Technical note: Evaluation of an automatic system for monitoring rumination time in weaning calves

Rodrigues, João Paulo Pacheco; Pereira, L. G. R.; Neto, Hilton do Carmo Diniz; Lombardi, Mayara Campos; Lage, Camila Flávia de Assis; Coelho, Sandra Gesteira; Sacramento, J. P.; Machado, F. S.; Tomich, T. R.; Maurício, Rogério Martins; Campos, M. M.

doi:10.1016/j.livsci.2018.11.017

Cited by 18 publications

(25 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Finally, though rumination behavior is most commonly recorded with accelerometers, other herd management-based PDT have recorded rumination using a microphone. Rumination patterns have been reported in calves as young as 2 d of age (Lopreiato et al, 2018), but this PDT failed to find agreement between auditory rumination records against live observations in calves less than 9 wk of age (Rodrigues et al, 2019), despite its validity in heifers older than 9 mo (Burfiend et al, 2010). Therefore, caution should be applied when interpreting results from studies when the validity of the PDT has not been determined in a range of calf ages.…”

Section: Validation and Application Of Pdt For Monitoring Physiological Attributesmentioning

confidence: 94%

Symposium review: Precision technologies for dairy calves and management applications

Costa

Cantor

Neave

2021

Journal of Dairy Science

View full text Add to dashboard Cite

Section: Validation and Application Of Pdt For Monitoring Physiological Attributesmentioning

confidence: 94%

Symposium review: Precision technologies for dairy calves and management applications

Costa

Cantor

Neave

2021

Journal of Dairy Science

View full text Add to dashboard Cite

“…For example, an algorithm developed to identify play behaviour in calves overestimated occurrence by some 200% despite pre-processing to increase the prevalence of positive samples [ 24 ]. Overestimation has also been reported in other low-prevalence behaviours such as movement activity [ 25 ] and rumination [ 26 ]. Estimates were improved when the prevalence of these behaviours increased [ 26 ].…”

Section: Introductionmentioning

confidence: 99%

“…Overestimation has also been reported in other low-prevalence behaviours such as movement activity [ 25 ] and rumination [ 26 ]. Estimates were improved when the prevalence of these behaviours increased [ 26 ]. The importance and need for quantification methods has been discussed widely in human machine learning tasks [ 22 ] but, to our knowledge, no such methods have been presented in the precision livestock literature.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Algorithms to Classify and Quantify Multiple Behaviours in Dairy Calves Using a Sensor: Moving beyond Classification in Precision Livestock

Carslake

Vázquez-Diosdado

Kaler

2020

Sensors

View full text Add to dashboard Cite

Previous research has shown that sensors monitoring lying behaviours and feeding can detect early signs of ill health in calves. There is evidence to suggest that monitoring change in a single behaviour might not be enough for disease prediction. In calves, multiple behaviours such as locomotor play, self-grooming, feeding and activity whilst lying are likely to be informative. However, these behaviours can occur rarely in the real world, which means simply counting behaviours based on the prediction of a classifier can lead to overestimation. Here, we equipped thirteen pre-weaned dairy calves with collar-mounted sensors and monitored their behaviour with video cameras. Behavioural observations were recorded and merged with sensor signals. Features were calculated for 1–10-s windows and an AdaBoost ensemble learning algorithm implemented to classify behaviours. Finally, we developed an adjusted count quantification algorithm to predict the prevalence of locomotor play behaviour on a test dataset with low true prevalence (0.27%). Our algorithm identified locomotor play (99.73% accuracy), self-grooming (98.18% accuracy), ruminating (94.47% accuracy), non-nutritive suckling (94.96% accuracy), nutritive suckling (96.44% accuracy), active lying (90.38% accuracy) and non-active lying (90.38% accuracy). Our results detail recommended sampling frequencies, feature selection and window size. The quantification estimates of locomotor play behaviour were highly correlated with the true prevalence (0.97; p < 0.001) with a total overestimation of 18.97%. This study is the first to implement machine learning approaches for multi-class behaviour identification as well as behaviour quantification in calves. This has potential to contribute towards new insights to evaluate the health and welfare in calves by use of wearable sensors.

show abstract

“…Mientras que en animales enfermos se ha registrado una caída en la duración de la misma (Borderas, de Passille, & Rushen, 2008). Por lo que, conocer el tiempo de rumia durante la crianza podría generar información relevante para el monitoreo de las prácticas de manejo, alimentación, desarrollo ruminal y estado de salud y bienestar de los animales (Webb et al, 2012;Rodrigues et al, 2019).…”

unclassified

“…Actualmente, la cuantificación del tiempo de rumia en terneros se basa únicamente en observaciones visuales directas y/o grabaciones de videos, que suelen ser inexactas ya que generalmente se realizan durante breves periodos de tiempo y determinados momentos del día (Kononoff, Lehman, & Heinrichs, 2002). Si bien en los últimos años se ha comenzado a utilizar sensores de medición de rumia en terneras de crianza (Burfeind et al, 2011;Butler, Thomson, Lomax, & Clark, 2017;Hill et al, 2017;Lopreiato et al, 2018Lopreiato et al, , 2020Rodrigues et al, 2019) para registrar los cambios en la frecuencia de rumia a través de las distintas semanas de vida, se necesitan más estudios para lograr una completa validación de esta tecnología en edades tempranas (Lopreiato et al, 2018) y poder así evaluar posibles correlaciones de la rumia con el ambiente y desarrollo ruminal, niveles de consumo y ganancia de peso diaria (GPD).…”

unclassified

Efecto de distintas dietas sobre el tiempo de rumia durante el periodo de predestete en reemplazos de lechería

Frossasco-Davicini

Elizondo-Salazar

2020

Nut. Anim. Trop.

View full text Add to dashboard Cite

En ganado lechero adulto, los patrones de rumia han sido ampliamente estudiados y asociados a niveles de consumo de materia seca, composición física-química de la dieta, estro, estado salud y bienestar animal. No ocurre lo mismo en terneras, donde la información disponible sobre el tiempo y los patrones de rumia es muy incipiente. El objetivo de esta revisión fue analizar los resultados obtenidos en investigaciones donde se evaluaron los efectos de la combinación de distintos programas de alimentación en la crianza de terneras sobre el tiempo de rumia en las semanas previas y posteriores al destete. Además, se analizó la tasa de crecimiento, el ambiente ruminal y el comportamiento animal alcanzado en los tratamientos nutricionales que presentaron mayor actividad de rumia. Para lo cual se consideraron siete investigaciones que registraron la rumia, a través de observadores calificados, durante las horas próximas a la alimentación. El tiempo de rumia se expresó como porcentaje del tiempo total observado y presentó un amplio rango de dispersión entre los diferentes tratamientos nutricionales, con valores que oscilaron entre 2 y 18%. Los mayores porcentajes se alcanzaron al suplementar con forrajes en proporciones inferiores al 10-15% de la ración. No obstante, en algunas investigaciones, la inclusión de ciertos forrajes no generó efectos sobre el tiempo de rumia; lo cual hace suponer que otros factores relacionados a la composición físico-química de la dieta estarían influyendo. En general, los animales que presentaron mayor actividad de rumia mostraron valores superiores de pH ruminal, consumo de alimento balanceado y ganancia de peso diaria, principalmente en posdestete. Por consiguiente, el tiempo y los patrones de rumia en terneras podría ser un indicador promisorio para monitorear la alimentación, el ambiente ruminal y el estado de bienestar animal. No obstante, en algunas de las investigaciones estas asociaciones no fueron encontradas o incluso se registró una menor concentración de ácidos grasos volátiles que podría comprometer el desarrollo ruminal.

show abstract

Technical note: Evaluation of an automatic system for monitoring rumination time in weaning calves

Cited by 18 publications

References 14 publications

Symposium review: Precision technologies for dairy calves and management applications

Symposium review: Precision technologies for dairy calves and management applications

Machine Learning Algorithms to Classify and Quantify Multiple Behaviours in Dairy Calves Using a Sensor: Moving beyond Classification in Precision Livestock

Efecto de distintas dietas sobre el tiempo de rumia durante el periodo de predestete en reemplazos de lechería

Contact Info

Product

Resources

About