Automatic sign language recognition is a challenging task in machine learning and computer vision. Most works have focused on recognizing sign language using hand gestures only. However, body motion and facial gestures play an essential role in sign language interaction. Taking this into account, we introduce an automatic sign language recognition system based on multiple gestures, including hands, body, and face. We used a depth camera (OAK-D) to obtain the 3D coordinates of the motions and recurrent neural networks for classification. We compare multiple model architectures based on recurrent networks such as Long Short-Term Memories (LSTM) and Gated Recurrent Units (GRU) and develop a noise-robust approach. For this work, we collected a dataset of 3000 samples from 30 different signs of the Mexican Sign Language (MSL) containing features coordinates from the face, body, and hands in 3D spatial coordinates. After extensive evaluation and ablation studies, our best model obtained an accuracy of 97% on clean test data and 90% on highly noisy data.

Desarrollo de competencias digitales docentes mediante entornos virtuales: una revisión sistemática

School dropout in higher education remains a significant global challenge with profound socioeconomic consequences. To address this complex issue, educational institutions increasingly rely on business intelligence (BI) and related predictive analytics, such as machine learning and data mining techniques. This systematic review critically examines the application of BI and predictive analytics for analyzing and preventing student dropout, synthesizing evidence from 230 studies published globally between 1996 and 2025. We collected literature from the Google Scholar and Scopus databases using a comprehensive search strategy, incorporating keywords such as “business intelligence”, “machine learning”, and “big data”. The results highlight a wide range of predictive tools and methodologies, notably data visualization platforms (e.g., Power BI) and algorithms like decision trees, Random Forest, and logistic regression, demonstrating effectiveness in identifying dropout patterns and at-risk students. Common predictive variables included personal, socioeconomic, academic, institutional, and engagement-related factors, reflecting dropout’s multifaceted nature. Critical challenges identified include data privacy regulations (e.g., GDPR and FERPA), limited data integration capabilities, interpretability of advanced models, ethical considerations, and educators’ capacity to leverage BI effectively. Despite these challenges, BI applications significantly enhance institutions’ ability to predict dropout accurately and implement timely, targeted interventions. This review emphasizes the need for ongoing research on integrating ethical AI-driven analytics and scaling BI solutions across diverse educational contexts to reduce dropout rates effectively and sustainably.

Learning objects are used as teaching materials and are intended to support teaching and learning processes. The objective of the article was to evaluate a learning object developed with the free software tool H5P to be used as support material in a course of Research Methodology in the Administration career at a public university located in the state of Sonora, Mexico. Based on a quantitative, descriptive and cross-sectional study, the evaluation of the learning object was carried out on four dimensions: utility, impact, integration and characteristics. The results obtained are derived from a pilot with 70 undergraduate students and show a positive assessment of the learning object, they also allow us to glimpse the potential and benefits of the H5P platform to generate all kinds of educational materials. With the findings of this intervention, a reference framework is available for future developments and implementations of learning objects with H5P. Los objetos de aprendizaje son utilizados como materiales didácticos y tienen la finalidad de apoyar procesos de enseñanza y aprendizaje. El objetivo de este trabajo fue el de evaluar un objeto de aprendizaje, desarrollado con la herramienta de software libre H5P para ser utilizado como material de apoyo en un curso de Metodología de la Investigación en la Licenciatura en Administración en una universidad pública ubicada en el estado de Sonora, México. Con base en un estudio cuantitativo, descriptivo y transversal, se realizó la evaluación del objeto aprendizaje a partir de cuatro dimensiones: utilidad, impacto, integración y atributos. Los resultados obtenidos se derivan de una muestra de 70 estudiantes en donde se observa una valoración positiva del objeto de aprendizaje, además permiten vislumbrar el potencial y los beneficios que tiene la plataforma H5P para generar todo tipo de materiales educativos. Con los hallazgos de esta intervención, se dispone de un marco de referencia para futuros desarrollos e implementaciones de objetos de aprendizaje con H5P.

In the modern digital ecosystem, the effective management of knowledge and the integration of information and communication technologies are the keys to revolutionizing educational practices within higher education institutions. This study presents a systematic review of recent literature, examining how the incorporation of information and communication technologies facilitates the creation and transfer of knowledge, enables collaboration among educators, and supports continuous professional development. We explore the benefits of personalized learning and the application of technological tools to enhance collaboration, access to educational resources, and pedagogical reflection. The key findings emphasize the role of these tools in promoting teacher interaction and exchange of ideas, highlighting the critical importance of training in digital competency to maximize their impact. The study also identifies challenges, including the need to improve effective knowledge transfer and technological training. In conclusion, effective knowledge management, supported by information and communication technologies, fortifies digital competencies and cultivates a culture of collaboration and content creation in higher education institutions.

The objective of this documentary review was to analyze the notion of educational digital inclusión and establish the boundaries of the concept in relation to other terms. The conceptual mapping method was chosen (Tobón, 2004), wich consists of four phases: 1) search for documents relevant to the research problem, 2) definition of inclusion and exclusion criteria, 3) data analysis based on eight axes, and 4) interpretation of the results. A total of 40 documents were reviewed from the databases Dialnet and SciELO, as well as from the Fundación Ceibal repository. The results obtained make it possible to establish that it is often difficult to relate the term with educational inclusion (higher category) given that the latter is oriented towards equalize the conditions. In this sense, the link between both concepts has permeated a vision focused on the implementation of actions and strategies that, for the most part, do not consider the particularities of the institutions to which they are directed. Likewise, its association with the term innovation has weighed on the figure of the teacher, since it is assumed that the insertion of technological artifacts is enough to achieve innovative uses, without considering that the inclusion of these tools must be accompanied by the corresponding literacy processes.