One of the challenges in precision livestock farming is controlling the variables that affect production and automation for actuator triggering. Automated systems with fuzzy logic allow the integration of expert knowledge from various contexts, facilitating the adoption of animal welfare practices. The objective of this study was to compare a fuzzy logic-based system model with a proportional control-based system model for regulating environmental conditions in pig pens. Through input variables such as temperature, relative air humidity and ammonia levels, the system output was the activation of fans/extractors and the opening/closing of curtains. MATLAB® software was used to model the systems and simulate actions to promote animal welfare. When comparing the efficiency of the fuzzy logic-based system with the proportional control system, it was observed that the output result of the fuzzy model was faster in 90.1% of the samples, with its average output in rpm being 12.7% higher than the proportional control system. The proposed fuzzy logic control system demonstrates efficiency for use in precision livestock farming processes. Um dos desafios da pecuária de precisão é o controle das variáveis que afetam a produção e a automação para acionamento de atuadores. Sistemas automatizados com lógica fuzzy permite incorporar o conhecimento de especialistas em diferentes realidades, favorecendo a adoção do bem-estar desses animais. O objetivo deste estudo foi comparar um modelo de sistema baseado em lógica fuzzy com um modelo de sistema baseado em controle proporcional para regulação de condições ambientais em baias em suínos. Por meio das variáveis de entrada como temperatura, umidade relativa do ar e nível de amônia, a saída do sistema era o acionamento de ventiladores/exaustores e a abertura/fechamento de cortinas. Foi utilizado o software MATLAB® para modelar os sistemas e simular ações para promover o bem-estar animal. Ao comparar a eficiência do sistema baseado na lógica fuzzy com o sistema de controle em ação proporcional, observou-se que o resultado de saída do modelo fuzzy foi mais rápido em 90,1% das amostras, sendo em média sua saída em rpm 12,7% maior do que o sistema em ação proporcional. O sistema de controle proposto em lógica fuzzy se apresenta eficiente para uso nos processos de pecuária de precisão.

The automatic recognition of animal vocalizations is a valuable tool for monitoring pigs’ behavior, health, and welfare. This study investigates the feasibility of implementing a convolutional neural network (CNN) model for classifying pig vocalizations using tiny machine learning (TinyML) on a low-cost, resource-constrained embedded system. The dataset was collected in 2011 at the University of Illinois at Urbana-Champaign on an experimental pig farm. In this experiment, 24 piglets were housed in environmentally controlled rooms and exposed to gradual thermal variations. Vocalizations were recorded using directional microphones, processed to reduce background noise, and categorized into “agonistic” and “social” behaviors using a CNN model developed on the Edge Impulse platform. Despite hardware limitations, the proposed approach achieved an accuracy of over 90%, demonstrating the potential of TinyML for real-time behavioral monitoring. These findings underscore the practical benefits of integrating TinyML into swine production systems, enabling early detection of issues that may impact animal welfare, reducing reliance on manual observations, and enhancing overall herd management.