The paper proposes an approach for estimating the rectal temperature of dairy cows based on the non-invasive real-time monitoring of their respiration rates and the temperature-humidity index (THI) of the environment, combined with the analysis of infrared images. We use multimodal machine learning for the joint processing (fusion) of these different types of data. The implementation is performed using a new open source AutoML Python module named AutoGluon. After training and optimizing three different regression models (a neural network and two powerful boosting algorithms), it reduces the variance of the result using level 2 stacking. The evaluation metrics we work with are the mean absolute error, MAE, and the coefficient of determination, $R^2$. For a sample of 295 studied animals, a weighted ensemble provides quite decent results: $R^2=0.73$ and MAE $\approx 0.1$ °C. For another sample of 118 cows, we additionally use the pulse rate as a predictor and we achieve $R^2=0.65$, MAE $\approx 0.2$ °C. The maximal error is almost $1$ °C due to outliers, but the median absolute error in both cases is significantly lower: MedAE $<0.1$ °C, with the standard deviations respectively being $0.{118}^{°}$ and $0.{137}^{°}$. These encouraging results give us confidence that tabular and visual data fusion in ML models has great potential for the advancement of non-invasive real-time monitoring and early diagnostics methods.

The aim of the study was to investigate the possibility of using infrared thermography (IRT) as a tool for monitoring the physiological condition of dairy cows. The goal was to monitor cows at normal temperatures. As physiological parameters began to change with the onset of heat stress, the study focused on a group with temperature and humidity index (THI) values below 72. The study monitors the surface temperature at various points on the body, rectal temperature (RT) and Frequency of Breathing. Those parameters were chosen because they give the most accurate data on physiology and can be objectively measured. Thermography images of the udder surface temperature (UST), leg surface temperature (LST) and shoulder surface temperature (SST) of the cows were taken. Surface temperatures were extracted from the photos using specialized software. The data were processed and analyzed statistically. The correlation coefficient between UST and SST was 0.90, between RT and Frequency of Breathing was 0.65, between LST and UST it was 0.45 and between LST and SST - 0.39. In conclusion, it can be said that IRT can be used to monitor the physiological condition of dairy cows.

Introduction. The Sumo sport discipline is characterized by incomparable by the nature and character force interactions. The briefness of the fight requires the sumo wrestlers to possess a wide range of sports and technical, almost automated skills to manage their motor action depending on the opponent’s qualification. The present study aims to establish the phase structure, functional features, and mechanical principles of the sport-technical skills of the fight by frontal head pressure on the opponent’s chest in sumo. Methodology. For the purposes of the analysis, the fight is divided into separate phases, using a video computer system for determining the kinematic and energetic parameters of the movements. Results. Taking into account the fact that the mass of the defeating athlete is 23.5% lower and he is 0.05 m shorter than the opponent, the results show three basic mechanical conditions that contribute to his victory during the fight: generating a powerful power torque from the lower limbs to raise and guide the upper body through the initial acceleration phase; creating and increasing the detour force arm in order to disturb the balance of the opponent in the sagittal plane and use its inertia of movement. Discussion and Conclusion. The results of the study, on the one hand, justify the use of this sport technique against opponents with higher stature and mass. On the other hand, the resulting quantitative values of the parameters can serve to improve the training process, providing guidance on the qualities required for the competitors to use this technique and also for defensive actions.

This paper discusses the problems when overvoltage's occur on the operation of a HPPS. After the tripping of the protections, several power plants go into islanding and fluctuations of active power and frequency occur.