Preliminary Development of a Database for Detecting Active Mounting Behaviors Using Signals Acquired from IoT Collars in Free-Grazing Cattle

This study presents the development of a database for detecting active mounts, utilizing IoT collars equipped with Inertial Measurement Units (IMUs) installed on eight Holstein Friesian cows, along with video recordings from a long-range PTZ camera mounted in a central pole for event labeling in the...

Full description

Saved in:
Bibliographic Details
Main Authors: Miguel Guarda-Vera, Carlos Muñoz-Poblete
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/10/3233
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849719375079145472
author Miguel Guarda-Vera
Carlos Muñoz-Poblete
author_facet Miguel Guarda-Vera
Carlos Muñoz-Poblete
author_sort Miguel Guarda-Vera
collection DOAJ
description This study presents the development of a database for detecting active mounts, utilizing IoT collars equipped with Inertial Measurement Units (IMUs) installed on eight Holstein Friesian cows, along with video recordings from a long-range PTZ camera mounted in a central pole for event labeling in the natural environment when free grazing. The resulting database comprises 415 labeled events associated with various behaviors, containing acceleration signals in both the Body and World Frame of reference and gyroscope signals. A Support Vector Machine (SVM) algorithm is implemented to evaluate the effectiveness of the dataset in detecting active mounts and to compare training performance using both frames. The algorithm achieves an average F1 Score of 88.6% for the World Frame of reference, showing a significant improvement compared to the algorithm trained with Body Frame (78.6%) when both are trained with the same 112 features. After applying feature selection using Sequential Backward Selection (SBS), the SVM exhibits a minor performance difference between the F1 Score obtained with the two reference frames (89.7% World Frame vs. 91.5% Body Frame). This study provides a public dataset and a replicable methodology, facilitating future research on movement-based behavior classification in cattle.
format Article
id doaj-art-efb067e0433b4e9ab6b5f981ced4c0d2
institution DOAJ
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-efb067e0433b4e9ab6b5f981ced4c0d22025-08-20T03:12:09ZengMDPI AGSensors1424-82202025-05-012510323310.3390/s25103233Preliminary Development of a Database for Detecting Active Mounting Behaviors Using Signals Acquired from IoT Collars in Free-Grazing CattleMiguel Guarda-Vera0Carlos Muñoz-Poblete1Magíster en Ciencias de la Ingeniería, Universidad de La Frontera, Temuco 4811230, ChileDepartamento de Ingeniería Eléctrica, Universidad de La Frontera, Temuco 4811230, ChileThis study presents the development of a database for detecting active mounts, utilizing IoT collars equipped with Inertial Measurement Units (IMUs) installed on eight Holstein Friesian cows, along with video recordings from a long-range PTZ camera mounted in a central pole for event labeling in the natural environment when free grazing. The resulting database comprises 415 labeled events associated with various behaviors, containing acceleration signals in both the Body and World Frame of reference and gyroscope signals. A Support Vector Machine (SVM) algorithm is implemented to evaluate the effectiveness of the dataset in detecting active mounts and to compare training performance using both frames. The algorithm achieves an average F1 Score of 88.6% for the World Frame of reference, showing a significant improvement compared to the algorithm trained with Body Frame (78.6%) when both are trained with the same 112 features. After applying feature selection using Sequential Backward Selection (SBS), the SVM exhibits a minor performance difference between the F1 Score obtained with the two reference frames (89.7% World Frame vs. 91.5% Body Frame). This study provides a public dataset and a replicable methodology, facilitating future research on movement-based behavior classification in cattle.https://www.mdpi.com/1424-8220/25/10/3233estrus in cowsactive mountsIoT collarIMUpublic databasemachine learning
spellingShingle Miguel Guarda-Vera
Carlos Muñoz-Poblete
Preliminary Development of a Database for Detecting Active Mounting Behaviors Using Signals Acquired from IoT Collars in Free-Grazing Cattle
Sensors
estrus in cows
active mounts
IoT collar
IMU
public database
machine learning
title Preliminary Development of a Database for Detecting Active Mounting Behaviors Using Signals Acquired from IoT Collars in Free-Grazing Cattle
title_full Preliminary Development of a Database for Detecting Active Mounting Behaviors Using Signals Acquired from IoT Collars in Free-Grazing Cattle
title_fullStr Preliminary Development of a Database for Detecting Active Mounting Behaviors Using Signals Acquired from IoT Collars in Free-Grazing Cattle
title_full_unstemmed Preliminary Development of a Database for Detecting Active Mounting Behaviors Using Signals Acquired from IoT Collars in Free-Grazing Cattle
title_short Preliminary Development of a Database for Detecting Active Mounting Behaviors Using Signals Acquired from IoT Collars in Free-Grazing Cattle
title_sort preliminary development of a database for detecting active mounting behaviors using signals acquired from iot collars in free grazing cattle
topic estrus in cows
active mounts
IoT collar
IMU
public database
machine learning
url https://www.mdpi.com/1424-8220/25/10/3233
work_keys_str_mv AT miguelguardavera preliminarydevelopmentofadatabasefordetectingactivemountingbehaviorsusingsignalsacquiredfromiotcollarsinfreegrazingcattle
AT carlosmunozpoblete preliminarydevelopmentofadatabasefordetectingactivemountingbehaviorsusingsignalsacquiredfromiotcollarsinfreegrazingcattle