Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Force Classification01:22

Force Classification

2.3K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
2.3K
Classification of Systems-II01:31

Classification of Systems-II

460
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
460
Classification of Systems-I01:26

Classification of Systems-I

552
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
552

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

First fatal human bloodstream infection caused by <i>Macrococcus caseolyticus</i> subsp. <i>caseolyticus</i> in China: genomic insights into virulence and antimicrobial resistance.

Frontiers in cellular and infection microbiology·2026
Same author

GMD-YOLO: A Dual-Modality Framework with Multi-Scale Enhancement and Adaptive Fusion for PV Fault Detection.

Sensors (Basel, Switzerland)·2026
Same author

Mechanical Damage Modulates Bacterial and Fungal Succession on the Surface of <i>Hypsizygus marmoreus</i> During Refrigerated Storage.

Microorganisms·2026
Same author

Comorbidity prevalence of degenerative lumbar scoliosis in lumbar spinal stenosis: age-related radiological and symptomatological characteristics in a large sample.

Frontiers in neurology·2026
Same author

Genomic characterization and pathogenicity assessment of a novel strain of duck reovirus identified in China.

Frontiers in microbiology·2026
Same author

Rational Design, Synthesis, and Systematic Evaluation of Redox-Responsive SN-38 Prodrugs for Selective Activation in Hypoxic Tumor Microenvironments.

Pharmaceuticals (Basel, Switzerland)·2026

Related Experiment Video

Updated: Jan 17, 2026

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

829

DMSF-YOLO: Cow Behavior Recognition Algorithm Based on Dynamic Mechanism and Multi-Scale Feature Fusion.

Changfeng Wu1,2,3, Jiandong Fang1,2,3, Xiuling Wang1,2,3

  • 1College of Information Engineering, Inner Mongolia University of Technology, Hohhot 010051, China.

Sensors (Basel, Switzerland)
|September 19, 2025
PubMed
Summary

This study introduces DMSF-YOLO, an advanced algorithm for recognizing dairy cow behaviors like lying, standing, and eating. The model accurately identifies multiple cow activities in complex farm settings, improving disease prevention and herd management.

Keywords:
YOLOv11behavior recognitioncowdynamic mechanismmulti-scale feature fusion

More Related Videos

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

7.2K

Related Experiment Videos

Last Updated: Jan 17, 2026

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

829
Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

7.2K

Area of Science:

  • Computer Vision and Machine Learning
  • Animal Science and Husbandry
  • Agricultural Technology

Background:

  • Dairy cow behavior is a key indicator of health and welfare, crucial for timely disease intervention and farm management.
  • Complex farm environments present challenges for behavior recognition due to background noise, multi-scale behavior variations, similar actions, and small target detection difficulties.

Purpose of the Study:

  • To develop a novel algorithm, DMSF-YOLO, for accurate and rapid recognition of multiple dairy cow behaviors in real-world farm conditions.
  • To enhance the model's capability in handling multi-scale features, background interference, and distinguishing similar behaviors.

Main Methods:

  • Proposed DMSF-YOLO algorithm integrating dynamic mechanisms and multi-scale feature fusion for behavior recognition.
  • Introduced Multi-Scale Feature Fusion Convolution (MSFConv) module to extract and fuse features across different scales.
  • Designed C2BRA module with a two-layer routing attention mechanism for dynamic feature extraction and background suppression.
  • Incorporated Dynamic Head detection head to improve scale, spatial, and task-specific perception for enhanced feature extraction.

Main Results:

  • The DMSF-YOLO model demonstrated significant improvements on a custom dataset, increasing precision (P) by 2.4%, recall (R) by 3%, mAP50 by 1.6%, and F1 score by 2.7%.
  • Achieved high Frames Per Second (FPS) indicating efficient real-time processing capabilities.
  • Effectively suppressed background interference, dynamically extracted multi-scale features, and improved detection of small targets and similar behaviors.

Conclusions:

  • The DMSF-YOLO algorithm significantly enhances the accuracy and overall performance of dairy cow behavior recognition in complex environments.
  • The model's ability to handle multi-scale features, background noise, and similar behaviors makes it suitable for practical applications in dairy farm management.
  • This technology provides a robust tool for automated monitoring, enabling timely interventions and improving animal health and welfare.