approach for standardizing the collection, analysis, and interpretation of multisensor biologging data. Here, we present (i) a custom-designed integrated multisensor collar (IMSC), which was field tested on 71 free-ranging wild boar (Sus scrofa) over 2 years; (ii) a machine learning behavioral classifier capable of identifying six behaviors in free-roaming boar, validated across individuals equipped with differing collar designs; and (iii) laboratory and field-based calibration and accuracy assessments of animal magnetic heading measurements derived from raw magnetometer data. The IMSC capacity and durability exceeded expectations, with a 94% collar recovery rate and a 75% cumulative data recording success rate, with a maximum logging duration of 421 days. The behavioral classifier had an overall accuracy of 85% in identifying the six behavioral classes when tested on multiple collar designs and improved to 90% when tested on data exclusively from the IMSC. Both laboratory and field tests of magnetic compass headings were in precise agreement with expectations, with overall median magnetic headings deviating from ground truth observations by 1.7° and 0°, respectively. Although multisensor equipment and sophisticated analyses are now commonplace in biologging studies, the IMSC hardware and analytical framework presented here provide a valuable tool for biologging researchers and will facilitate standardization of biologging data across studies. In addition, we highlight the potential of additional analyses available using this framework that can be adapted for use in future studies on terrestrial mammals.

Social behavioral profiling by unsupervised deep learning reveals a stimulative effect of dopamine D3 agonists on zebrafish sociality

It has been a major challenge to systematically evaluate and compare how pharmacological perturbations influence social behavioral outcomes. Although some pharmacological agents are known to alter social behavior, precise description and quantification of such effects have proven difficult. We developed a scalable social behavioral assay for zebrafish named ZeChat based on unsupervised deep learning to characterize sociality at high resolution. High-dimensional and dynamic social behavioral phenotypes are automatically classified using this method. By screening a neuroactive compound library, we found that different classes of chemicals evoke distinct patterns of social behavioral fingerprints. By examining these patterns, we discovered that dopamine D3 agonists possess a social stimulative effect on zebrafish. The D3 agonists pramipexole, piribedil, and 7-hydroxy-DPAT-HBr rescued social deficits in a valproic-acid-induced zebrafish autism model. The ZeChat platform provides a promising approach for dissecting the pharmacology of social behavior and discovering novel social-modulatory compounds.