4.7 Review

Emerging technologies for behavioral research in changing environments

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 Computer Science, Theory & Methods

Transformers in Vision: A Survey

Salman Khan et al.

Summary: Transformer models have shown impressive results in computer vision tasks by simulating long dependencies, supporting parallel processing, and handling multi-modal data. They are widely used in visual recognition, generative modeling, multi-modal tasks, video processing, low-level vision, and three-dimensional analysis, showcasing their strengths in scalability and flexibility.

ACM COMPUTING SURVEYS (2022)

Article Multidisciplinary Sciences

Perspectives in machine learning for wildlife conservation

Devis Tuia et al.

Summary: Inexpensive and accessible sensors are increasingly used in animal ecology to accelerate data acquisition. By combining machine learning with domain knowledge, ecologists can harness large datasets generated by modern sensors to improve ecological models and develop integrated hybrid modeling tools through interdisciplinary collaboration.

NATURE COMMUNICATIONS (2022)

Article Ecology

Seismic savanna: machine learning for classifying wildlife and behaviours using ground-based vibration field recordings

Alexandre Szenicer et al.

Summary: The study developed a machine learning approach to detect and discriminate elephants from other species based on seismic data, achieving 80%-90% balanced accuracy in detecting elephants and over 90% balanced accuracy in recognizing running and rumbling behaviors. The results suggest that seismic data offer substantial benefits for wildlife monitoring and propose further development of methods using dense arrays for a seismic shift in wildlife monitoring.

REMOTE SENSING IN ECOLOGY AND CONSERVATION (2022)

Article Biochemical Research Methods

SLEAP: A deep learning system for multi-animal pose tracking

Talmo D. Pereira et al.

Summary: This paper presents Social LEAP Estimates Animal Poses (SLEAP), a machine learning system for multi-animal pose tracking. SLEAP achieves high accuracy and speed, making it suitable for real-time applications. It features a user-friendly interface, standardized data model, and versatile workflows for data labeling, model training, and inference. The researchers applied SLEAP to various datasets and compared it with existing approaches, demonstrating its effectiveness in tracking animal behavior during social interactions.

NATURE METHODS (2022)

Article Biochemical Research Methods

Multi-animal pose estimation, identification and tracking with DeepLabCut

Jessy Lauer et al.

Summary: This research extends the DeepLabCut toolbox to enable multi-animal pose estimation, animal identification, and tracking. It is of great significance for solving computer vision problems in multi-animal scenarios and provides a benchmark dataset for algorithm development.

NATURE METHODS (2022)

Article Multidisciplinary Sciences

On the dimensionality of behavior

William Bialek

Summary: This article discusses the dimensionality of behavior in animal behavior physics, including the definition of continuous trajectories and discrete state sequences and situations where the dimensionality of behavior is effectively infinite.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2022)

Article Biology

A guide to area-restricted search: a foundational foraging behaviour

Arik Dorfman et al.

Summary: Area-restricted search refers to the adaptive change in search effort based on resource encounters or expectations, helping organisms find targets. Conditions for this search pattern include clustered resources, active search, searcher memory, and ignorance about exact target locations.

BIOLOGICAL REVIEWS (2022)

Article Neurosciences

Measuring and modeling the motor system with machine learning

Sebastien B. Hausmann et al.

Summary: This review explores the growing use of machine learning in understanding the motor system, from pose estimation to neural correlates research, and discusses potential new avenues for hypothesis-driven research.

CURRENT OPINION IN NEUROBIOLOGY (2021)

Article Biology

TRex, a fast multi-animal tracking system with markerless identification, and 2D estimation of posture and visual fields

Tristan Walter et al.

Summary: TRex is a fast and easy-to-use automated visual tracking solution that can track a large number of individuals simultaneously and provide accurate visual identification. Compared to similar software, TRex offers higher performance and lower resource consumption.
Article Biochemical Research Methods

Geometric deep learning enables 3D kinematic profiling across species and environments

Timothy W. Dunn et al.

Summary: The study introduces a method called DANNCE, which tracks whole-body movements of animals in 3D and robustly tracks anatomical landmarks in freely moving animals. By constructing inputs to a convolutional neural network based on projective geometry, quantitative profiling of behavioral lineage in animals was achieved.

NATURE METHODS (2021)

Article Biochemical Research Methods

LiftPose3D, a deep learning-based approach for transforming two-dimensional to three-dimensional poses in laboratory animals

Adam Gosztolai et al.

Summary: LiftPose3D is a deep network-based method that reconstructs 3D poses from a single 2D camera view, overcoming the limitations of traditional triangulation methods. It has been demonstrated to be versatile and effective in analyzing behaviors of various experimental animals, even in scenarios where 3D triangulation is not feasible. The framework enables accurate 3D pose estimation without the need for complex camera arrays and tedious calibration procedures, even in the presence of occluded body parts in freely behaving animals.

NATURE METHODS (2021)

Article Biology

Future trends in measuring physiology in free-living animals

H. J. Williams et al.

Summary: Ecophysiology research has been mainly conducted in controlled laboratory settings due to technological limitations in monitoring physiological parameters in wild animals. Future research directions include technological advancements, financial and ethical challenges, and the potential for collaboration with human health monitoring to advance the field of physiologging in free-ranging animals.

PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES (2021)

Review Biology

Animal tag technology keeps coming of age: an engineering perspective

Mark D. Holton et al.

Summary: Animal-borne tags have become highly sophisticated tools for studying wild animals, but their design and implementation require engineers to balance performance and function under tough conditions while minimizing impact on animal wellbeing. Understanding engineering issues in tag design is important for both biologists and engineers to improve tag construction and research outcomes. Embracing conventional technology and new approaches will further advance our understanding of wild-animal biology using smart tags.

PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES (2021)

Review Ecology

Certainty and integration of options in animal movement

Hannah J. Williams et al.

Summary: Physical energy landscape determines species-specific cost of movement, while social sampling increases individual certainty in unpredictable environments. Developing an optimal movement theory that integrates ecological landscapes can predict individual movement patterns and investigate aggregation dynamics.

TRENDS IN ECOLOGY & EVOLUTION (2021)

Article Biology

A framework for studying behavioral evolution by reconstructing ancestral repertoires

Damian G. Hernandez et al.

Summary: The study introduces a new framework for simultaneously studying the evolution of multiple behaviors. By measuring the behavioral repertoire of fruit flies and estimating intra- and inter-species behavioral covariances, the research found similarities in the covariance structure of intra-specific behavioral variation and proposed a method to identify groups of behaviors that appear to have evolved in a correlated manner.
Review Computer Science, Information Systems

Principles and Practice of Explainable Machine Learning

Vaishak Belle et al.

Summary: Artificial intelligence offers opportunities for improving private and public life, but understanding the decisions made by AI systems to trust them poses a significant challenge. This report focuses on data-driven methods, particularly machine learning and pattern recognition models, to survey and distill results from literature. It aims to help industry practitioners better understand the field of explainable machine learning and apply the right tools.

FRONTIERS IN BIG DATA (2021)

Article Biochemistry & Molecular Biology

Probabilistic Models of Larval Zebrafish Behavior Reveal Structure on Many Scales

Robert Evan Johnson et al.

CURRENT BIOLOGY (2020)

Article Neurosciences

Deep learning tools for the measurement of animal behavior in neuroscience

Mackenzie Weygandt Mathis et al.

CURRENT OPINION IN NEUROBIOLOGY (2020)

Article Computer Science, Artificial Intelligence

Video Object Segmentation and Tracking: A Survey

Rui Yao et al.

ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY (2020)

Article Multidisciplinary Sciences

Automatic Identification of Individual Primates with Deep Learning Techniques

Songtao Guo et al.

ISCIENCE (2020)

Article Ecology

Deep learning-based methods for individual recognition in small birds

Andre C. Ferreira et al.

METHODS IN ECOLOGY AND EVOLUTION (2020)

Article Neurosciences

Revealing the structure of pharmacobehavioral space through motion sequencing

Alexander B. Wiltschko et al.

NATURE NEUROSCIENCE (2020)

Review Neurosciences

Quantifying behavior to understand the brain

Talmo D. Pereira et al.

NATURE NEUROSCIENCE (2020)

Review Computer Science, Information Systems

Review of Automatic Detection and Classification Techniques for Cetacean Vocalization

Ayinde M. Usman et al.

IEEE ACCESS (2020)

Article Multidisciplinary Sciences

Chimpanzee face recognition from videos in the wild using deep learning

Daniel Schofield et al.

SCIENCE ADVANCES (2019)

Review Neurosciences

Computational Neuroethology: A Call to Action

Sandeep Robert Datta et al.

NEURON (2019)

Article Biochemical Research Methods

idtracker.ai: tracking all individuals in small or large collectives of unmarked animals

Francisco Romero-Ferrero et al.

NATURE METHODS (2019)

Review Ecology

Advances in Microclimate Ecology Arising from Remote Sensing

Florian Zellweger et al.

TRENDS IN ECOLOGY & EVOLUTION (2019)

Review Biology

Measuring behavior across scales

Gordon J. Berman

BMC BIOLOGY (2018)

Article Physics, Multidisciplinary

Ethology as a physical science

Andre E. X. Brown et al.

NATURE PHYSICS (2018)

Article Biology

Synchronization, coordination and collective sensing during thermalling flight of freely migrating white storks

Mate Nagy et al.

PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES (2018)

Article Multidisciplinary Sciences

From local collective behavior to global migratory patterns in white storks

Andrea Flack et al.

SCIENCE (2018)

Article Biochemistry & Molecular Biology

Resource Ephemerality Drives Social Foraging in Bats

Katya Egert-Berg et al.

CURRENT BIOLOGY (2018)

Article Multidisciplinary Sciences

Can we open the black box of AI?

Davide Castelvecchi

NATURE (2016)

Article Multidisciplinary Sciences

Predictability and hierarchy in Drosophila behavior

Gordon J. Berman et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2016)

Review Multidisciplinary Sciences

Deep learning

Yann LeCun et al.

NATURE (2015)

Article Neurosciences

Mapping Sub-Second Structure in Mouse Behavior

Alexander B. Wiltschko et al.

NEURON (2015)

Article Biology

Maximally informative foraging by Caenorhabditis elegans

Adam J. Calhoun et al.

Article Multidisciplinary Sciences

Social Learning of Migratory Performance

Thomas Mueller et al.

SCIENCE (2013)

Article Biochemistry & Molecular Biology

The Dynamics of Coordinated Group Hunting and Collective Information Transfer among Schooling Prey

Nils Olav Handegard et al.

CURRENT BIOLOGY (2012)

Article Multidisciplinary Sciences

A movement ecology paradigm for unifying organismal movement research

Ran Nathan et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2008)