El libro Administración Inteligente: Estrategias Empresariales Basadas en Inteligencia Artificial, Analítica de Datos y Sostenibilidad examina la transformación contemporánea de la gestión organizacional a partir de la convergencia entre inteligencia artificial, analítica de datos, infraestructura digital y sostenibilidad. La obra plantea que la administración inteligente no debe entenderse como una simple incorporación de herramientas tecnológicas, sino como una reorganización de la capacidad directiva para decidir, coordinar, anticipar riesgos, aprender y crear valor en contextos crecientemente complejos. A lo largo de cuatro capítulos, se abordan los fundamentos conceptuales del enfoque, el papel estratégico del dato en la toma de decisiones, las condiciones de implementación organizacional incluyendo liderazgo, interoperabilidad, ciberseguridad junto a la gobernanza operativa y, finalmente, la articulación entre innovación empresarial, criterios ESG y resiliencia del modelo de negocio. En conjunto, el libro sostiene que el verdadero valor de la transformación inteligente depende menos de la sofisticación técnica aislada más la capacidad de integrar tecnología, juicio humano, trazabilidad y sostenibilidad en una arquitectura de gestión coherente, responsable y estratégicamente viable.

This study investigates stress detection in dairy cattle by integrating circadian rhythm analysis and deep learning. Behavioral biomarkers, including feeding, resting, and rumination, were continuously monitored using Nedap CowControl sensors over a 12-month period to capture seasonal variability. Circadian features were extracted using the Fast Fourier Transform (FFT), and deviations from expected 24 h patterns were quantified using Euclidean distance. These features were used to train a Long Short-Term Memory (LSTM) neural network to classify stress into three levels: normal, mild, and high. Expert veterinary observations of anomalous behaviors and environmental records were used to validate stress labeling. We continuously monitored 10 lactating Holstein cows for 365 days, yielding 87,600 raw hours and 3650 cow-days (one day per cow as the analytical unit). The Short-Time Fourier Transform (STFT, 36 h window, 1 h step) was used solely to derive daily circadian characteristics (amplitude, phase, coherence); STFT windows are not statistical samples. A 60 min window prior to stress onset was incorporated to anticipate stress conditions triggered by management practices and environmental stressors, such as vaccination, animal handling, and cold stress. The proposed LSTM model achieved an accuracy of 82.3% and an AUC of 0.847, outperforming a benchmark logistic regression model (65% accuracy). This predictive capability, with a one-hour lead time, provides a critical window for preventive interventions and represents a practical tool for precision livestock farming and animal welfare monitoring.

This study presents a novel approach for early stress detection in dairy cattle by combining circadian rhythm analysis with LSTM , neural networks. Behavioral data (feeding, resting, rumination) from Nedap Cow Control sensors were processed via Fast Fourier Transform (FFT) to extract circadian features. These inputs trained an LSTM classifier for stress prediction (baseline/mild/acute states). Key results: 82.3% accuracy (AUC: 0.847) in stress classification; 60-minute prediction window before stress onset; Identified circadian biomarkers for each stress level. Validated with 12-month longitudinal data (*n*=10 cows), the method outperforms traditional approaches by enabling proactive welfare interventions, operating with low computational cost, and maintaining robustness across seasons. This work establishes a precision livestock monitoring framework with direct applications in commercial herds.

This article reviews the impact of artificial intelligence (AI) and machine learning (ML) on modern livestock farming, focusing on monitoring animal welfare and detecting thermal stress in cattle. It highlights digital technologies such as smart sensors and the Internet of Things (IoT), which enable continuous and non-invasive monitoring. Articles from indexed journals since 2020 were analyzed using keywords related to stress and precision livestock farming. Findings indicate that algorithms like Random Forest and XGBoost show high accuracy in predicting health conditions, with one study reporting 89.3% accuracy in detecting thermal stress. Despite promising advancements, the need to improve model accuracy and data integration for effective implementation is emphasized. Overall, AI and sensor technologies provide advanced tools for managing stress in livestock, enhancing animal welfare and productivity in the industry.

Contemporary education integrates information and communication technologies in the pedagogical process; an alternative to integrate these aspects is the technological, pedagogical and content knowledge model. The objective of this study was to propose the use of TPACK in teaching Chemical stoichiometry to second-year high school students at the Tulcán Educational Unit. The TPACK model, its components and the parameters involved in the teaching-learning process of Chemistry were addressed. A quasi-experimental design was used with a quantitative, exploratory, correlational and transversal approach. There was an experimental group of 28 students and a control group of 24. A pretest and a posttest were applied to analyze the statistically significant differences when using the model in teaching. Validated instruments were used at a quantitative level using Cronbach's Alpha coefficient and at a qualitative level with the opinion of experts in education and technology. The results showed that the use of the TPACK model led to improvements in student performance, with a bilateral significance, lower than the significance level of 0.05 (alpha). A proposal was generated based on the use of technological tools for teaching Chemical stoichiometry. The possibility of replicating this approach in a greater number of Chemistry topics or other subjects in the future is suggested.