Machine-learning-based calving prediction from activity, lying, and ruminating behaviors in dairy cattle

Borchers, M.R.; Chang, Yu‐Mei; Proudfoot, Kathryn L.; Wadsworth, Barbara; Stone, Amanda E.; Bewley, J.M.

doi:10.3168/jds.2016-11526

Cited by 171 publications

(164 citation statements)

References 41 publications

(56 reference statements)

Supporting

Mentioning

144

Contrasting

Unclassified

Order By: Relevance

“…() set the time window as 1 min, and Shen et al. () set the time window as 1 s. Different time windows have also used: 2 hr (Borchers et al., ), 10 s (Martiskainen et al., ), 5 s (Dutta et al., ), and 1–10 min (Diosdado et al., ). When changes in behavior patterns are frequent, the time window should be set for a short range, but it results in a huge data set, making analysis more complicated.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Dairy cattle behavior classifications based on decision tree learning using 3‐axis neck‐mounted accelerometers

Tamura

Okubo

Deguchi

et al. 2019

Animal Science Journal

View full text Add to dashboard Cite

Demand has been increasing recently for an automated monitoring system of animal behavior as a tool for the management of livestock animals. This study investigated the association between the behavior of dairy cattle and the acceleration data collected using three‐axis neck‐mounted accelerometers, as well as the feasibility of improving the precision of behavior classifications through machine learning. In total 38 Holstein dairy cows were used, and kept in four different farms. A logger was mounted to each collar to obtain acceleration data for calculating the activity level and variations. At the same time the behavior of the cattle was observed visually. Characteristic acceleration waves were recorded for eating, rumination, and lying, respectively; and the activity level and variations were significantly different among these behaviors (p < 0.01). Decision tree learning was performed on the data set from Farm A and validated its precision; which proved to be 99.2% in cross‐validation, and 100% in test data sets from Farms B to D. This study showed that highly precise classifications for eating, rumination, and lying is possible by using decision tree learning to calculate the activity level and variations of cattle based on the data obtained by three‐axis accelerometers mounted to a collar.

show abstract

Section: Discussionmentioning

confidence: 99%

“…In recent years, multiple studies have reported on cow behavior using accelerometers together with machine learning (Borchers et al, 2017;Dutta et al, 2014;Martiskainen et al, 2009). Although there are many methods of machine learning, this study used a simple decision tree.…”

Section: Discussionmentioning

confidence: 99%

Dairy cattle behavior classifications based on decision tree learning using 3‐axis neck‐mounted accelerometers

Tamura

Okubo

Deguchi

et al. 2019

Animal Science Journal

View full text Add to dashboard Cite

show abstract

“…Machine learning approaches recently became the leading technique for object and action recognition in humans (Jain, Tompson, Andriluka, Taylor, & Bregler, 2013;Toshev & Szegedy, 2013). The technique has great potential in animal sciences for studying of different aspects of animal behavior such as movement, food intake, social structure and competition, reproduction behavior, communication and welfare, and nesting using complex datasets (Borchers et al, 2017;Stern, He, & Yang, 2015;Valletta, Torney, Kings, Thornton, & Madden, 2017;Wang, 2019;XU & Cheng, 2017). Automated imaging technologies provide a large number of images that require an efficient strategy of analysis such as machine learning.…”

Section: Discussionmentioning

confidence: 99%

Efficient phenotypic sex classification of zebrafish using machine learning methods

Hosseini

Simianer

Tetens

et al. 2019

Ecology and Evolution

View full text Add to dashboard Cite

Sex determination in zebrafish by manual approaches according to current guidelines relies on human observation. These guidelines for sex recognition have proven to be subjective and highly labor‐intensive. To address this problem, we present a methodology to automatically classify the phenotypic sex using two machine learning methods: Deep Convolutional Neural Networks (DCNNs) based on the whole fish appearance and Support Vector Machine (SVM) based on caudal fin coloration. Machine learning techniques in sex classification provide potential efficiency with the advantage of automatization and robustness in the prediction process. Furthermore, since developmental plasticity can be influenced by environmental conditions, we have investigated the impact of elevated water temperature during embryogenesis on sex and sex‐related differences in color intensity of adult zebrafish. The estimated color intensity based on SVM was then applied to detect the association between coloration and body weight and length. Phenotypic sex classifications using machine learning methods resulted in a high degree of association with the real sex in nontreated animals. In temperature‐induced animals, DCNNs reached a performance of 100%, whereas 20% of males were misclassified using SVM due to a lower color intensity. Furthermore, a positive association between color intensity and body weight and length was observed in males. Our study demonstrates that high ambient temperature leads to a lower color intensity in male animals and a positive association of male caudal fin coloration with body weight and length, which appears to play a significant role in sexual attraction. The software developed for sex classification in this study is readily applicable to other species with sex‐linked visible phenotypic differences.

show abstract

“…As normal daily variation in ruminating time is about 10% (>10% with finely chopped or high-grain diets; Dulphy et al, 1979), the assumption is that large reductions in rumination time by an individual cow on a particular day can be an indication of a change in cow health. For example, rumination time has been shown to be consistently reduced about 8 h before calving and increase about 6 h later, likely a result of limited feed intake (Schirmann et al, 2013;Pahl et al, 2014;Paudyal et al, 2016;Borchers et al, 2017;Kovács et al, 2017). Thus, monitoring rumination time could be useful in predicting time of calving.…”

Section: Detection Of Parturition and Illness In Dairy Cowsmentioning

confidence: 99%

Invited review: Current perspectives on eating and rumination activity in dairy cows

Beauchemin

2018

Journal of Dairy Science

278

221

View full text Add to dashboard Cite

Many early studies laid the foundation for our understanding of the mechanics of chewing, the physiological role of chewing for the cow, and how chewing behavior is affected by dietary characteristics. However, the dairy cow has changed significantly over the past decades, as have the types of diets fed and the production systems used. The plethora of literature published in recent years provides new insights on eating and ruminating activity of dairy cows. Lactating dairy cows spend about 4.5 h/d eating (range: 2.4-8.5 h/d) and 7 h/d ruminating (range: 2.5-10.5 h/d), with a maximum total chewing time of 16 h/d. Chewing time is affected by many factors, most importantly whether access to feed is restricted, intake of neutral detergent fiber from forages, and mean particle size of the diet. Feed restriction and long particles (≥19 mm) have a greater effect on eating time, whereas intake of forage neutral detergent fiber and medium particles (4-19 mm) affects rumination time. It is well entrenched in the literature that promoting chewing increases salivary secretion of dairy cows, which helps reduce the risk of acidosis. However, the net effect of a change in chewing time on rumen buffing is likely rather small; therefore, acidosis prevention strategies need to be broad. Damage to plant tissues during mastication creates sites that provide access to fungi, adhesion of bacteria, and formation of biofilms that progressively degrade carbohydrates. Rumination and eating are the main ways in which feed is reduced in particle size. Contractions of the rumen increase during eating and ruminating activity and help move small particles to the escapable pool and into the omasum. Use of recently developed low-cost sensors that monitor chewing activity of dairy cows in commercial facilities can provide information that is helpful in management decisions, especially when combined with other criteria. Although accuracy and precision can be somewhat variable depending on sensor and conditions of use, relative changes in cow behavior, such as a marked decrease in rumination time of a cow or sustained low rumination time compared with a contemporary group of cows, can be used to help detect estrus, parturition, and some illnesses. This review provides a comprehensive understanding of the dietary, animal, and management factors that affect eating and ruminating behavior in dairy cows and presents an overview of the physiological importance of chewing with emphasis on recent developments and practical implications for feeding and managing the modern housed dairy cow.

show abstract

Machine-learning-based calving prediction from activity, lying, and ruminating behaviors in dairy cattle

Cited by 171 publications

References 41 publications

Dairy cattle behavior classifications based on decision tree learning using 3‐axis neck‐mounted accelerometers

Dairy cattle behavior classifications based on decision tree learning using 3‐axis neck‐mounted accelerometers

Efficient phenotypic sex classification of zebrafish using machine learning methods

Invited review: Current perspectives on eating and rumination activity in dairy cows

Contact Info

Product

Resources

About