Uncovering Patterns in Dairy Cow Behaviour: A Deep Learning Approach with Tri-Axial Accelerometer Data
The accurate detection of behavioural changes represents a promising method of detecting the early onset of disease in dairy cows. This study assessed the performance of deep learning (DL) in classifying dairy cows’ behaviour from accelerometry data acquired by single sensors on the cows’ left flank...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/13/11/1886 |
| _version_ | 1797597980911468544 |
|---|---|
| author | Paolo Balasso Cristian Taccioli Lorenzo Serva Luisa Magrin Igino Andrighetto Giorgio Marchesini |
| author_facet | Paolo Balasso Cristian Taccioli Lorenzo Serva Luisa Magrin Igino Andrighetto Giorgio Marchesini |
| author_sort | Paolo Balasso |
| collection | DOAJ |
| description | The accurate detection of behavioural changes represents a promising method of detecting the early onset of disease in dairy cows. This study assessed the performance of deep learning (DL) in classifying dairy cows’ behaviour from accelerometry data acquired by single sensors on the cows’ left flanks and compared the results with those obtained through classical machine learning (ML) from the same raw data. Twelve cows with a tri-axial accelerometer were observed for 136 ± 29 min each to detect five main behaviours: standing still, moving, feeding, ruminating and resting. For each 8 s time interval, 15 metrics were calculated, obtaining a dataset of 211,720 observation units and 15 columns. The entire dataset was randomly split into training (80%) and testing (20%) datasets. The DL accuracy, precision and sensitivity/recall were calculated and compared with the performance of classical ML models. The best predictive model was an 8-layer convolutional neural network (CNN) with an overall accuracy and F1 score equal to 0.96. The precision, sensitivity/recall and F1 score of single behaviours had the following ranges: 0.93–0.99. The CNN outperformed all the classical ML algorithms. The CNN used to monitor the cows’ conditions showed an overall high performance in successfully predicting multiple behaviours using a single accelerometer. |
| first_indexed | 2024-03-11T03:12:57Z |
| format | Article |
| id | doaj.art-dd896541c717450bb61a525f8de47c67 |
| institution | Directory Open Access Journal |
| issn | 2076-2615 |
| language | English |
| last_indexed | 2024-03-11T03:12:57Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Animals |
| spelling | doaj.art-dd896541c717450bb61a525f8de47c672023-11-18T07:31:01ZengMDPI AGAnimals2076-26152023-06-011311188610.3390/ani13111886Uncovering Patterns in Dairy Cow Behaviour: A Deep Learning Approach with Tri-Axial Accelerometer DataPaolo Balasso0Cristian Taccioli1Lorenzo Serva2Luisa Magrin3Igino Andrighetto4Giorgio Marchesini5Dipartimento di Medicina Animale, Produzioni e Salute, Università degli Studi di Padova, 35020 Legnaro, ItalyDipartimento di Medicina Animale, Produzioni e Salute, Università degli Studi di Padova, 35020 Legnaro, ItalyDipartimento di Medicina Animale, Produzioni e Salute, Università degli Studi di Padova, 35020 Legnaro, ItalyDipartimento di Medicina Animale, Produzioni e Salute, Università degli Studi di Padova, 35020 Legnaro, ItalyDipartimento di Medicina Animale, Produzioni e Salute, Università degli Studi di Padova, 35020 Legnaro, ItalyDipartimento di Medicina Animale, Produzioni e Salute, Università degli Studi di Padova, 35020 Legnaro, ItalyThe accurate detection of behavioural changes represents a promising method of detecting the early onset of disease in dairy cows. This study assessed the performance of deep learning (DL) in classifying dairy cows’ behaviour from accelerometry data acquired by single sensors on the cows’ left flanks and compared the results with those obtained through classical machine learning (ML) from the same raw data. Twelve cows with a tri-axial accelerometer were observed for 136 ± 29 min each to detect five main behaviours: standing still, moving, feeding, ruminating and resting. For each 8 s time interval, 15 metrics were calculated, obtaining a dataset of 211,720 observation units and 15 columns. The entire dataset was randomly split into training (80%) and testing (20%) datasets. The DL accuracy, precision and sensitivity/recall were calculated and compared with the performance of classical ML models. The best predictive model was an 8-layer convolutional neural network (CNN) with an overall accuracy and F1 score equal to 0.96. The precision, sensitivity/recall and F1 score of single behaviours had the following ranges: 0.93–0.99. The CNN outperformed all the classical ML algorithms. The CNN used to monitor the cows’ conditions showed an overall high performance in successfully predicting multiple behaviours using a single accelerometer.https://www.mdpi.com/2076-2615/13/11/1886convolutional neural networkmachine learningprecision livestock farminganimal welfare |
| spellingShingle | Paolo Balasso Cristian Taccioli Lorenzo Serva Luisa Magrin Igino Andrighetto Giorgio Marchesini Uncovering Patterns in Dairy Cow Behaviour: A Deep Learning Approach with Tri-Axial Accelerometer Data Animals convolutional neural network machine learning precision livestock farming animal welfare |
| title | Uncovering Patterns in Dairy Cow Behaviour: A Deep Learning Approach with Tri-Axial Accelerometer Data |
| title_full | Uncovering Patterns in Dairy Cow Behaviour: A Deep Learning Approach with Tri-Axial Accelerometer Data |
| title_fullStr | Uncovering Patterns in Dairy Cow Behaviour: A Deep Learning Approach with Tri-Axial Accelerometer Data |
| title_full_unstemmed | Uncovering Patterns in Dairy Cow Behaviour: A Deep Learning Approach with Tri-Axial Accelerometer Data |
| title_short | Uncovering Patterns in Dairy Cow Behaviour: A Deep Learning Approach with Tri-Axial Accelerometer Data |
| title_sort | uncovering patterns in dairy cow behaviour a deep learning approach with tri axial accelerometer data |
| topic | convolutional neural network machine learning precision livestock farming animal welfare |
| url | https://www.mdpi.com/2076-2615/13/11/1886 |
| work_keys_str_mv | AT paolobalasso uncoveringpatternsindairycowbehaviouradeeplearningapproachwithtriaxialaccelerometerdata AT cristiantaccioli uncoveringpatternsindairycowbehaviouradeeplearningapproachwithtriaxialaccelerometerdata AT lorenzoserva uncoveringpatternsindairycowbehaviouradeeplearningapproachwithtriaxialaccelerometerdata AT luisamagrin uncoveringpatternsindairycowbehaviouradeeplearningapproachwithtriaxialaccelerometerdata AT iginoandrighetto uncoveringpatternsindairycowbehaviouradeeplearningapproachwithtriaxialaccelerometerdata AT giorgiomarchesini uncoveringpatternsindairycowbehaviouradeeplearningapproachwithtriaxialaccelerometerdata |