Use of Predicted Behavior from Accelerometer Data Combined with GPS Data to Explore the Relationship between Dairy Cow Behavior and Pasture Characteristics

Riaboff, Lucile; Couvreur, Sébastien; Madouasse, Aurélien; Roig-Pons, Marie; Aubin, Sébastien; Massabie, Patrick; Chauvin, Alain; Bédère, Nicolas; Plantier, Guy

doi:10.3390/s20174741

Cited by 32 publications

(24 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Actually, the elevation of the watering sites and the horizontal distance to the water are significant predictors of livestock grazing distribution (these two variables negatively correlate to the frequency of visits to the water sources) [ 28 ]. Grazing animals typically prefer to ruminate and rest in small areas close to water troughs [ 10 ] or trees [ 29 ], although grazing hotspots are also recognised near to water points [ 10 , 29 ].…”

Section: Effect Of External Factors On Site Use Preferencementioning

confidence: 99%

Factors Affecting Site Use Preference of Grazing Cattle Studied from 2000 to 2020 through GPS Tracking: A Review

Rivero

Grau-Campanario

Mullan

et al. 2021

Sensors

View full text Add to dashboard Cite

Understanding the behaviour of grazing animals at pasture is crucial in order to develop management strategies that will increase the potential productivity of grazing systems and simultaneously decrease the negative impact on the environment. The objective of this review was to summarize and analyse the scientific literature that has addressed the site use preference of grazing cattle using global positioning systems (GPS) collars in the past 21 years (2000–2020) to aid the development of more sustainable grazing livestock systems. The 84 studies identified were undertaken in several regions of the world, in diverse production systems, under different climate conditions and with varied methodologies and animal types. This work presents the information in categories according to the main findings reviewed, covering management, external and animal factors driving animal movement patterns. The results showed that some variables, such as stocking rate, water and shade location, weather conditions and pasture (terrain and vegetation) characteristics, have a significant impact on the behaviour of grazing cattle. Other types of bio-loggers can be deployed in grazing ruminants to gain insights into their metabolism and its relationship with the landscape they utilise. Changing management practices based on these findings could improve the use of grasslands towards more sustainable and productive livestock systems.

show abstract

Section: Effect Of External Factors On Site Use Preferencementioning

confidence: 99%

Factors Affecting Site Use Preference of Grazing Cattle Studied from 2000 to 2020 through GPS Tracking: A Review

Rivero

Grau-Campanario

Mullan

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Foldager [38] uses accelerometers and radio frequency identification (RFID) prototype devices installed on the collar to collect data, and detects the feed intake and feeding time of dairy cows, with an accuracy of more than 85%. Riaboff [39] collected the acceleration and GPS data of dairy cows and comprehensively detected the behavior of dairy cows in the pasture. They found that in permanent grassland, dairy cows ruminate and rest under trees for a longer time, and in fluffy grass ( Holcus lanatus) area has more grazing time; on the temporary grassland, the conclusion that behavior is easily affected by the external environment.…”

Section: B Comparison Of Test Resultsmentioning

confidence: 99%

Real-Time Behavioral Recognition in Dairy Cows Based on Geomagnetism and Acceleration Information

et al. 2021

View full text Add to dashboard Cite

The feeding, ruminating(standing, lying down), running, being still (standing, lying down), head-shaking, drinking, and walking behaviors of dairy cows can reflect their health status. In this study, a multi-sensor was used to collect data of cow's multi-behaviors for research on behavior recognition. Firstly, a collar style data acquisition system was designed using geomagnetic and acceleration sensors to collect the behavioral data of dairy cows during their daily activities. Secondly, the dairy cow behavioral recognition fusion model based on K-Nearest-Neighbors (KNN) and Random Forest (RF) models were used for behavior classification. To verify the accuracy of the fusion model, the algorithms of KNN, RF, Gradient Boosting Decision Tree (GBDT), Support Vector Machine (SVM), and Learning Vector Quantization (LVQ) were introduced for comparative recognition experiments among different algorithms. The KNN-RF fusion model had the highest average recognition accuracy of 98.51%, followed by the KNN model with an average recognition accuracy of 95.37%, and the LVQ model had the lowest average recognition accuracy of 80.81%. For the recognition and verification of each behavior, the KNN-RF fusion model had the most obvious improvement in the recognition of dairy cow feeding behavior, with a recognition accuracy of 99.34%, followed by the KNN model with a recognition accuracy of 95.07%. All six models had the lowest recognition accuracy for cow head-shaking behavior: a recognition accuracy of 89.11% with the KNN-RF model followed by the RF model with a recognition accuracy of 85.14%. The system can quickly and continuously collect cow behavior information, accurately recognize individual behaviors, and provide a scientific basis for the optimal design and efficient management of digital facilities and equipment for dairy cows.

show abstract

“…Drinking behavior has been reported in studies with a controlled environment [ 9 ] and in general the authors suggested further studies and adaptations for better drinking behavior predictions [ 10 ]. Additionally, the majority of results reported for animal behavior prediction using accelerometer information is with a taurine genetic composition [ 11 , 12 , 13 , 14 ], which can be different from a zebu genetic composition, due to the differences in temperament [ 15 ].…”

Section: Introductionmentioning

confidence: 99%

Strategy to Predict High and Low Frequency Behaviors Using Triaxial Accelerometers in Grazing of Beef Cattle

Watanabe¹,

Bernardes

Romanzini

et al. 2021

Animals

View full text Add to dashboard Cite

Knowledge of animal behavior can be indicative of the well-being, health, productivity, and reproduction of animals. The use of accelerometers to classify and predict animal behavior can be a tool for continuous animal monitoring. Therefore, the aim of this study was to provide strategies for predicting more and less frequent beef cattle grazing behaviors. The behavior activities observed were grazing, ruminating, idle, water consumption frequency (WCF), feeding (supplementation) and walking. Three Machine Learning algorithms: Random Forest (RF), Support Vector Machine (SVM) and Naïve Bayes Classifier (NBC) and two resample methods: under and over-sampling, were tested. Overall accuracy was higher for RF models trained with the over-sampled dataset. The greatest sensitivity (0.808) for the less frequent behavior (WCF) was observed in the RF algorithm trained with the under-sampled data. The SVM models only performed efficiently when classifying the most frequent behavior (idle). The greatest predictor in the NBC algorithm was for ruminating behavior, with the over-sampled training dataset. The results showed that the behaviors of the studied animals were classified with high accuracy and specificity when the RF algorithm trained with the resampling methods was used. Resampling training datasets is a strategy to be considered, especially when less frequent behaviors are of interest.

show abstract

Use of Predicted Behavior from Accelerometer Data Combined with GPS Data to Explore the Relationship between Dairy Cow Behavior and Pasture Characteristics

Cited by 32 publications

References 34 publications

Factors Affecting Site Use Preference of Grazing Cattle Studied from 2000 to 2020 through GPS Tracking: A Review

Factors Affecting Site Use Preference of Grazing Cattle Studied from 2000 to 2020 through GPS Tracking: A Review

Real-Time Behavioral Recognition in Dairy Cows Based on Geomagnetism and Acceleration Information

Strategy to Predict High and Low Frequency Behaviors Using Triaxial Accelerometers in Grazing of Beef Cattle

Contact Info

Product

Resources

About