Estimation of respiratory frequency and rectal temperature on pigs in heat stress by fuzzy logic

Abstract

Physiological parameters such as respiratory frequency and rectal temperature stand out as indicators for heat stress in pigs, however, requiring time and labor for measurements. The possibility of using infrared thermography associated with prediction systems of these physiological variables can help in decision making, allowing greater welfare and productivity of the animals. With this objective, an experiment was carried out with growing pigs submitted to acute and chronic heat stress, working with a thermoneutrality temperature (22° C) and heat stress (34° C). The results were used for the development of a fuzzy model using as input variables: air dry bulb temperature (°C), average surface temperature (°C) and, as output variables: respiratory frequency (movements/minute) and rectal temperature (°C). The method of inference used was the one of Mamdani having been elaborated six rules and the defuzzification technique used was the one of the Center of Gravity. In the obtained results on simulation model when compared with experimental data was evidenced satisfactory efficiency in respiratory frequency determination and the rectal temperature, in which the R2 values calculated were respectively 0.997 and 0.951 for acute stress and 0.993 and 0.964 for chronic heat stress.