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

Livestock monitoring is a task traditionally carried out through direct observation by experienced caretakers. By analyzing its behavior, it is possible to predict to a certain degree events that require human action, such as calving. However, this continuous monitoring is in many cases not feasible. In this work, we propose, develop and evaluate the accuracy of intelligent algorithms that operate on data obtained by low-cost sensors to determine the state of the animal in the terms used by the caregivers (grazing, ruminating, walking, etc.). The best results have been obtained using aggregations and averages of the time series with support vector classifiers and tree-based ensembles, reaching accuracies of 57% for the general behavior problem (4 classes) and 85% for the standing behavior problem (2 classes). This is a preliminary step to the realization of event-specific predictions.

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

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.

Novel method for holocellulose analysis of non-woody biomass wastes.

Compositional analysis of non-woody biomass is quite important to determine its possible applications. However, current standard methods developed for woody biomass compositional analysis have been revealed to be unsuitable when applied to non-woody biomass. Therefore, a novel and less-time consuming modified method which enables for a proper isolation of holocellulose in non-woody biomass samples while increasing lignin degradation has been developed. The novel method mainly consists in a treatment with sodium chlorite and glacial acetic acid at boiling point, which precludes changes in the holocellulose crystallinity degree or losses of carbohydrates, as shown by DSC, XRPD, and HPLC analysis. It was successfully applied to the determination of the structural components of 10 different non-woody biomass samples. Also, its use revealed that non-woody biomass belongs to LHC and LCH groups in the biomass structural composition ternary diagram, which are completely different than the ones the woody biomass belongs to.

Capacitive Sensing for Non-Invasive Breathing and Heart Monitoring in Non-Restrained, Non-Sedated Laboratory Mice.

Animal testing plays a vital role in biomedical research. Stress reduction is important for improving research results and increasing the welfare and the quality of life of laboratory animals. To estimate stress we believe it is of great importance to develop non-invasive techniques for monitoring physiological signals during the transport of laboratory animals, thereby allowing the gathering of information on the transport conditions, and, eventually, the improvement of these conditions. Here, we study the suitability of commercially available electric potential integrated circuit (EPIC) sensors, using both contact and contactless techniques, for monitoring the heart rate and breathing rate of non-restrained, non-sedated laboratory mice. The design has been tested under different scenarios with the aim of checking the plausibility of performing contactless capture of mouse heart activity (ideally with an electrocardiogram). First experimental results are shown.

Colonic tuberculosis in an immunocompetent patient.

INTRODUCTION: One-third of the world's population is infected with tuberculosis (TB), with intestinal TB representing the sixth most common presentation of extrapulmonary TB. The diagnosis of intestinal TB is a challenge for physicians due to its diverse clinical manifestations that mimic other infectious, autoimmune, and neoplastic disorders, and is thus rarely considered as the causative agent of disease. PRESENTATION OF CASE: We present a 55-year-old male with no relevant familial history, who presented due to a loss of 10kg of weight in 2 months accompanied by nocturnal diaphoresis and continuous abdominal distension. DISCUSSION: The incidence and the severity of intestinal TB are increased in immunosuppressed patients and more rapidly progress due to deficient immune response. However, our immunocompetent had severe progression resulting in surgery less than a month after the diagnosis was made. CONCLUSION: While the diagnosis of intestinal TB, and specifically colonic TB, is difficult and is almost never the first diagnosis entertained outside the immunocompromised population, we present a rare case in which the disease presents in an immunocompetent patient.