BovineTalk: machine learning for vocalization analysis of dairy cattle under the negative affective state of isolation
There is a critical need to develop and validate non-invasive animal-based indicators of affective states in livestock species, in order to integrate them into on-farm assessment protocols, potentially via the use of precision livestock farming (PLF) tools. One such promising approach is the use of...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-02-01
|
| Series: | Frontiers in Veterinary Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fvets.2024.1357109/full |
| _version_ | 1797337288032649216 |
|---|---|
| author | Dinu Gavojdian Madalina Mincu Teddy Lazebnik Teddy Lazebnik Ariel Oren Ioana Nicolae Anna Zamansky |
| author_facet | Dinu Gavojdian Madalina Mincu Teddy Lazebnik Teddy Lazebnik Ariel Oren Ioana Nicolae Anna Zamansky |
| author_sort | Dinu Gavojdian |
| collection | DOAJ |
| description | There is a critical need to develop and validate non-invasive animal-based indicators of affective states in livestock species, in order to integrate them into on-farm assessment protocols, potentially via the use of precision livestock farming (PLF) tools. One such promising approach is the use of vocal indicators. The acoustic structure of vocalizations and their functions were extensively studied in important livestock species, such as pigs, horses, poultry, and goats, yet cattle remain understudied in this context to date. Cows were shown to produce two types of vocalizations: low-frequency calls (LF), produced with the mouth closed, or partially closed, for close distance contacts, and open mouth emitted high-frequency calls (HF), produced for long-distance communication, with the latter considered to be largely associated with negative affective states. Moreover, cattle vocalizations were shown to contain information on individuality across a wide range of contexts, both negative and positive. Nowadays, dairy cows are facing a series of negative challenges and stressors in a typical production cycle, making vocalizations during negative affective states of special interest for research. One contribution of this study is providing the largest to date pre-processed (clean from noises) dataset of lactating adult multiparous dairy cows during negative affective states induced by visual isolation challenges. Here, we present two computational frameworks—deep learning based and explainable machine learning based, to classify high and low-frequency cattle calls and individual cow voice recognition. Our models in these two frameworks reached 87.2 and 89.4% accuracy for LF and HF classification, with 68.9 and 72.5% accuracy rates for the cow individual identification, respectively. |
| first_indexed | 2024-03-08T09:07:21Z |
| format | Article |
| id | doaj.art-68c50dbbeb544ad18015888dce401501 |
| institution | Directory Open Access Journal |
| issn | 2297-1769 |
| language | English |
| last_indexed | 2024-03-08T09:07:21Z |
| publishDate | 2024-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Veterinary Science |
| spelling | doaj.art-68c50dbbeb544ad18015888dce4015012024-02-01T04:20:58ZengFrontiers Media S.A.Frontiers in Veterinary Science2297-17692024-02-011110.3389/fvets.2024.13571091357109BovineTalk: machine learning for vocalization analysis of dairy cattle under the negative affective state of isolationDinu Gavojdian0Madalina Mincu1Teddy Lazebnik2Teddy Lazebnik3Ariel Oren4Ioana Nicolae5Anna Zamansky6Cattle Production Systems Laboratory, Research and Development Institute for Bovine, Balotesti, RomaniaCattle Production Systems Laboratory, Research and Development Institute for Bovine, Balotesti, RomaniaDepartment of Mathematics, Ariel University, Ariel, IsraelDepartment of Cancer Biology, University College London, London, United KingdomTech4Animals Laboratory, Information Systems Department, University of Haifa, Haifa, IsraelCattle Production Systems Laboratory, Research and Development Institute for Bovine, Balotesti, RomaniaTech4Animals Laboratory, Information Systems Department, University of Haifa, Haifa, IsraelThere is a critical need to develop and validate non-invasive animal-based indicators of affective states in livestock species, in order to integrate them into on-farm assessment protocols, potentially via the use of precision livestock farming (PLF) tools. One such promising approach is the use of vocal indicators. The acoustic structure of vocalizations and their functions were extensively studied in important livestock species, such as pigs, horses, poultry, and goats, yet cattle remain understudied in this context to date. Cows were shown to produce two types of vocalizations: low-frequency calls (LF), produced with the mouth closed, or partially closed, for close distance contacts, and open mouth emitted high-frequency calls (HF), produced for long-distance communication, with the latter considered to be largely associated with negative affective states. Moreover, cattle vocalizations were shown to contain information on individuality across a wide range of contexts, both negative and positive. Nowadays, dairy cows are facing a series of negative challenges and stressors in a typical production cycle, making vocalizations during negative affective states of special interest for research. One contribution of this study is providing the largest to date pre-processed (clean from noises) dataset of lactating adult multiparous dairy cows during negative affective states induced by visual isolation challenges. Here, we present two computational frameworks—deep learning based and explainable machine learning based, to classify high and low-frequency cattle calls and individual cow voice recognition. Our models in these two frameworks reached 87.2 and 89.4% accuracy for LF and HF classification, with 68.9 and 72.5% accuracy rates for the cow individual identification, respectively.https://www.frontiersin.org/articles/10.3389/fvets.2024.1357109/fullcattleanimal communicationaffective statesvocal parameterswelfare indicators |
| spellingShingle | Dinu Gavojdian Madalina Mincu Teddy Lazebnik Teddy Lazebnik Ariel Oren Ioana Nicolae Anna Zamansky BovineTalk: machine learning for vocalization analysis of dairy cattle under the negative affective state of isolation Frontiers in Veterinary Science cattle animal communication affective states vocal parameters welfare indicators |
| title | BovineTalk: machine learning for vocalization analysis of dairy cattle under the negative affective state of isolation |
| title_full | BovineTalk: machine learning for vocalization analysis of dairy cattle under the negative affective state of isolation |
| title_fullStr | BovineTalk: machine learning for vocalization analysis of dairy cattle under the negative affective state of isolation |
| title_full_unstemmed | BovineTalk: machine learning for vocalization analysis of dairy cattle under the negative affective state of isolation |
| title_short | BovineTalk: machine learning for vocalization analysis of dairy cattle under the negative affective state of isolation |
| title_sort | bovinetalk machine learning for vocalization analysis of dairy cattle under the negative affective state of isolation |
| topic | cattle animal communication affective states vocal parameters welfare indicators |
| url | https://www.frontiersin.org/articles/10.3389/fvets.2024.1357109/full |
| work_keys_str_mv | AT dinugavojdian bovinetalkmachinelearningforvocalizationanalysisofdairycattleunderthenegativeaffectivestateofisolation AT madalinamincu bovinetalkmachinelearningforvocalizationanalysisofdairycattleunderthenegativeaffectivestateofisolation AT teddylazebnik bovinetalkmachinelearningforvocalizationanalysisofdairycattleunderthenegativeaffectivestateofisolation AT teddylazebnik bovinetalkmachinelearningforvocalizationanalysisofdairycattleunderthenegativeaffectivestateofisolation AT arieloren bovinetalkmachinelearningforvocalizationanalysisofdairycattleunderthenegativeaffectivestateofisolation AT ioananicolae bovinetalkmachinelearningforvocalizationanalysisofdairycattleunderthenegativeaffectivestateofisolation AT annazamansky bovinetalkmachinelearningforvocalizationanalysisofdairycattleunderthenegativeaffectivestateofisolation |