4.5 Article

Quantifying mating behaviour using accelerometry and machine learning: challenges and opportunities

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Behavioral Sciences

Year-round behavioural time budgets of common woodpigeons inferred from acceleration data using machine learning

Juan F. Masello et al.

Summary: Accelerometers and machine learning algorithms were used to analyze the behaviors of woodpigeons in different environments, and the results showed variations in time budgets among seasons and locations. Urban woodpigeons were found to spend more time foraging compared to forest woodpigeons.

BEHAVIORAL ECOLOGY AND SOCIOBIOLOGY (2023)

Article Multidisciplinary Sciences

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

Charlotte Christensen et al.

Summary: This study successfully identified social grooming behavior of wild baboons using machine learning and accelerometer data, providing continuous data for studying their social behavior.

ROYAL SOCIETY OPEN SCIENCE (2023)

Article Biology

Hidden Markov and Semi-Markov Models When and Why are These Models Useful for Classifying States in Time Series Data?

Sofia Ruiz-Suarez et al.

Summary: Hidden Markov models (HMMs) and their extensions, such as hidden semi-Markov models (HSMMs) and autoregressive-HMMs, have been shown to be powerful tools for classifying observations that have temporal dependence. This paper provides implementation details for these models in a supervised learning context and demonstrates their application in classifying accelerometer data from Merino sheep. The study also investigates the impact of model misspecification on classification performance.

JOURNAL OF AGRICULTURAL BIOLOGICAL AND ENVIRONMENTAL STATISTICS (2022)

Article Zoology

Tri-axial accelerometry shows differences in energy expenditure and parental effort throughout the breeding season in long-lived raptors

Pascual Lopez-Lopez et al.

Summary: Cutting-edge technologies were used to monitor 25 Bonelli's eagles during the breeding season, revealing roles and differences in parental care between sexes and substantial increase in energetic requirements of males. The study highlights the crucial role of males in raptor species exhibiting biparental care.

CURRENT ZOOLOGY (2022)

Article Ecology

Ecological inference using data from accelerometers needs careful protocols

Baptiste Garde et al.

Summary: Accelerometers in animal-attached tags are powerful tools in behavioural ecology, but using data repositories for ecological inference requires understanding of error sources and assessment methods. Laboratory experiments and case studies demonstrate that accelerometer accuracy, tag placement, and attachment can impact signal amplitude and the system's ability to detect biological phenomena.

METHODS IN ECOLOGY AND EVOLUTION (2022)

Article Ecology

Quantifying song behavior in a free-living, light-weight, mobile bird using accelerometers

Elena Eisenring et al.

Summary: To understand animal communication, this study used lightweight accelerometers to observe and classify the behavior of European Nightjars. The results show that accelerometer-based identification of vocalizations can be a promising tool to study communication in free-living, small-sized birds. It also reveals the limitations of using audio recorders to investigate individual-based variation in song behavior.

ECOLOGY AND EVOLUTION (2022)

Article Ecology

Categorising cheetah behaviour using tri-axial accelerometer data loggers: a comparison of model resolution and data logger performance

Natasha E. McGowan et al.

Summary: Understanding the fine-scale behaviors of vulnerable species is crucial for effective conservation. This study used animal-attached accelerometers to categorize cheetah behaviors and compare the performance of different devices. The results showed that remote sensing technology accurately classified cheetah behaviors, providing valuable insights for monitoring wild cheetahs and other conservation species.

MOVEMENT ECOLOGY (2022)

Article Environmental Sciences

Integrating Biologging and Behavioral State Modeling to Identify Cryptic Behaviors and Post-capture Recovery Processes: New Insights From a Threatened Marine Apex Predator

Richard Grainger et al.

Summary: Multisensor biologging provides a powerful tool for ecological research, although challenges remain in objectively identifying distinct behavioral modes. Integrating multiple sensors and behavioral state modeling can improve understanding of animal behavior processes and recovery.

FRONTIERS IN MARINE SCIENCE (2022)

Article Ecology

Continuous on-board behaviour classification using accelerometry: A case study with a new GPS-3G-Bluetooth system in Pacific black ducks

Hui Yu et al.

Summary: Accelerometer data have become increasingly important for studying animal behaviors and energetics over the past two decades. However, the large amount of raw data can be burdensome in terms of storage and power consumption. On-board data processing and compression have shown great potential in reducing these problems and opening up new possibilities for ecological and behavioral research.

METHODS IN ECOLOGY AND EVOLUTION (2022)

Article Chemistry, Analytical

Improving Human Activity Recognition Performance by Data Fusion and Feature Engineering

Jingcheng Chen et al.

Summary: Human activity recognition is crucial in health-related fields, and fusion from heterogeneous wearable sensors has been developed for portable and accurate recognition. Feature selection plays a key role in reducing system burden and achieving good classification performance. The proposed genetic algorithm-based feature selection algorithm showed good performance in activity recognition with experiments demonstrating the benefits of sensor calibration and joint angle estimation.

SENSORS (2021)

Article Ecology

Detection of foraging behavior from accelerometer data using U-Net type convolutional networks

Manh Cuong Ngo et al.

Summary: The narwhal, an elusive marine mammal living in the Arctic, was studied to detect its feeding behavior through accelerometer data. Reliable buzz detectors were developed, and the hunting patterns of narwhals were found to differ from other marine mammals.

ECOLOGICAL INFORMATICS (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

Measuring the bias of incorrect application of feature selection when using cross-validation in radiomics

Aydin Demircioglu

Summary: In radiomic studies, performing feature selection before cross-validation can lead to bias, and it is important to conduct feature selection within cross-validation to reduce bias.

INSIGHTS INTO IMAGING (2021)

Article Chemistry, Analytical

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

Stefanie Brandes et al.

Summary: Averting the loss of biodiversity and ecosystem services can be achieved through conservation efforts, particularly focusing on keystone species like giraffes. Monitoring animal behavior in the wild using accelerometers can aid in conservation management, with promising results in predictive accuracy for certain behaviors. These devices, in combination with GPS tracking, have the potential to greatly contribute to the conservation of giraffes.

SENSORS (2021)

Article Chemistry, Analytical

Using Machine Learning for Remote Behaviour Classification-Verifying Acceleration Data to Infer Feeding Events in Free-Ranging Cheetahs

Lisa Giese et al.

Summary: Behavioral studies of elusive wildlife species are challenging but important, especially in cases of human-wildlife conflicts. Accelerometers and supervised machine learning algorithms were used to remotely determine behaviors in captive cheetahs. The model successfully identified feeding events in free-ranging cheetahs, demonstrating reliable detection capabilities.

SENSORS (2021)

Article Ecology

Using tri-axial accelerometer loggers to identify spawning behaviours of large pelagic fish

Thomas M. Clarke et al.

Summary: The study applied a machine learning algorithm to classify accelerometer data from yellowtail kingfish, successfully identifying five distinct behaviors with an overall accuracy of 94%. The model was also successfully applied to free-ranging kingfish, predicting all behavior classes observed in captive fish, including 19 courtship events.

MOVEMENT ECOLOGY (2021)

Article Ecology

Limitations of using surrogates for behaviour classification of accelerometer data: refining methods using random forest models in Caprids

Eleanor R. Dickinson et al.

Summary: This study assessed the validity of using captive conspecifics and phylogenetically-similar domesticated counterparts for calibrating behaviour classification. Results showed high accuracy in behavioural classification of captive Alpine ibex and domestic pygmy goats, but using domestic counterparts to predict wild species behaviour was not sufficient. The study highlights the importance of calibrating biologging devices with similar conspecifics in environments that reflect the wild species' habitat.

MOVEMENT ECOLOGY (2021)

Review Ecology

Uncovering ecological state dynamics with hidden Markov models

Brett T. McClintock et al.

ECOLOGY LETTERS (2020)

Article Computer Science, Information Systems

Efficient Human Activity Recognition Using a Single Wearable Sensor

Jianchao Lu et al.

IEEE INTERNET OF THINGS JOURNAL (2020)

Review Computer Science, Artificial Intelligence

Hyperparameters and tuning strategies for random forest

Philipp Probst et al.

WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY (2019)

Article Ecology

A novel biomechanical approach for animal behaviour recognition using accelerometers

Pritish Chakravarty et al.

METHODS IN ECOLOGY AND EVOLUTION (2019)

Review Instruments & Instrumentation

An overview of human activity recognition based on smartphone

Guan Yuan et al.

SENSOR REVIEW (2019)

Article Computer Science, Theory & Methods

Feature Selection: A Data Perspective

Jundong Li et al.

ACM COMPUTING SURVEYS (2018)

Article Ecology

Analysis of animal accelerometer data using hidden Markov models

Vianey Leos-Barajas et al.

METHODS IN ECOLOGY AND EVOLUTION (2017)

Article Biodiversity Conservation

Using tri-axial accelerometers to identify wild polar bear behaviors

A. M. Pagano et al.

ENDANGERED SPECIES RESEARCH (2017)

Review Behavioral Sciences

Applications of machine learning in animal behaviour studies

John Joseph Valletta et al.

ANIMAL BEHAVIOUR (2017)

Article Genetics & Heredity

A supergene determines highly divergent male reproductive morphs in the ruff

Clemens Kuepper et al.

NATURE GENETICS (2016)

Article Agriculture, Dairy & Animal Science

Using a three-axis accelerometer to identify and classify sheep behaviour at pasture

F. A. P. Alvarenga et al.

APPLIED ANIMAL BEHAVIOUR SCIENCE (2016)

Article Computer Science, Interdisciplinary Applications

fitdistrplus: An R Package for Fitting Distributions

Marie Laure Delignette-Muller et al.

JOURNAL OF STATISTICAL SOFTWARE (2015)

Review Multidisciplinary Sciences

Deep learning

Yann LeCun et al.

NATURE (2015)

Article Ecology

Quantifying individual variation in behaviour: mixed-effect modelling approaches

Niels J. Dingemanse et al.

JOURNAL OF ANIMAL ECOLOGY (2013)

Review Biology

Polyandry and alternative mating tactics

Bryan D. Neff et al.

PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES (2013)

Article Multidisciplinary Sciences

From Sensor Data to Animal Behaviour: An Oystercatcher Example

Judy Shamoun-Baranes et al.

PLOS ONE (2012)

Article Multidisciplinary Sciences

Adaptive Sleep Loss in Polygynous Pectoral Sandpipers

John A. Lesku et al.

SCIENCE (2012)

Review Biochemistry & Molecular Biology

Assessing the development and application of the accelerometry technique for estimating energy expenditure

Lewis G. Halsey et al.

COMPARATIVE BIOCHEMISTRY AND PHYSIOLOGY A-MOLECULAR & INTEGRATIVE PHYSIOLOGY (2011)

Article Behavioral Sciences

Using a behaviour discovery curve to predict optimal observation time

Kristen R. Jule et al.

BEHAVIOUR (2009)

Review Computer Science, Artificial Intelligence

Learning from Imbalanced Data

Haibo He et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2009)

Article Biodiversity Conservation

Identification of animal movement patterns using tri-axial accelerometry

ELC Shepard et al.

Endangered Species Research (2008)

Article Biodiversity Conservation

Prying into the intimate details of animal lives: use of a daily diary on animals

RP Wilson et al.

Endangered Species Research (2007)

Article Biology

Permanent female mimics in a lekking shorebird

Joop Jukema et al.

BIOLOGY LETTERS (2006)