Early detection of anomalies in cattle growth is essential for ensuring animal welfare, improving productivity, and enabling timely management interventions in livestock farming. However, centralized machine learning solutions raise concerns about data privacy, ownership, and heterogeneity across farms. This paper proposes a federated learning (FL) framework for detecting anomalies in beef cattle fattening, which enables decentralized model training while preserving data confidentiality. The system employs deep neural networks trained locally on real and synthetic farm datasets, and aggregated via the Federated Averaging function. Two experimental scenarios were designed to evaluate the system under different variance conditions: (i) balanced variance across farms, and (ii) high variance concentrated in one farm. In Scenario 1, the global model achieved a Mean Absolute Error (MAE) of 2.53 kg and a coefficient of determination (R2) of 0.9974. In Scenario 2, where a single farm introduced significant variability, the global MAE increased to 2.96 kg, with an R2of 0.9884. The anomaly detection mechanism, based on a residual thresholding method using the 2σ rule, identified 399 anomalies 4.87% in the balanced scenario. Results demonstrate the feasibility of using FL in livestock settings for robust and privacy-preserving anomaly detection, and highlight the need for adaptive techniques to address inter-farm variability.

The concept of digital transformation involves exploiting digital technologies to generate new ways of doing things in organizations, including the creation of new processes, models, and services that produce value based on the digitization of data and processes. The application of digital technologies enables organizations to develop capabilities for innovation, automation, etc., utilizing both established and emerging technologies, including the widespread use of artificial intelligence. In this paper is proposed the implementation of a fuzzy cognitive map based on experts for the evaluation of the level of digital transformation in MSMEs (Micro, Small & Medium Enterprises). The main variables of digital transformation used to define our fuzzy cognitive map were classified into five types: i) Organization and Culture variables related to strategies, way of working, and ecosystems, ii) Customer variables related to services and digital channels and products, iii) Operations and Internal Processes variables related to supply chain, suppliers, business model, iv) Information Technologies variables related to innovation, digitization, data and analytic. Finally, the fifth type of variable is the target, which indicates the level of digital transformation of the organization. Our model managed to specify with 99.4% the level of digital transformation of the organization. Thus, our fuzzy cognitive map can predict and analyze the factors associated with digital transformation in MSMEs.

Viral diseases such as dengue and COVID-19 constitute a public health problem due to high morbidity and mortality rates when diagnosis is not rapid and appropriate. The difficulties in the diagnostic process of these diseases lie in the variability of the clinical manifestations and the similarity with other viral diseases such as Zika and chikungunya. The implementation of computer-aided approaches can support medical professionals to support and improve decision making. In this article, we propose two medical decision support systems for severity prediction in dengue and COVID-19. The proposed systems use fuzzy cognitive maps for prediction and federated learning to increase the feature space, sample size, and ensure data privacy and security. The models were evaluated using dengue and COVID-19 datasets, and the results showed good performance in predicting severity and classifying patients. The implementation of the proposed systems in real clinical settings would be useful for the diagnosis of viral diseases such as dengue and COVID-19.

Integrated pest management (IPM) seeks to minimize the environmental impact of pesticide application. IPM is based on two important aspects —prevention and monitoring of diseases and insect pests— which today are being assisted by sensing and artificial-intelligence (AI). Particularly, AI helps to identify, monitor, control and make decisions about pests in crops. In this paper, we present a comparison among five machine-learning models to classify the population of the boll weevil in cotton into three classes: low, medium and high. Weather data (average daily rainfall, humidity and temperature) were used to classify the population of the boll weevil in the department of Córdoba, Colombia. The results showed that XGBoost obtained the highest accuracy (88%). Results showed that it is possible to classify boll-weevil populations using weather data.