System specification and validation of a noseband pressure sensor for measurement of ruminating and eating behavior in stable-fed cows

Zehner, Nils; Umsttter, Christina; Niederhauser, J.J.; Schick, Matthias

doi:10.1016/j.compag.2017.02.021

Cited by 132 publications

(134 citation statements)

References 25 publications

Supporting

Mentioning

105

Contrasting

Order By: Relevance

“…The sensitivity of the DT was 93 % for feeding and 92 % for ruminating and matched the performance of the RumiWatch sensor. Similar results were obtained in Zehner et al, (2017), where the RumiWatch noseband sensor classified ruminating and eating behaviours with an accuracy of 94 % and 92 %, respectively.…”

Section: Discussionsupporting

confidence: 83%

“…These two activities have patterns similar to feeding. The values of the specificity of the three behaviours were similar to those obtained in Zehner et al (2017). The relevance of these results is clearer when looking into the difference in ruminating and feeding time (Table 5).…”

Section: Discussionsupporting

confidence: 78%

“…It incorporates a noseband pressure sensor, data logger with on-line data analysis, and evaluation software. The system also records and classifies the duration of chewing activities, and enables quantifying individual ruminating and eating chews performed by the animal (Zehner et al, 2017). On the other hand, the accelerometer was attached to the right side of the collar of each cow as shown in Fig.…”

Section: Sensor Datamentioning

confidence: 99%

“…In particular, wearable accelerometers and noseband halters have been widely tested to automatically assess cow behaviours (Martiskainen et al, 2009a;Müller and Schrader, 2003;Robert et al, 2009;Vázquez Diosdado et al, 2015). For example, the RumiWatch noseband sensor was developed and validated as a monitoring device for ruminating and eating activities in stable-fed dairy cows (Braun et al, 2013;Zehner et al, 2017). In addition, grazing and ruminating times were recorded using HOBO accelerometers attached to the cows' jaws (Rayas-Amor et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Classification of ingestive-related cow behaviours using RumiWatch halter and neck-mounted accelerometers

Benaissa

Tuyttens

David

et al. 2019

Applied Animal Behaviour Science

View full text Add to dashboard Cite

Highlights Simple decision-tree (DT) algorithm to classify feeding and ruminating behaviours  The DT performs similar to support vector machine and a RumiWatch noseband. The use of a simple DT would help implementing the algorithm on the on-cow sensor  It would enable online measurements of the ingestive-related cow behaviours Abstract A new simple decision-tree (DT) algorithm was developed using the data from a neck-mounted accelerometer for real-time classification of feeding and ruminating behaviours of dairy cows. The performance of the DT was compared to that of a support vector machine (SVM) algorithm and a RumiWatch noseband sensor and the effect of decreasing the sampling rate of the accelerometer on the classification accuracy of the developed algorithms was investigated. Ten multiparous dairy cows were used in this study. Each cow was fitted with a RumiWatch halter and an accelerometer attached to the cow's collar with both sensors programmed to log data at 10 Hz. Direct observations of the cows' behaviours were used as reference (baseline data). Results indicate that the two sensors have similar classification performances for the considered behavioural categories (i.e., feeding, ruminating, other activity), with an overall accuracy of 93 % for the accelerometer with SVM, 90 % for the accelerometer with DT, and 91 % for the Rumiwatch sensor. The difference between the predicted and the observed ruminating time (in min/h) was less than 1 min/h (1.5% of the observed time) for the SVM and less than 2 min/h (2.8%) for both DT and the RumiWatch. Similarly, the difference in feeding time was 1.3 min/h (2.1%) for the SVM compared to 2.5 min/h (4.3%) and 2.4 min/h (4.1%) for both RumiWatch and DT, respectively. These preliminary findings illustrate the potential of the collarmounted accelerometer to classify feeding and ruminating behaviours with accuracy measures comparable to the Rumiwatch noseband sensor.

show abstract

Section: Discussionsupporting

confidence: 83%

Section: Discussionsupporting

confidence: 78%

Section: Sensor Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Classification of ingestive-related cow behaviours using RumiWatch halter and neck-mounted accelerometers

Benaissa

Tuyttens

David

et al. 2019

Applied Animal Behaviour Science

View full text Add to dashboard Cite

show abstract

“…In the course of the preparation for an experiment with cattle (Dittmann et al., ), the first author (MTD) tested a chew‐monitoring head collar operating with a noseband sensor (RumiWatch; Itin + Hoch GmbH, Liestal, Switzerland) on a horse for practicing halter application and data evaluation functions. The system had been developed primarily for cattle (Ruuska, Kajava, Mughal, Zehner, & Mononen, ; Zehner, Umstätter, Niederhauser, & Schick, ) but in the meantime was also validated for application in horses (Werner, Umstatter, Zehner, Niederhauser, & Schick, ). The system comprises a proprietary algorithm developed to classify chewing events of cattle as “ingestive” or “rumination” mastication, a differentiation not required in nonruminating species such as horses.…”

Section: Introductionmentioning

confidence: 99%

Ingestive mastication in horses resembles rumination but not ingestive mastication in cattle and camels

Dittmann

Kreuzer

Runge³

et al. 2017

J. Exp. Zool.

View full text Add to dashboard Cite

Horses achieve a higher degree of particle size reduction through ingestive mastication than functional ruminants. We characterized mastication using chew-monitoring halters (RumiWatch) in six domestic horses, cattle, and Bactrian camels each. All animals were offered grass hay of the same batch for 15 min. In cattle and camels, measurements were continued after eating until rumination was observed. Except for one horse, 96% of the horses' ingestive mastication data were identified as "rumination" by the proprietary RumiWatch algorithm, whereas ingestion and rumination by cattle and camels were mostly classified correctly. There were no systematic differences between cattle and camels. In cattle and camels, ingestive mastication was less regular than rumination, indicated by significantly higher standard deviations of chewing peak intervals, peak heights, and peak breadths in intraindividual comparisons. The average standard deviations of these measures were lower in horses than in cattle and camel ingestive mastication, indicating a more consistent chewing pattern in horses. Horse values were similar to those of rumination mastication, suggesting equally regular chewing motions. Regular, rhythmic chewing represents a common feature of horses and functional ruminants, but the less uniform ingestive mastication in functional ruminants represents a deviating pattern, the adaptive value of which remains unclear. In particular, it does not appear to promote a higher ingestion rate. A potential cause may be the avoidance of high tooth wear rates by delaying a more regular, systematic mastication until ingesta has been softened and the grit has been washed off in the forestomach.

show abstract

Dairy Cow Rumination Detection: A Deep Learning Approach

Ayadi

Said

Jabbar

et al. 2020

Communications in Computer and Information Science

View full text Add to dashboard Cite

System specification and validation of a noseband pressure sensor for measurement of ruminating and eating behavior in stable-fed cows

Cited by 132 publications

References 25 publications

Classification of ingestive-related cow behaviours using RumiWatch halter and neck-mounted accelerometers

Classification of ingestive-related cow behaviours using RumiWatch halter and neck-mounted accelerometers

Ingestive mastication in horses resembles rumination but not ingestive mastication in cattle and camels

Dairy Cow Rumination Detection: A Deep Learning Approach

Contact Info

Product

Resources

About