The development of Precision Livestock tools is of great relevance for the continuous and non-invasive monitoring of farm animals. Until now, the use of these tools in dairy farming has taken hold in cattle breeding (Zebari et al., 2018; Viazzi et al., 2014; Tullo et al., 2019), remaining marginal in the breeding of small ruminants. The use of machine learning technologies, such as the automatic analysis of vocalizations, is being developed for pigs (Manteuffel et al., 2017), but it represents a completely new and unexplored field in goats. The ongoing VOCAPRA project (Multidisciplinary approach for setting up a continuous monitoring system in goat farms by means of vocalization analysis, Rural development 2014 - 2020 for Operational Groups, in the sense of Art 56 of Reg.1305/2013) aims at increasing human understanding of goats’ vocalizations by collecting the bleats emitted by more than 300 dairy goats reared in four farms in northern Italy. To achieve this goal, 18 sensors collect acoustic data, which are then processed thanks to intelligence techniques (neural networks and/or decision trees), in order to extrapolate the bleating of goats from a pool of generic sounds. Up to now, a sample of 2000 bleats has been collected and associated to the contexts in which they were emitted (e.g. feed distribution, social isolation, injuries). The acoustic parameters of these vocalizations (duration, intensity, tone, etc.) are then analyzed to identify those that can be associated with the different emission contexts. Thanks to this pool of vocalizations referred to known contexts, we are currently developing an IT tool (smartphone application), which will allow farmers to receive real-time notifications on what is happening in their farm and therefore to intervene promptly in case of need. As part of this conference, we would like to propose an interactive poster to test the ability of participants to interpret goats’ vocalizations. To this aim, participants will be asked to listen to some audio tracks of goat bleatings emitted in known contexts and to associate each bleating to the situation in which it was emitted. Participants will be also interviewed by administering them a questionnaire to evaluate their level of empathy towards animals. This will then allow us to correlate the ability to interpret vocalizations to the level of empathy and other individual characteristics, such as age, sex and level of experience with animals.

Why do goats bleat? / S. Celozzi, M. Battini, S. Ntalampiras, L.A. Ludovico, G. Presti, M.V. Vena, E. Prato Previde, S. Mattiello - In: Proceedings of the 3rd International Precision Dairy Farming Conference[s.l] : University of Veterinary Medicine Vienna, 2022 Jan 31. - pp. 111-111 (( Intervento presentato al 3. convegno International Conference on Precision Dairy Farming tenutosi a Vienna : 30 August - 2 September nel 2022.

Why do goats bleat?

S. Celozzi
Primo
;
M. Battini
Secondo
;
S. Ntalampiras;L.A. Ludovico;G. Presti;E. Prato Previde
Penultimo
;
S. Mattiello
Ultimo
2022

Abstract

The development of Precision Livestock tools is of great relevance for the continuous and non-invasive monitoring of farm animals. Until now, the use of these tools in dairy farming has taken hold in cattle breeding (Zebari et al., 2018; Viazzi et al., 2014; Tullo et al., 2019), remaining marginal in the breeding of small ruminants. The use of machine learning technologies, such as the automatic analysis of vocalizations, is being developed for pigs (Manteuffel et al., 2017), but it represents a completely new and unexplored field in goats. The ongoing VOCAPRA project (Multidisciplinary approach for setting up a continuous monitoring system in goat farms by means of vocalization analysis, Rural development 2014 - 2020 for Operational Groups, in the sense of Art 56 of Reg.1305/2013) aims at increasing human understanding of goats’ vocalizations by collecting the bleats emitted by more than 300 dairy goats reared in four farms in northern Italy. To achieve this goal, 18 sensors collect acoustic data, which are then processed thanks to intelligence techniques (neural networks and/or decision trees), in order to extrapolate the bleating of goats from a pool of generic sounds. Up to now, a sample of 2000 bleats has been collected and associated to the contexts in which they were emitted (e.g. feed distribution, social isolation, injuries). The acoustic parameters of these vocalizations (duration, intensity, tone, etc.) are then analyzed to identify those that can be associated with the different emission contexts. Thanks to this pool of vocalizations referred to known contexts, we are currently developing an IT tool (smartphone application), which will allow farmers to receive real-time notifications on what is happening in their farm and therefore to intervene promptly in case of need. As part of this conference, we would like to propose an interactive poster to test the ability of participants to interpret goats’ vocalizations. To this aim, participants will be asked to listen to some audio tracks of goat bleatings emitted in known contexts and to associate each bleating to the situation in which it was emitted. Participants will be also interviewed by administering them a questionnaire to evaluate their level of empathy towards animals. This will then allow us to correlate the ability to interpret vocalizations to the level of empathy and other individual characteristics, such as age, sex and level of experience with animals.
Settore AGR/19 - Zootecnica Speciale
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
PDC Proceedings 2022 Vienna.pdf

accesso riservato

Tipologia: Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione 21.68 MB
Formato Adobe PDF
21.68 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/939183
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact