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

You might also read

Related Articles

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

Sort by
Same author

What information counts when detecting mastitis in automatic milking systems? A mixed methods approach from a Swedish perspective.

Journal of dairy science·2025
Same author

Behavioural responses of dairy cows and calves to fenceline weaning after 4 or 6 months of full cow-calf contact.

Animal : an international journal of animal bioscience·2025
Same author

Social network analysis to predict social behavior in dairy cattle.

JDS communications·2024
Same author

New insight into social relationships in dairy cows and how time of birth, parity, and relatedness affect spatial interactions later in life.

Journal of dairy science·2023
Same author

Cow characteristics associated with the variation in number of contacts between dairy cows.

Journal of dairy science·2023
Same author

Exploration of body weight in 115 000 young adult dogs of 72 breeds.

Scientific reports·2023

Related Experiment Video

Updated: Oct 30, 2025

An Efficient Single—Person Technique for Milk Sampling from Laboratory Mice
04:56

An Efficient Single—Person Technique for Milk Sampling from Laboratory Mice

Published on: March 28, 2025

1.0K

Detecting and predicting changes in milk homogeneity using data from automatic milking systems.

D Anglart1, U Emanuelson2, L Rönnegård3

  • 1DeLaval International AB, PO Box 39, SE-147 21 Tumba, Sweden; Swedish University of Agricultural Sciences, Department of Clinical Sciences, PO Box 7054, SE-750 07 Uppsala, Sweden.

Journal of Dairy Science
|July 5, 2021
PubMed
Summary

Detecting milk clots using automatic milking systems (AMS) is possible, though prediction accuracy for milk homogeneity changes remains low. Models showed high specificity but low sensitivity in identifying clots, with better performance for heavier clot cases.

Keywords:
clinical mastitisclotdairy cowmultilayer perceptron

More Related Videos

Milk Collection in the Rat Using Capillary Tubes and Estimation of Milk Fat Content by Creamatocrit
07:38

Milk Collection in the Rat Using Capillary Tubes and Estimation of Milk Fat Content by Creamatocrit

Published on: December 16, 2015

12.7K
Individualized Reconstitution of Human Milk Microbiota: A Feasible Approach in Real-World Settings
04:16

Individualized Reconstitution of Human Milk Microbiota: A Feasible Approach in Real-World Settings

Published on: February 7, 2025

689

Related Experiment Videos

Last Updated: Oct 30, 2025

An Efficient Single—Person Technique for Milk Sampling from Laboratory Mice
04:56

An Efficient Single—Person Technique for Milk Sampling from Laboratory Mice

Published on: March 28, 2025

1.0K
Milk Collection in the Rat Using Capillary Tubes and Estimation of Milk Fat Content by Creamatocrit
07:38

Milk Collection in the Rat Using Capillary Tubes and Estimation of Milk Fat Content by Creamatocrit

Published on: December 16, 2015

12.7K
Individualized Reconstitution of Human Milk Microbiota: A Feasible Approach in Real-World Settings
04:16

Individualized Reconstitution of Human Milk Microbiota: A Feasible Approach in Real-World Settings

Published on: February 7, 2025

689

Area of Science:

  • Dairy Science
  • Animal Husbandry
  • Machine Learning in Agriculture

Background:

  • Mastitis detection in cows is crucial for milk quality and animal health.
  • Manual prestripping and inline filter inspection are traditional methods for detecting milk clots.
  • These manual methods are incompatible with automatic milking systems (AMS).

Purpose of the Study:

  • To investigate the feasibility of using AMS data to detect and predict changes in milk homogeneity (presence of clots).
  • To evaluate the performance of machine learning models in identifying milk clots during milking.

Main Methods:

  • Collected 21,335 quarter-level milk inspections from 5,424 milkings across 624 cows on 4 farms.
  • Visual inspection of inline filters for clots, with density scoring.
  • Utilized AMS data (milk yield, flow, conductivity, somatic cell counts) as input for four multilayer perceptron models.

Main Results:

  • Models achieved high specificity (98-100%) in identifying milkings without clots.
  • Sensitivity for detecting milkings with clots was low (highest at 26% for single milking detection).
  • Positive predictive value was relatively high (up to 72% for 30-h periods), especially for heavier clot cases.

Conclusions:

  • Detecting changes in milk homogeneity using AMS data appears feasible.
  • Current prediction performance for milk clots, based on the study's definitions, is poor.
  • Further research is needed to improve model sensitivity and predictive accuracy for clot detection in AMS.