Prediction of Cow Calving in Extensive Livestock Using a New Neck-Mounted Sensorized Wearable Device: A Pilot Study

Abstract

In this study, new low-cost neck-mounted sensorized wearable device is presented to help farmers detect the onset of calving in extensive livestock farming by continuously monitoring cow data. The device incorporates three sensors: an inertial measurement unit (IMU), a global navigation satellite system (GNSS) receiver, and a thermometer. The hypothesis of this study was that onset calving is detectable through the analyses of the number of transitions between lying and standing of the animal (lying bouts). A new algorithm was developed to detect calving, analysing the frequency and duration of lying and standing postures. An important novelty is that the proposed algorithm has been designed with the aim of being executed in the embedded microcontroller housed in the cow’s collar and, therefore, it requires minimal computational resources while allowing for real time data processing. In this preliminary study, six cows were monitored during different stages of gestation (before, during, and after calving), both with the sensorized wearable device and by human observers. It was carried out on an extensive livestock farm in Salamanca (Spain), during the period from August 2020 to July 2021. The preliminary results obtained indicate that lying-standing animal states and transitions may be useful to predict calving. Further research, with data obtained in future calving of cows, is required to refine the algorithm.

Machine Learning-Based Prediction of Cattle Activity Using Sensor-Based Data

“…To collect the data that has been used to train and evaluate the different machine learning architectures presented in this paper, we have fitted neck-mounted wearable devices, previously presented in González-Sánchez et al [16], to different cows. The collars are powered using a lithium-ion battery and enclose the following components in a polymer (ABS) box sealed with a nitrile O-ring:…”

“…Furthermore, two human observers directly monitored and recorded the actions performed by the cows using a custom-made PC software application running on a laptop. Further information on the procedure is available in González-Sánchez et al [16]. The annotation of the cows' actions was separated into two groups of labels: general behavior and standing behavior.…”

“…In this study, data compiled by a low-cost neck-mounted sensorized wearable device, presented in González-Sánchez et al [16] is analyzed, and different machine learning algorithms are used to produce models that allow the detection of different physiological states of the animal based on the information captured by the sensors.…”

Machine Learning Methods and Visual Observations to Categorize Behavior of Grazing Cattle Using Accelerometer Signals

“…Precision livestock management is the new frontier in grazing livestock production [1]. The livestock production industry faces a series of challenges, such as labor shortages, social pressures, and increasing efforts to implement sustainable grazing practices to protect sensitive ecosystems [1][2][3][4]. These challenges may be overcome by developing smart tracking technology [4,5], such as global positioning systems (GPS) and accelerometers [1,6], temperature and heart-rate monitors [7], and video cameras [8].…”

“…To overcome issues related to direct behavioral observations, wildlife ecologists have confronted this issue by using remote sensing technologies such as motion sensors, accelerometers, acoustic recorders, and animal-borne camera systems (camera collars) to classify animal behavior and activity across broad temporal and spatial scales at fine resolution [18,19]. Rangeland ecologists experience similar limitations when working in extensive rangelands [3,6,20]. Behavior classification has been collected via video cameras mounted on tracking collars [18,[21][22][23].…”