Klinge Orlando Villalba-Condori

Visible foliar damage in maize caused by fall armyworm(Spodoptera frugiperda)is commonly assessed through manual field scouting, a labor-intensive process that is difficult to scale across large planting areas. Multispectral and hyperspectral sensing can support more objective assessment but remain costly and impractical for routine field use. This exploratory case study evaluated whether low-cost red–green–blue (RGB) imagery can provide preliminary indicators of visible foliar damage associated with natural S. frugiperda infestation. RGB video was recorded in maize fields in Jerez, Zacatecas, Mexico, yielding seven field-acquired sequences and 302 extracted frames. The pipeline combined hue–saturation–value (HSV)-based foliar segmentation with four visible-spectrum indices—Excess Green (ExG), Excess Red (ExR), the Visible Atmospherically Resistant Index (VARI), and the Green Leaf Index (GLI)—an ExG-ratio damage threshold, and a 17-feature descriptor per frame used to train a Random Forest (RF) severity classifier. The study is positioned relative to RGB, Unmanned Aerial Vehicle (UAV)-based, deep learning, and multimodal approaches through its emphasis on traceability, low acquisition cost, and sequence-aware validation. Using the recovered canonical HSV/ExG-ratio pipeline, sequence-level mean damage ranged from 0.1086% to 0.4511%, with maximum frame-level damage up to 7.7401%. Severity labels were percentile-derived from the canonical damage index, yielding 100 Low, 99 Medium, and 103 High samples. Under a stratified frame-level split, the RF baseline reached 76.9% accuracy and a macro F1-score of 0.759. Under leave-one-sequence-out validation, performance decreased to 57.3% overall accuracy and 0.577 macro F1-score, indicating sequence-level dependence and supporting a conservative interpretation of classifier generalization. A zero-shot comparison using the Segment Anything Model (SAM) on a curated ten-frame-per-sequence subset produced higher damage estimates (SAM 1.30–11.67% versus HSV 0.82–2.61% on the same frames), suggesting HSV segmentation may under-detect pale or bleached tissue. These results provide preliminary, exploratory evidence that low-cost RGB indices can capture information associated with visible foliar damage in the studied recordings, without establishing agronomic validation, generalization beyond this dataset, or readiness for field deployment.

Text vectorization is indispensable for natural language processing (NLP). It allows us to transform text—from comments, reviews, documents, and even complete books—into formats or values that we can use as input in machine learning (ML) models. In this article, we present a comparative analysis between some of these methods used for text vectorization. The general purpose is to identify which of these methods offers a superior performance when applied together with some classification models on binary classification datasets. Each vectorization method, in combination with the models used, is evaluated by standard metrics in machine learning, such as Accuracy, Precision, Recall, F1-score and area under the curve (Receiver Operating Characteristic (ROC)) for a robust evaluation, demonstrating that the newest and most complex vectorization methods are not necessarily better for all binary classification tasks.

Este artículo presenta el desarrollo y la evaluación inicial de un prototipo de aplicación móvil basada en Realidad Aumentada (RA) para la visualización de información sobre edificios históricos en el centro de la ciudad de Zacatecas, México, siguiendo un enfoque de Diseño Centrado en el Usuario (DCU). El objetivo fue diseñar una herramienta interactiva que enriqueciera la experiencia cultural mediante la superposición de información contextual sobre monumentos y el acceso a una agenda de eventos culturales cercanos. El perfil del usuario potencial se definió mediante entrevistas, lo que permitió adaptar el diseño del prototipo a sus necesidades y expectativas. La propuesta fue evaluada mediante pruebas de usabilidad con usuarios reales usando el Sistema de Escalas de Usabilidad (SUS), obteniendo una calificación de 71.5 puntos, correspondiente a una usabilidad aceptable. Además, se recopiló retroalimentación cualitativa que permitió identificar mejoras clave para la evolución del prototipo hacia una aplicación funcional. Pese a que los resultados son promisorios, se reconocen las limitaciones derivadas del uso de un entorno simulado y el alcance de la evaluación, por lo que los hallazgos deben interpretarse como una validación formativa inicial. El prototipo demuestra potencial para fortalecer el turismo cultural y fomentar la valoración del patrimonio local.

This study presents Robo-ICARE (Robotics-Inclusive Child-Centered Approach for Robotics in Education), a Child–Robot Interaction (cHRI) framework for designing inclusive educational robotics in under-resourced and multigrade classroom contexts. The framework addresses gaps in existing educational robotics approaches by integrating user-centered design, affective expressiveness, pedagogical alignment and inclusivity, with particular attention to learner variability and contextual constraints. Robo-ICARE comprises six interrelated design dimensions—embodiment, interactivity, intelligence, pedagogical alignment, inclusivity, and user-centered process—intended to guide the design implementation, and evaluation of educational robots in authentic classroom environments. The framework is operationalized and empirically examined through a case study involving COODI, a low-cost and emotionally expressive educational robot co-designed with students and teachers in rural Chile. The study follows a primarily qualitative, exploratory design-based research approach, supported by descriptive quantitative measures. Empirical evaluation with 49 participants focuses on usability, user experience, engagement, and emotional acceptance, rather than on causal measurement of learning gains. The findings indicate that the proposed framework supports the design of emotionally engaging and context-sensitive educational robotics experiences that are feasible in low-resource settings. Overall, this work contributes a design-guiding, empirically grounded framework that bridges child–robot interaction theory and educational practice, offering a replicable approach for inclusive educational robotics in under-resourced classroom contexts.

The Problem- and Technology-Based Research (IBPT) approach constitutes an innovative pedagogical model designed for first-year university students, with the objective of strengthening research and technological competencies through the integration of technological resources, problem-solving, and formative research. The aim of this research was to introduce and validate IBPT as a viable option for higher education by evaluating its effects on the gradual enhancement of research skills among 73 first-year engineering and nursing students at a public university in Peru. A quasi-experimental pretest-posttest methodology was utilized, incorporating a questionnaire designed according to the four phases of IBPT: understanding the problem, planning activities, executing tasks, and reviewing solutions. The findings revealed significant improvements in research competencies, particularly in activity execution and solution review, while more moderate progress was observed in problem comprehension and activity planning. In conclusion, IBPT emerges as an effective alternative for integrating problem-solving and technological resources in higher education, fostering the acquisition of research competencies and laying the groundwork for the consolidation of advanced research skills, essential for academic knowledge production and professional development in later stages.

This study analyzed the implementation of a problem-solving method based on Pólya’s proposal, complemented by accessible technological resources such as the Arduino board, sensors, and STEM educational cards, in engineering and nursing students from public universities in Peru. A quasi-experimental design with pre- and post-test was used, employing a quantitative approach and intentional non-probabilistic sampling. The participants were 98 first-year students who developed formative research projects contextualized to their local reality, using the visual programming environment mBlock. The results show significant development of research competencies in both majors, especially in the solution review phase, evidencing critical thinking and reflective evaluation. No significant differences were found between the majors regarding the use of educational technology, reinforcing its cross-disciplinary applicability. It is concluded that the combination of Pólya’s method and the use of accessible technologies strengthens active, reflective, and contextualized learning in higher education.

In infants, teaching strategies focus on play and experiential activities; The development of scientific competencies based on STEAM involves a series of pedagogical approaches, so the purpose of this work was to implement a mini-ecosystem as a teaching strategy. 20 children between 4 and 5 years old from the educational institution “Dulces Brotecitos” participated. The study is developed within the qualitative paradigm, as a case study over a period of 2 months for the operation of the mini-ecosystem and 3 months for its implementation. Non- participant observation, recording of photos and videos were used; and field notebook to analyse the results. In the findings, four and five years old children spontaneously and flexibly use their senses to observe different phenomena and objects of everyday life, they also raise hypotheses and make inferences to solve problems. The various experiences presented to infants activate their interest in science, such as robotics. The STEAM approach, acronym for Science, Technology, Engineering, Art and Mathematics, aims to integrate these disciplines into the educational process and encourage the development of each of them (Pahnke, Janna ; O’Donnell, Carol; Bascopé). The approach of STEAM learning sessions at an early age favors the development of skills in these subjects, which will then facilitate subsequent learning (Zollman, 2012). The objective of this project was to analyse the development of scientific thinking skills in children aged 4 and 5 at the Initial level, under the STEAM approach, working in a Mini Ecosystem, in which the sectors are implemented: the pedagogical garbage dump, games to build and sensory tables. The work with parents, community entities and private companies contributed to the implementation of a mini-laboratory, as part of the mini-ecosystem.

This study focuses on evaluating the influence of mentoring in technological tools on women operating in the textile sector in the high Andean areas of Cusco, Puno, Tacna, Moquegua and Arequipa in southern Peru. To measure this impact, surveys were conducted before and after the virtual mentorships, focusing on the acquisition of basic level technology skills, such as Google search, use of Canva and social media management. The results indicate that the mentorships have influenced the development of technology skills among the participants. Pre-mentoring surveys revealed a generalized lack in most of these skills, with limited knowledge in the use of tools such as search engines and graphic design platforms. However, post- mentoring surveys showed improvements in these areas. This study highlights the importance of mentoring in the development of basic technological skills, empowering women in the textile sector in the high Andean regions. These results suggest that mentoring can play a key role in closing technology gaps and improving the active participation of this demographic group in the digital economy and society in general.