This research introduces a new data-driven methodology for fault detection and isolation in dynamic systems, integrating fuzzy/Bayesian change point detection and decision trees induced by genetic programming for pattern classification. Tracking changes in sensor signals enables the detection of faults, and using decision trees generated by genetic programming allows for accurate categorization into specific fault classes. Change point detection utilizes a combination of fuzzy set theory and the Metropolis–Hastings algorithm. The primary contribution of the study lies in the development of a distinctive classification system, which results in a comprehensive and highly effective approach to fault detection and isolation. Validation is carried out using the Tennessee Eastman benchmark process as an experimental framework, ensuring a rigorous evaluation of the efficacy of the proposed methodology.

Resumo O objetivo deste estudo é descrever o desenvolvimento de protótipo de aplicativos móveis pareados para agentes comunitários de saúde e usuários como estratégia para aumentar a adesão vacinal. Trata-se de um estudo metodológico de produção tecnológica do tipo prototipagem. A construção seguiu o modelo do design centrado no ser humano, caracterizando-se por ser um processo colaborativo focalizado na pessoa para a pessoa. O desenvolvimento dos aplicativos se deu em quatro etapas. O conteúdo técnico-científico do aplicativo foi construído de acordo com as recomendações e informações do Programa Nacional de Imunização do Ministério da Saúde do Brasil. O objetivo do protótipo desenvolvido para os agentes comunitários de saúde é auxiliar na gestão das vacinas dos usuários adscritos em suas microáreas. O aplicativo do usuário tem por objetivo emitir informações confiáveis sobre vacinas e lembretes de alertas para adesão vacinal. Os aplicativos pareados auxiliam na busca ativa de usuários com incompletude vacinal e aplicação de outras intervenções oportunas, como educação em saúde e autogestão para busca de saúde.

This study aims to describe the development of a prototype of paired mobile applications for community health workers and users as a strategy to increase vaccination adherence. This is a methodological study of technological production using prototyping. The construction followed the human-centered design model, characterized by being a collaborative process focused on the person for the person. The development of the applications took place in four stages. The technical-scientific content of the application was built according to the recommendations and information from the National Immunization Program of the Brazilian Ministry of Health. The goal of the prototype developed for community health agents is to assist in managing the vaccines of users assigned to their microareas. The user application aims to provide reliable information about vaccines and alert reminders for vaccination adherence. The paired applications help in actively seeking users with incomplete vaccinations and applying other timely interventions, such as health education and self-management for health seeking.

Resumen El objetivo de este estudio es describir el desarrollo del prototipo de aplicaciones móviles emparejadas para agentes comunitarios de salud y usuarios como estrategia para aumentar la adherencia a la vacunación. Se trata de un estudio metodológico de producción tecnológica del tipo prototipado. La construcción siguió el modelo de diseño centrado en el ser humano, caracterizándose por ser un proceso colaborativo enfocado en la persona para la persona. El desarrollo de las aplicaciones se realizó en cuatro etapas. El contenido técnico-científico de la aplicación fue construido de acuerdo con las recomendaciones e información del Programa Nacional de Inmunización del Ministerio de Salud de Brasil. El objetivo del prototipo desarrollado para los agentes comunitarios de salud es ayudar en la gestión de las vacunas de los usuarios adscritos a sus microáreas. La aplicación del usuario tiene como objetivo emitir información confiable sobre las vacunas y recordatorios de alertas para la adherencia a la vacunación. Las aplicaciones emparejadas ayudan en la búsqueda activa de usuarios con incompletitud de vacunación y en la aplicación de otras intervenciones oportunas, como la educación en salud y la autogestión para la búsqueda de salud.

Fault classification in industrial processes is of paramount importance, as it allows the implementation of preventive and corrective measures before catastrophic failures occur, which can result in significant repair costs and production loss, for example. Therefore, the purpose of this study was to develop a classification model by merging the concepts of Decision Trees with Genetic Programming. To accomplish this, the proposed model randomly generates a set of decision trees using the adapted Tennessee Eastman dataset. The generation of these trees does not rely on classical construction logic; instead, they employ an approach where the structure and characteristics of the trees are randomly determined and adjusted throughout the evolutionary process. This approach enables a broader exploration of the search space and may lead to diverse solutions. The results obtained were moderate, largely due to the high number of target classes for classification (21 classes), resulting in the creation of complex trees. The average accuracy on the test data was 0.75, indicating the need to implement new alternatives and enhancements in the algorithm to improve the results.

Accurately predicting dry matter intake (DMI) in lactating crossbred cows under semi-arid conditions is a critical challenge in dairy farming. Precise DMI predictions are essential for optimizing nutrient utilization and enhancing animal performance, particularly in semi-arid environments, where complex and dynamic conditions prevail. This paper introduces a novel Error-Based Evolving Takagi-Sugeno (EBETS) Fuzzy Model designed to address these challenges by dynamically adapting to real-time data and leveraging both current and historical information to enhance prediction accuracy. The EBETS model employs fuzzy set theory and multivariate Gaussian functions to model complex, nonlinear relationships between variables, offering a more robust and flexible approach to DMI prediction. In experiments involving data from 114 crossbred cows under semi-arid conditions, the EBETS model was compared to traditional models and an artificial neural network. It achieved a mean squared error of 0.25, which is more than 90% lower than that of all the other models, while demonstrating a higher correlation coefficient with the expected values, indicating superior predictive performance and reliability. These results underscore the EBETS model’s substantial superiority over existing methods, highlighting its potential to significantly improve dairy farming productivity by providing precise and reliable DMI predictions in challenging environmental conditions. The model’s ability to continuously learn and adapt to changing conditions makes it a promising tool for various applications in agricultural science.