Cargando…

Development and Analysis of a CNN- and Transfer-Learning-Based Classification Model for Automated Dairy Cow Feeding Behavior Recognition from Accelerometer Data

Due to technological developments, wearable sensors for monitoring the behavior of farm animals have become cheaper, have a longer lifespan and are more accessible for small farms and researchers. In addition, advancements in deep machine learning methods provide new opportunities for behavior recog...

Descripción completa

Detalles Bibliográficos
Autores principales: Bloch, Victor, Frondelius, Lilli, Arcidiacono, Claudia, Mancino, Massimo, Pastell, Matti
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10006954/
https://www.ncbi.nlm.nih.gov/pubmed/36904813
http://dx.doi.org/10.3390/s23052611
_version_ 1784905398689464320
author Bloch, Victor
Frondelius, Lilli
Arcidiacono, Claudia
Mancino, Massimo
Pastell, Matti
author_facet Bloch, Victor
Frondelius, Lilli
Arcidiacono, Claudia
Mancino, Massimo
Pastell, Matti
author_sort Bloch, Victor
collection PubMed
description Due to technological developments, wearable sensors for monitoring the behavior of farm animals have become cheaper, have a longer lifespan and are more accessible for small farms and researchers. In addition, advancements in deep machine learning methods provide new opportunities for behavior recognition. However, the combination of the new electronics and algorithms are rarely used in PLF, and their possibilities and limitations are not well-studied. In this study, a CNN-based model for the feeding behavior classification of dairy cows was trained, and the training process was analyzed considering a training dataset and the use of transfer learning. Commercial acceleration measuring tags, which were connected by BLE, were fitted to cow collars in a research barn. Based on a dataset including 33.7 cow × days (21 cows recorded during 1–3 days) of labeled data and an additional free-access dataset with similar acceleration data, a classifier with F1 = 93.9% was developed. The optimal classification window size was 90 s. In addition, the influence of the training dataset size on the classifier accuracy was analyzed for different neural networks using the transfer learning technique. While the size of the training dataset was being increased, the rate of the accuracy improvement decreased. Beginning from a specific point, the use of additional training data can be impractical. A relatively high accuracy was achieved with few training data when the classifier was trained using randomly initialized model weights, and a higher accuracy was achieved when transfer learning was used. These findings can be used for the estimation of the necessary dataset size for training neural network classifiers intended for other environments and conditions.
format Online
Article
Text
id pubmed-10006954
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-100069542023-03-12 Development and Analysis of a CNN- and Transfer-Learning-Based Classification Model for Automated Dairy Cow Feeding Behavior Recognition from Accelerometer Data Bloch, Victor Frondelius, Lilli Arcidiacono, Claudia Mancino, Massimo Pastell, Matti Sensors (Basel) Article Due to technological developments, wearable sensors for monitoring the behavior of farm animals have become cheaper, have a longer lifespan and are more accessible for small farms and researchers. In addition, advancements in deep machine learning methods provide new opportunities for behavior recognition. However, the combination of the new electronics and algorithms are rarely used in PLF, and their possibilities and limitations are not well-studied. In this study, a CNN-based model for the feeding behavior classification of dairy cows was trained, and the training process was analyzed considering a training dataset and the use of transfer learning. Commercial acceleration measuring tags, which were connected by BLE, were fitted to cow collars in a research barn. Based on a dataset including 33.7 cow × days (21 cows recorded during 1–3 days) of labeled data and an additional free-access dataset with similar acceleration data, a classifier with F1 = 93.9% was developed. The optimal classification window size was 90 s. In addition, the influence of the training dataset size on the classifier accuracy was analyzed for different neural networks using the transfer learning technique. While the size of the training dataset was being increased, the rate of the accuracy improvement decreased. Beginning from a specific point, the use of additional training data can be impractical. A relatively high accuracy was achieved with few training data when the classifier was trained using randomly initialized model weights, and a higher accuracy was achieved when transfer learning was used. These findings can be used for the estimation of the necessary dataset size for training neural network classifiers intended for other environments and conditions. MDPI 2023-02-27 /pmc/articles/PMC10006954/ /pubmed/36904813 http://dx.doi.org/10.3390/s23052611 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Bloch, Victor
Frondelius, Lilli
Arcidiacono, Claudia
Mancino, Massimo
Pastell, Matti
Development and Analysis of a CNN- and Transfer-Learning-Based Classification Model for Automated Dairy Cow Feeding Behavior Recognition from Accelerometer Data
title Development and Analysis of a CNN- and Transfer-Learning-Based Classification Model for Automated Dairy Cow Feeding Behavior Recognition from Accelerometer Data
title_full Development and Analysis of a CNN- and Transfer-Learning-Based Classification Model for Automated Dairy Cow Feeding Behavior Recognition from Accelerometer Data
title_fullStr Development and Analysis of a CNN- and Transfer-Learning-Based Classification Model for Automated Dairy Cow Feeding Behavior Recognition from Accelerometer Data
title_full_unstemmed Development and Analysis of a CNN- and Transfer-Learning-Based Classification Model for Automated Dairy Cow Feeding Behavior Recognition from Accelerometer Data
title_short Development and Analysis of a CNN- and Transfer-Learning-Based Classification Model for Automated Dairy Cow Feeding Behavior Recognition from Accelerometer Data
title_sort development and analysis of a cnn- and transfer-learning-based classification model for automated dairy cow feeding behavior recognition from accelerometer data
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10006954/
https://www.ncbi.nlm.nih.gov/pubmed/36904813
http://dx.doi.org/10.3390/s23052611
work_keys_str_mv AT blochvictor developmentandanalysisofacnnandtransferlearningbasedclassificationmodelforautomateddairycowfeedingbehaviorrecognitionfromaccelerometerdata
AT frondeliuslilli developmentandanalysisofacnnandtransferlearningbasedclassificationmodelforautomateddairycowfeedingbehaviorrecognitionfromaccelerometerdata
AT arcidiaconoclaudia developmentandanalysisofacnnandtransferlearningbasedclassificationmodelforautomateddairycowfeedingbehaviorrecognitionfromaccelerometerdata
AT mancinomassimo developmentandanalysisofacnnandtransferlearningbasedclassificationmodelforautomateddairycowfeedingbehaviorrecognitionfromaccelerometerdata
AT pastellmatti developmentandanalysisofacnnandtransferlearningbasedclassificationmodelforautomateddairycowfeedingbehaviorrecognitionfromaccelerometerdata