Automated Observations of Dogs’ Resting Behaviour Patterns Using Artificial Intelligence and Their Similarity to Behavioural Observations
Although direct behavioural observations are widely used, they are time-consuming, prone to error, require knowledge of the observed species, and depend on intra/inter-observer consistency. As a result, they pose challenges to the reliability and repeatability of studies. Automated video analysis is...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-04-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/14/7/1109 |
| _version_ | 1797212938667294720 |
|---|---|
| author | Ivana Schork Anna Zamansky Nareed Farhat Cristiano Schetini de Azevedo Robert John Young |
| author_facet | Ivana Schork Anna Zamansky Nareed Farhat Cristiano Schetini de Azevedo Robert John Young |
| author_sort | Ivana Schork |
| collection | DOAJ |
| description | Although direct behavioural observations are widely used, they are time-consuming, prone to error, require knowledge of the observed species, and depend on intra/inter-observer consistency. As a result, they pose challenges to the reliability and repeatability of studies. Automated video analysis is becoming popular for behavioural observations. Sleep is a biological metric that has the potential to become a reliable broad-spectrum metric that can indicate the quality of life and understanding sleep patterns can contribute to identifying and addressing potential welfare concerns, such as stress, discomfort, or health issues, thus promoting the overall welfare of animals; however, due to the laborious process of quantifying sleep patterns, it has been overlooked in animal welfare research. This study presents a system comparing convolutional neural networks (CNNs) with direct behavioural observation methods for the same data to detect and quantify dogs’ sleeping patterns. A total of 13,688 videos were used to develop and train the model to quantify sleep duration and sleep fragmentation in dogs. To evaluate its similarity to the direct behavioural observations made by a single human observer, 6000 previously unseen frames were used. The system successfully classified 5430 frames, scoring a similarity rate of 89% when compared to the manually recorded observations. There was no significant difference in the percentage of time observed between the system and the human observer (<i>p</i> > 0.05). However, a significant difference was found in total sleep time recorded, where the automated system captured more hours than the observer (<i>p</i> < 0.05). This highlights the potential of using a CNN-based system to study animal welfare and behaviour research. |
| first_indexed | 2024-04-24T10:50:20Z |
| format | Article |
| id | doaj.art-cab5a74622194eaf9664f1e1edfa1384 |
| institution | Directory Open Access Journal |
| issn | 2076-2615 |
| language | English |
| last_indexed | 2024-04-24T10:50:20Z |
| publishDate | 2024-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Animals |
| spelling | doaj.art-cab5a74622194eaf9664f1e1edfa13842024-04-12T13:14:24ZengMDPI AGAnimals2076-26152024-04-01147110910.3390/ani14071109Automated Observations of Dogs’ Resting Behaviour Patterns Using Artificial Intelligence and Their Similarity to Behavioural ObservationsIvana Schork0Anna Zamansky1Nareed Farhat2Cristiano Schetini de Azevedo3Robert John Young4School of Sciences, Engineering & Environment, University of Salford, Manchester M5 4WT, UKInformation Systems Department, University of Haifa, Haifa 31905, IsraelInformation Systems Department, University of Haifa, Haifa 31905, IsraelDepartment of Evolution, Biodiversity and Environment, Institute of Exact and Biological Sciences, Federal University of Ouro Preto, Ouro Preto 35402-136, BrazilSchool of Sciences, Engineering & Environment, University of Salford, Manchester M5 4WT, UKAlthough direct behavioural observations are widely used, they are time-consuming, prone to error, require knowledge of the observed species, and depend on intra/inter-observer consistency. As a result, they pose challenges to the reliability and repeatability of studies. Automated video analysis is becoming popular for behavioural observations. Sleep is a biological metric that has the potential to become a reliable broad-spectrum metric that can indicate the quality of life and understanding sleep patterns can contribute to identifying and addressing potential welfare concerns, such as stress, discomfort, or health issues, thus promoting the overall welfare of animals; however, due to the laborious process of quantifying sleep patterns, it has been overlooked in animal welfare research. This study presents a system comparing convolutional neural networks (CNNs) with direct behavioural observation methods for the same data to detect and quantify dogs’ sleeping patterns. A total of 13,688 videos were used to develop and train the model to quantify sleep duration and sleep fragmentation in dogs. To evaluate its similarity to the direct behavioural observations made by a single human observer, 6000 previously unseen frames were used. The system successfully classified 5430 frames, scoring a similarity rate of 89% when compared to the manually recorded observations. There was no significant difference in the percentage of time observed between the system and the human observer (<i>p</i> > 0.05). However, a significant difference was found in total sleep time recorded, where the automated system captured more hours than the observer (<i>p</i> < 0.05). This highlights the potential of using a CNN-based system to study animal welfare and behaviour research.https://www.mdpi.com/2076-2615/14/7/1109animal welfarebehavioural observationscomputer visionAI |
| spellingShingle | Ivana Schork Anna Zamansky Nareed Farhat Cristiano Schetini de Azevedo Robert John Young Automated Observations of Dogs’ Resting Behaviour Patterns Using Artificial Intelligence and Their Similarity to Behavioural Observations Animals animal welfare behavioural observations computer vision AI |
| title | Automated Observations of Dogs’ Resting Behaviour Patterns Using Artificial Intelligence and Their Similarity to Behavioural Observations |
| title_full | Automated Observations of Dogs’ Resting Behaviour Patterns Using Artificial Intelligence and Their Similarity to Behavioural Observations |
| title_fullStr | Automated Observations of Dogs’ Resting Behaviour Patterns Using Artificial Intelligence and Their Similarity to Behavioural Observations |
| title_full_unstemmed | Automated Observations of Dogs’ Resting Behaviour Patterns Using Artificial Intelligence and Their Similarity to Behavioural Observations |
| title_short | Automated Observations of Dogs’ Resting Behaviour Patterns Using Artificial Intelligence and Their Similarity to Behavioural Observations |
| title_sort | automated observations of dogs resting behaviour patterns using artificial intelligence and their similarity to behavioural observations |
| topic | animal welfare behavioural observations computer vision AI |
| url | https://www.mdpi.com/2076-2615/14/7/1109 |
| work_keys_str_mv | AT ivanaschork automatedobservationsofdogsrestingbehaviourpatternsusingartificialintelligenceandtheirsimilaritytobehaviouralobservations AT annazamansky automatedobservationsofdogsrestingbehaviourpatternsusingartificialintelligenceandtheirsimilaritytobehaviouralobservations AT nareedfarhat automatedobservationsofdogsrestingbehaviourpatternsusingartificialintelligenceandtheirsimilaritytobehaviouralobservations AT cristianoschetinideazevedo automatedobservationsofdogsrestingbehaviourpatternsusingartificialintelligenceandtheirsimilaritytobehaviouralobservations AT robertjohnyoung automatedobservationsofdogsrestingbehaviourpatternsusingartificialintelligenceandtheirsimilaritytobehaviouralobservations |