Simple Behavioral Analysis (SimBA) as a platform for explainable machine learning in behavioral neuroscience

Nature Neuroscience, Journal Year: 2024, Volume and Issue: 27(7), P. 1411 - 1424

Published: May 22, 2024

Language: Английский

---

Automatically annotated motion tracking identifies a distinct social behavioral profile following chronic social defeat stress

Nature Communications, Journal Year: 2023, Volume and Issue: 14(1)

Published: July 18, 2023

Severe stress exposure increases the risk of stress-related disorders such as major depressive disorder (MDD). An essential characteristic MDD is impairment social functioning and lack motivation. Chronic defeat an established animal model for research, which induces a cascade physiological behavioral changes. Current markerless pose estimation tools allow more complex naturalistic tests. Here, we introduce open-source tool DeepOF to investigate individual profile in mice by providing supervised unsupervised pipelines using DeepLabCut-annotated data. Applying this chronic male mice, detect distinct stress-induced pattern, was particularly observed at beginning novel encounter fades with time due habituation. In addition, while classical avoidance task does identify differences, both provide clearer detailed profile. Moreover, aims facilitate reproducibility unification classification tool, can advance study rodent behavior, thereby enabling biological insights and, example, subsequent drug development psychiatric disorders.

Language: Английский

---

The quest to develop automated systems for monitoring animal behavior

Applied Animal Behaviour Science, Journal Year: 2023, Volume and Issue: 265, P. 106000 - 106000

Published: July 17, 2023

Automated behavior analysis (ABA) strategies are being researched at a rapid rate to detect an array of behaviors across range species. There is growing optimism that soon ethologists will not have manually decode hours (and hours) animal videos, but instead computers process them for us. However, before we assume ABA ready practical use, it important take realistic look exactly what developed, the expertise used develop it, and context in which these studies occur. Once understand common pitfalls occurring during development identify limitations, can construct robust tools achieve automated (ultimately even continuous real time) behavioral data, allowing more detailed or longer-term on larger numbers animals than ever before. only as good trained be. A key starting point having annotated data model training assessment. most developers ethology. Often no formal ethogram developed descriptions target publications limited inaccurate. In addition, also frequently using small datasets, lack sufficient variability morphometrics, activities, camera viewpoints, environmental features be generalizable. Thus, often needs further validated satisfactorily different populations under other conditions, research purposes. Multidisciplinary teams researchers including ethicists well computer scientists, engineers needed help address problems when applying vision measure behavior. Reference datasets detection should generated shared include image annotations, baseline analyses benchmarking. Also critical standards creating such reference best practices methods validating results from ensure they At present, handful publicly available exist tools. As work realize promise subsequent precision livestock farming technologies) behavior, clear understanding practices, access accurately networking among increase our chances successes.

Language: Английский

---

LabGym: Quantification of user-defined animal behaviors using learning-based holistic assessment

Cell Reports Methods, Journal Year: 2023, Volume and Issue: 3(3), P. 100415 - 100415

Published: Feb. 24, 2023

Quantifying animal behavior is important for biological research. Identifying behaviors the prerequisite of quantifying them. Current computational tools behavioral quantification typically use high-level properties such as body poses to identify behaviors, which constrains information available a holistic assessment. Here we report

Language: Английский

---

Hierarchical action encoding in prefrontal cortex of freely moving macaques

Cell Reports, Journal Year: 2023, Volume and Issue: 42(9), P. 113091 - 113091

Published: Aug. 31, 2023

Our natural behavioral repertoires include coordinated actions of characteristic types. To better understand how neural activity relates to the expression and action switches, we studied macaques performing a freely moving foraging task in an open environment. We developed novel analysis pipeline that can identify meaningful units behavior, corresponding recognizable such as sitting, walking, jumping, climbing. On basis transition probabilities between these actions, found behavior is organized modular hierarchical fashion. that, after regressing out many potential confounders, are associated with specific patterns firing each six prefrontal brain regions overall, encoding category progressively stronger more dorsal caudal regions. Together, results establish link selection primate on one hand neuronal other.

Language: Английский

---

Multi-animal 3D social pose estimation, identification and behaviour embedding with a few-shot learning framework

Nature Machine Intelligence, Journal Year: 2024, Volume and Issue: 6(1), P. 48 - 61

Published: Jan. 8, 2024

Abstract The quantification of animal social behaviour is an essential step to reveal brain functions and psychiatric disorders during interaction phases. While deep learning-based approaches have enabled precise pose estimation, identification behavioural classification multi-animals, their application challenged by the lack well-annotated datasets. Here we show a computational framework, Social Behavior Atlas (SBeA) used overcome problem caused limited SBeA uses much smaller number labelled frames for multi-animal three-dimensional achieves label-free recognition successfully applies unsupervised dynamic learning classification. validated uncover previously overlooked phenotypes autism spectrum disorder knockout mice. Our results also demonstrate that can achieve high performance across various species using existing customized These findings highlight potential quantifying subtle behaviours in fields neuroscience ecology.

Language: Английский

---

MCP: Multi-Chicken Pose Estimation Based on Transfer Learning

Animals, Journal Year: 2024, Volume and Issue: 14(12), P. 1774 - 1774

Published: June 12, 2024

Poultry managers can better understand the state of poultry through behavior analysis. As one key steps in analysis, accurate estimation posture is focus this research. This study mainly analyzes a top-down pose method multiple chickens. Therefore, we propose “multi-chicken pose” (MCP), system for chickens deep learning. Firstly, find position each chicken from image via detector; then, an estimate made using network, which based on transfer On basis, pixel error (PE), root mean square (RMSE), and quantity distribution points are analyzed according to improved keypoint similarity (CKS). The experimental results show that algorithm scores different evaluation metrics average precision (mAP) 0.652, recall (mAR) 0.742, percentage correct keypoints (PCKs) 0.789, RMSE 17.30 pixels. To best our knowledge, first time learning has been used as objects. provide new path future analysis

Language: Английский

---

Elephants and algorithms: a review of the current and future role of AI in elephant monitoring

Journal of The Royal Society Interface, Journal Year: 2023, Volume and Issue: 20(208)

Published: Nov. 1, 2023

Artificial intelligence (AI) and machine learning (ML) present revolutionary opportunities to enhance our understanding of animal behaviour conservation strategies. Using elephants, a crucial species in Africa Asia’s protected areas, as focal point, we delve into the role AI ML their conservation. Given increasing amounts data gathered from variety sensors like cameras, microphones, geophones, drones satellites, challenge lies managing interpreting this vast data. New techniques offer solutions streamline process, helping us extract vital information that might otherwise be overlooked. This paper focuses on different AI-driven monitoring methods potential for improving elephant Collaborative efforts between experts ecological researchers are essential leveraging these innovative technologies enhanced wildlife conservation, setting precedent numerous other species.

Language: Английский

---

Open-source software for automated rodent behavioral analysis

Frontiers in Neuroscience, Journal Year: 2023, Volume and Issue: 17

Published: April 17, 2023

Rodent behavioral analysis is a major specialization in experimental psychology and neuroscience. Rodents display wide range of species-specific behaviors, not only their natural habitats but also under testing controlled laboratory conditions. Detecting categorizing these different kinds behavior consistent way challenging task. Observing analyzing rodent behaviors manually limits the reproducibility replicability analyses due to potentially low inter-rater reliability. The advancement accessibility object tracking pose estimation technologies led several open-source artificial intelligence (AI) tools that utilize various algorithms for analysis. These software provide high consistency compared manual methods, offer more flexibility than commercial systems by allowing custom-purpose modifications specific research needs. Open-source reviewed this paper automated or semi-automated methods detecting using hand-coded heuristics, machine learning, neural networks. underlying show key differences internal dynamics, interfaces, user-friendliness, variety outputs. This work reviews algorithms, capability, functionality, features properties tools, discusses how emergent technology facilitates quantification research.

Language: Английский

---

Advancing social behavioral neuroscience by integrating ethology and comparative psychology methods through machine learning

Neuroscience & Biobehavioral Reviews, Journal Year: 2023, Volume and Issue: 151, P. 105243 - 105243

Published: May 22, 2023

Social behavior is naturally occurring in vertebrate species, which holds a strong evolutionary component and crucial for the normal development survival of individuals throughout life. Behavioral neuroscience has seen different influential methods social behavioral phenotyping. The ethological research approach extensively investigated natural habitats, while comparative psychology was developed utilizing standardized univariate tests. advanced precise tracking tools, together with post-tracking analysis packages, recently enabled novel phenotyping method, that includes strengths both approaches. implementation such will be beneficial fundamental but also enable an increased understanding influences many factors can influence behavior, as stress exposure. Furthermore, future increase number data modalities, sensory, physiological, neuronal activity data, thereby significantly enhance our biological basis guide intervention strategies abnormalities psychiatric disorders.

Language: Английский

---