RESUMO O conteúdo de água no solo é um fator-chave na avaliação nas áreas agrícola e ecológica. O objetivo deste trabalho foi explorar a combinação de informações multisatélites para abordar a questão da baixa precisão na recuperação do conteúdo de água do solo a partir de informações de banda única e fonte única, e estabelecer um modelo para estimativa do conteúdo de água do solo baseado no método multiespectral simulado. Foi realizado um experimento de determinação hiperespectral de amostras de solo (Latossolos) com valores variáveis de teor de água. A reflectância de oito sensores de satélite multiespectral foi remapeada com base nas funções de resposta espectral. Os índices de vegetação (VIs) foram estabelecidos combinando todas as bandas de sensores disponíveis. Os VIs significativos e a reflectância da banda foram extraídos pelos métodos de coeficiente de correlação e análise de importância de dados out-of-bag (OOB), e em seguida modelos lineares e não lineares foram estabelecidos para a estimativa do conteúdo de água no solo. Correlação significativa foi obtida entre refletância multiespectral simulada, VIs e teor de água no solo. Os modelos não lineares apresentaram melhor desempenho que o modelo linear. A combinação do modelo OOB e Random Forest (OOB-RF) obteve a maior acurácia de predição, com R2 calibração e R2 predição de 0,852 e 0,834, respectivamente. De forma geral, verificou-se que o método de modelagem OOB-RF baseado em sensoriamento remoto multiespectral foi viável para estimar o teor de água no solo.

ABSTRACT The soil water content is a key evaluation factor in the agricultural and ecological fields. The objective of this study was to explore the combination of multi-satellite information to address the issue of low accuracy in soil water content retrieval from single-band, single-source information and to establish a model for the estimation of the soil water content based on a simulated multi-spectral method. An experiment involving the hyperspectral determination of soil samples (Oxisols) with varying values of the water content was conducted. The reflectance of eight multi-spectral satellite sensors was resampled based on the spectral response functions. The vegetation indices (VIs) were established by pairing all available sensor bands. The significant VIs and band reflectance were extracted using the correlation coefficient and out-of-bag (OOB) data importance analysis methods, and then linear models and nonlinear models were established for soil water content estimation. A significant correlation was achieved between the simulated multi-spectral reflectance, VIs, and soil water content. The nonlinear models had a better performance than the linear model. The combined OOB and random forest (OOB-RF) model achieved the highest prediction accuracy, with R2 calibration and R2 prediction values of 0.852 and 0.834, respectively. Overall, it was verified that the OOB-RF modeling method based on multi-spectral remote sensing was feasible for estimating the soil water content.

Abstract: The purpose of this document is to highlight the existing issue caused by a lack of knowledge about the actual condition of machinery and precise monitoring in an express mechanic workshop. This workshop consists of mechanical maintenance equipment such as vehicle lifts, balancers, aligners, and other common machinery in such work environments. The data collected from these machines are classified and processed using Artificial Intelligence, specifically Machine Learning, by employing a tabulation and interpretation algorithm alongside IoT (Internet of Things) through the instrumentation of these machines with sensors appropriate to their mechanical operation. This facilitates and enables the creation of predictive maintenance plans as well as operational schemes that help reduce operational costs, maintenance expenses, and energy consumption of the workshop equipment. The system innovatively uses a modular approach without requiring intervention or modification of the machines, allowing their interconnectivity with a computer that automatically manages the collected data. This results in a clear view of the usage of each component, providing critical information for generating predictive maintenance strategies.

Resumen: El propósito de este documento es dar a conocer la problemática existente por una falta de conocimiento del estado real de la maquinaria y del monitoreo preciso de un taller de mecánica exprés que se compone por elementos de mantenimiento mecánico tales como elevadores de vehículos, balanceadora, alineadora, entre otras las maquinarias más comunes en este tipo de centros de trabajo, estos datos son clasificados y procesados utilizando inteligencia artificial como Machine Learning al emplear un algoritmo de tabulación e interpretación y conjuntamente IoT (internet de las cosas) a través de la instrumentación de dichas máquinas con sensores acordes a su tipo de funcionamiento mecánico, esto facilita y permite generar planes de mantenimiento predictivo al igual que esquemas operativos que permitirán disminuir el costo operacional, costos de mantenimiento y consumo energético de la indumentaria del taller, utilizando de manera innovadora un sistema modular sin necesidad de intervenir o modificar las mismas, que permite la interconectividad de la maquinaria con un ordenador que gestione la data recogida de manera automática dando como resultado una visión clara del uso de cada componente, esta información es clave para la generación de un mantenimiento predictivo.

Despite significant technological advancements, there continues to be a considerable communication gap between individuals with hearing disabilities and the rest of society. This gap is exacerbated by the fact that the development and research of technologies, such as caption glasses, aimed at bridging this divide, primarily focus on sign languages used in countries with prominent tech industries, including European countries and USA. Consequently, there is a lack of resources and attention devoted to sign language recognition and translation systems for languages spoken in Africa. This research addresses this issue by concentrating on twenty-two common gestures in Kinyarwanda sign language. Through extensive exploration and evaluation of various machine learning algorithms, the study identifies the most effective approach for recognizing and translating these gestures. To validate the effectiveness of the developed system, real-world Kinyarwanda sign language video data is utilized for thorough training and testing. The research successfully culminates in the creation of a functional web application capable of accurately recognizing the 22 Kinyarwanda sign language gestures, both in live video feeds and recorded videos. This achievement represents a significant outcome of the research, as it addresses the specific needs of the Kinyarwanda signing community. By providing a reliable and accessible tool for gesture recognition and translation, the research contributes to narrowing the communication gap between individuals with hearing disabilities who use Kinyarwanda sign language and the wider society. OPEN LICENSE: CC-BY

Abstract — The exponential increase in Internet traffic is mainly due to the proliferation of services such as audio and video streaming, the emergence of applications that require a lot of bandwidth to work optimally and generally the process of digitalization of services. In this context, bandwidth management plays a fundamental role, which translates into a better experience for users. Traffic congestion causes the exchange of information to become deficient, that is why techniques such as automatic bandwidth adjustment have been investigated, which manages the bandwidth according to the traffic demand, therefore in this document a study is made about the automatic bandwidth adjustment, the way in which Artificial Intelligence is integrated with computer networks, finally a comparison will be made of several machine learning methods, cataloged within supervised learning, carrying out several experiments determining that Random Forest is the most effective method to predict the automatic bandwidth adjustment, followed by Naive Bayes, Logistic Regression, and Support Vectorial Machine (SMV), on the other hand K -nearest neighbor (KNN) and neural network do not demonstrate considerable effectiveness, each experiment was carried out taking into account the Quality of Service (QoS).

Resumen El aumento exponencial del tráfico en Internet se debe principalmente a la proliferación de servicios como el streaming de audio y video, a la aparición de aplicaciones que requieren un alto ancho de banda para funcionar de manera óptima, y, en general, al proceso de digitalización de servicios. En este contexto, la gestión del ancho de banda desempeña un papel fundamental, ya que contribuye a una mejor experiencia para los usuarios. La congestión de tráfico genera que el intercambio de información sea ineficiente. Por ello, se han investigado técnicas como el ajuste automático de ancho de banda, que permite gestionar el ancho de banda según la demanda de tráfico. En este documento se realiza un estudio sobre el ajuste automático de ancho de banda, abordando cómo la Inteligencia Artificial se integra con las redes de computadoras. Además, se presenta una comparación de varios métodos de aprendizaje supervisado en machine learning. A través de diversos experimentos, se determinó que Random Forest es el método más efectivo para predecir el ajuste automático de ancho de banda, seguido por Naive Bayes, Regresión Logística y Support Vector Machine (SVM). En contraste, los métodos K-Vecinos Más Cercanos (KNN) y redes neuronales no demostraron una efectividad significativa. Cada experimento se realizó considerando la Calidad de Servicio (QoS).

RESUMEN Se presenta un sistema de recomendación creado para optimizar la designación de profesores en el área de Gestión Computacional. La problemática radica en la subjetividad y poca eficiencia y para abordarlo se emplean técnicas de machine learning, específicamente el filtrado colaborativo y el análisis predictivo, con el propósito de mejorar la selección en función de experiencia, formación académica, destrezas pedagógicas y contentamiento. Se recopiló información de los últimos cinco años a través de encuestas a estudiantes y evaluaciones de desempeño en la docencia, identificando patrones en las asignaciones previas y predecir qué persona se ajusta mejor a los cursos futuros. Las asignaturas consideradas: Organización y Arquitectura Computacional, Sistemas Operativos, Redes de Computadoras, Seguridad Informática, entre otros. Como resultados, se demuestra una gran precisión, incrementando la satisfacción y optimizando el desempeño académico a comparación de métodos tradicionales. En conclusión, existe una contribución significativa en la mejora de la calidad educativa.

ABSTRACT A recommendation systen created to optimize the appointment of professors in the area of Computational Management is presented. The problem lies in subjectivity and lack of efficiency, and to address it, machine learning techniques are used, specifically collaborative filtering and predictive analysis, with the purpose of improving selection based on experience, academic training, pedagogical skills and contentment. Information from the last five years was collected through student surveys and teaching performance evaluations, identifying patterns in previous assignments and predicting which person is best suited for future courses. The subjects considered: Computer Organization and Architecture, Operating Systems, Computer Networks, Computer Security, among others. As a result, great accuracy is demonstrated, increasing satisfaction and optimizing academic performance compared to traditional methods. In conclusion, there is a significant contribution to the improvement of educational quality.

RESUMEN El artículo analizó el mercado de datos en la empresa "La Fabril" de Ecuador, enfocándose en la rentabilidad del cliente a través del desarrollo de un almacén de datos. Se estableció como objetivo principal identificar y analizar patrones que contribuyan a optimizar la asignación de recursos. La metodología incluyó un enfoque analítico-sintético, modelado y la aplicación de la metodología Hefesto, que permitió la limpieza de datos, modelado dimensional en PostgreSQL y la creación de tableros interactivos en Power BI. Los resultados revelaron tendencias estacionales en los ingresos, destacando el "aceite de palma" como el producto más rentable y la identificación de grupos de clientes según su rentabilidad. Se observó una relación directa entre la frecuencia de compra y la lealtad del cliente, lo que subraya la necesidad de implementar estrategias de fidelización. Además, se identificaron áreas de alto costo y se propusieron mejoras logísticas para optimizar la rentabilidad. En conclusión, la investigación demuestra que el uso efectivo de un almacén de datos puede transformar la toma de decisiones estratégicas y mejorar la rentabilidad en el contexto empresarial actual, y se planea ampliar el análisis a otros sectores y explorar técnicas avanzadas de análisis predictivo y aprendizaje automático para profundizar en la comprensión del comportamiento del cliente y optimizar aún más las estrategias empresariales.

ABSTRACT The paper analyzed the data mart in the company "La Fabril" in Ecuador, focusing on customer profitability through the development of a data warehouse. The main objective was to identify and analyze patterns that contribute to optimizing resource allocation. The methodology included an analytical-synthetic approach, modeling, and the application of the Hefesto methodology, which allowed for data cleaning, dimensional modeling in PostgreSQL, and the creation of interactive dashboards in Power BI. The results revealed seasonal trends in revenues, highlighting "palm oil" as the most profitable product and identifying customer groups based on their profitability. A direct relationship was observed between purchase frequency and customer loyalty, underscoring the need to implement loyalty strategies. Additionally, high-cost areas were identified, and logistical improvements were proposed to optimize profitability. In conclusion, the research demonstrates that the effective use of a data warehouse can transform strategic decision-making and enhance profitability in the current business context. There are plans to expand the analysis to other sectors and explore advanced techniques in predictive analysis and machine learning to deepen the understanding of customer behavior and further optimize business strategies.

Abstract: The present study aims to generate a semi-structured dataset for student regulation frequently asked questions presented by students of the School of Systems Engineering and Computing at the Pedagogical and Technological University of Colombia. The methodology is conducted under a quantitative deductive and applied approach. A data collection instrument for questions is generated in natural language, undergoing preprocessing, analysis, and post-processing of data. Unsupervised machine learning is applied to clustering algorithms and techniques for assessing the importance of terminology relative to their frequencies in a document. As a result, 33 categories of words related to a central reference element are obtained from a set of 197 questions. In conclusion, the present research study provides a set of questions stored in a JSON format that serve as input for training a conversational agent based on Deep Learning.

Resumen: El presente estudio tiene como finalidad generar un conjunto de datos de arquitectura semiestructurada para preguntas frecuentes sobre el reglamento estudiantil que son realizadas por estudiantes de la Escuela de Ingeniería de Sistemas y Computación de la Universidad Pedagógica y Tecnológica de Colombia. La metodología se desarrolla bajo un enfoque cuantitativo de aproximación deductiva y aplicada. Un instrumento de recolección de preguntas es generado en lenguaje natural, siendo sometidas a preprocesamiento, análisis y postprocesamiento de datos. Se aplica el aprendizaje automático de tipo no supervisado a algoritmos de agrupamiento y técnicas de evaluación de importancia de términos. Como resultado, se obtienen 33 categorías de palabras relativas a un elemento central de referencia, partiendo de un conjunto de 197 preguntas. En conclusión, la presente investigación brinda preguntas almacenadas en un documento de formato JSON que sirven como insumo para el entrenamiento de un agente conversacional basado en Deep Learning.

Abstract The emergence of Machine Learning (ML) technologies and their integration into agriculture has demonstrated a significant impact on disease detection in crops, enabling continuous monitoring and enhancing risk planning and management. This study applied image processing techniques such as thresholding, gamma correction, and the Stretched Neighborhood Effect Color to Grayscale (SNECG) method, alongside ML, to develop a predictive model for identifying five types of rice diseases. The ML techniques used included Logistic Regression, Multilayer Perceptron, Support Vector Machines, Decision Trees, and Random Forests (RF). Hyperparameters were optimized and evaluated through 5-fold cross-validation. In the results, the SNECG method successfully converted images to grayscale, capturing essential features of lesions on rice leaves. The ML models developed with these techniques showed evaluation metrics exceeding 80%, with the RF model (precision = 88.31%) demonstrating superior performance. Additionally, the RF model was integrated into an interface designed for agricultural decision-making. The practical application of the developed model could significantly improve the ability to detect and manage diseases in rice crops.

Resumen La floricultura es un sector de creciente importancia a nivel mundial, contribuyendo a la generación de empleo, ingresos y a la promoción de la biodiversidad y la sostenibilidad. Este estudio tuvo como objetivo identificar los factores que influyen en la adopción de la floricultura como cultivo alternativo en la provincia de Leoncio Prado, Perú, y evaluar su viabilidad económica. Para ello, se encuestó a 269 agricultores, analizando actitudes, aptitud de la tierra, factores socioeconómicos y ambientales. Mediante análisis descriptivo, pruebas de chi-cuadrado y regresión logística (p < 0,1) se seleccionaron los factores influyentes. Además, se emplearon múltiples algoritmos de aprendizaje automático (Árboles de Decisión, Regresión Logística, KNN, SVM, Ensemble, Redes Neuronales, Naive Bayes) con validación cruzada (k = 5) y métricas AUC para modelar la intención de adopción. Se desarrollaron escenarios incrementando la predisposición a adoptar la floricultura, y se realizó un análisis económico de ocho especies tropicales (Ginger Rojo, Anturio, Bastón del Emperador, Heliconia, Gardenia, Pico de Loro, Heliconias Golden, Maracas). Los resultados revelan que la disposición a cambiar de cultivo, la participación en campañas de sensibilización, la destinación de áreas a la conservación y el control de costos son factores clave. El modelo de redes neuronales alcanzó un AUC de 83,3% y escenarios mejorados indican que la adopción podría incrementar hasta en 11,32%. El Ginger Rojo demostró alta rentabilidad (VAN S/10428; TIR 51%; PRI 0,7 años). En conclusión, la floricultura representa una alternativa económica y ambientalmente viable que contribuye a la diversificación agrícola y a la sostenibilidad.

Abstract Floriculture is a sector of growing global importance, contributing to employment generation, income creation, and the promotion of biodiversity and sustainability. This study aimed to identify the factors influencing the adoption of floriculture as an alternative crop in the province of Leoncio Prado, Peru, and to assess its economic viability. A total of 269 farmers were surveyed, analyzing attitudes, land suitability, and socioeconomic and environmental factors. Influential factors were identified using descriptive analysis, chi-square tests, and logistic regression (p < 0.1). Additionally, multiple machine learning algorithms (Decision Trees, Logistic Regression, KNN, SVM, Ensemble, Neural Networks, Naive Bayes) with cross-validation (k = 5) and AUC metrics were employed to model adoption intentions. Scenarios were developed to increase the willingness to adopt floriculture, and an economic analysis of eight tropical species (Red Ginger, Anthurium, Emperor's Staff, Heliconia, Gardenia, Parrot's Beak, Golden Heliconias, Maracas) was conducted. The results reveal that willingness to change crops, participation in awareness campaigns, allocation of areas for conservation, and cost control are key factors. The neural network model achieved an AUC of 83.3%, and improved scenarios indicate that adoption could increase by up to 11.32%. Red Ginger demonstrated high profitability (NPV S/10428; IRR 51%; PBP 0.7 years). In conclusion, floriculture represents an economically and environmentally viable alternative that contributes to agricultural diversification and sustainability.

ABSTRACT Predicting the adhesive force between steel reinforcement and concrete is crucial as it influences stress distribution and the overall mechanical behavior of reinforced concrete. This study proposes a novel approach to enhance bond strength prediction using machine learning (ML) models optimized through Bayesian optimization (BO). A dataset comprising 401 beam tests with six key factors was used to train three distinct ML algorithms—Support Vector Regression (SVR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The prediction models were first trained on the full dataset, with BO applied to fine-tune hyperparameters and improve accuracy. Among these models, the BO-XGBoost achieved the best performance, with an R2 of 0.74, MAE of 1.412 MPa, and RMSE of 1.516 MPa on the test set, and R2 = 0.80, MAE = 0.950 MPa, RMSE = 1.200 MPa on the training set. In addition, a simplified model was developed, incorporating only three critical variables—rebar thickness, reinforcement tensile strength, and concrete compressive capacity—to make the model more applicable in real-world engineering scenarios. To further interpret the model’s predictions, Shapley additive explanations (SHAP) were employed, revealing the specific influence of each variable on bond strength. This study demonstrates that the integration of ML with Bayesian optimization can significantly improve the accuracy of bond strength predictions, offering valuable insights for structural design optimization.

ABSTRACT This experimental study investigates the axial compression effect of rectangular pultruded glass fiber-reinforced polymer (P-GFRP) tubular column sections, examining the impact of width-to-thickness ratio (B/t), aspect ratio (H/B), and column height on their structural performance. A total of 27 GFRP columns were subjected to axial compression tests to evaluate their ultimate load and initial stiffness. The columns exhibited a uniform failure pattern, characterized by crushing, mid-section fractures, and longitudinal splitting at the corners. The results revealed a negative correlation between the ultimate load and the aspect ratio, as well as the width-to-thickness ratio. This study utilized advanced machine learning algorithms, namely Response Surface Methodology (RSM) and Artificial Neural Network (ANN), to develop predictive models for the ultimate load of GFRP columns. The RSM model achieved an R2 value of 0.8347, demonstrating good accuracy in predicting ultimate load. The ANN model outperformed the RSM model, with an R criterion exceeding 0.68807 across training, testing, and validation phases, showing a stronger correlation between experimental and predicted outcomes. This research establishes a framework for forecasting the mechanical properties of column sections.

Abstract This mini-review explores the potential of precision medicine and personalized nutrition in addressing health challenges faced by perimenopausal women, focusing on the role of genetic polymorphisms in key metabolic pathways. Specifically focus on the single nucleotide polymorphisms (SNPs) in the COMT, FUT2, and MTHFR genes, which influence neurotransmitter metabolism, gut microbiota composition, and folate homeostasis, respectively. These polymorphisms are critical in modulating hormonal fluctuations, metabolic imbalances, and nutrient absorption during perimenopause. The review highlights the impact of COMT rs4680 on stress response and mood disorders, FUT2 rs602662 and rs601338 on vitamin B12 absorption and cortisol metabolism, and MTHFR rs1801133 and rs1801131 on homocysteine levels and cardiovascular risk. Furthermore, the integration of machine learning in precision medicine is discussed, offering insights into how genetic data can optimize personalized interventions. This approach enables targeted nutritional and therapeutic strategies to mitigate the metabolic and psychological effects of perimenopause. Overall, this review underscores the importance of incorporating genetic testing into preventive care for perimenopausal women to enhance quality of life and promote healthy aging.

Resumo Neste estudo, os princípios da climatologia complexa foram aplicados para delinear os topoclimas nas montanhas do leste de Cuba. Um modelo meteorológico numérico regional, alimentado por dados de reanálise, foi utilizado para obter padrões de temperatura com resolução de 0,6 km. Técnicas de aprendizado de máquina não supervisionadas foram posteriormente utilizadas para identificar tipos de clima com base na temperatura durante períodos chuvosos e menos chuvosos, bem como na localização geográfica. Esta análise foi complementada com dados históricos de precipitação e geográficos para identificar 23 topoclimas na área de estudo. Os métodos permitiram estimar erros de identificação topoclimática e proporcionaram um melhor entendimento sobre a representatividade das estações meteorológicas de superfície para a área de estudo. Os resultados mostraram que a distribuição das chuvas dos topoclimas identificados é consistente com a dos fatores formadores do clima local e de pesquisas anteriores. Além disso, foram identificados novos conhecimentos sobre as características climatológicas das chuvas nas alturas baixas e médias das montanhas no leste de Cuba.

Abstract In this study, the principles of complex climatology were applied to delineate topoclimates in the mountains of eastern Cuba. A regional numerical weather model, driven by reanalysis, was used to obtain temperature patterns at a resolution of 0.6 km. Unsupervised machine learning techniques were then utilized to identify weather types based on temperature during rainy and less rainy periods, as well as geographical location. This analysis was supplemented with historical precipitation and geographical data to identify 23 topoclimates in the study area. The methods allowed for the estimation of topoclimate identification errors and provided insights into the representativeness of surface meteorological stations for the study area. The results showed that the rainfall distribution of the identified topoclimates was consistent with that of local climate-forming factors and previous research. Furthermore, new insights into the climatological rainfall characteristics of the lower and middle heights of the mountains in eastern Cuba were identified.

ABSTRACT The study explores the perforating shear performance of Fiber-Reinforced Polymer (FRP) concrete blocks using machine learning techniques like Gradient-Boosted Regression Trees (GBRT), k-nearest Neighbours (KNN), and Lasso Regression. It aims to predict the structural integrity of FRP blocks under shear conditions based on experimental data. The models were assessed using Coefficient of Determination (R2), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). GBRT demonstrated superior performance during training with an R2 of 0.9786, RMSE of 52.75, and MAE of 34.12, indicating strong predictive accuracy and minimal error. It outperformed KNN (R2 = 0.92, RMSE = 83.91, MAE = 45.71) and Lasso Regression (R2 = 0.71, RMSE = 162.45, MAE = 115.83). In validation, GBRT again excelled with an R2 of 0.93, RMSE of 76.23, and MAE of 58.46, confirming its robustness in generalizing unseen data. KNN showed lower performance in validation (R2 = 0.86), with increased error values, while Lasso lagged further behind (R2 = 0.681, RMSE = 185.23, MAE = 138.34). GBRT consistently outperformed traditional regression methods, highlighting its potential for more accurate and reliable structural analysis in FRP concrete slabs.

Abstract Cancer is defined as a group of diseases in which abnormal cells multiply and can invade other organs, requiring continuous studies for new drugs. A series of 177 imidazo[1,2-a]pyridine and imidazo[1,2-a] pyrazine synthetic derivatives were previously obtained, and their anti-melanoma IC50 values have been determined. Here, Artificial Intelligence algorithms were used to select molecular descriptors and build a QSAR model, highlighting structural characteristics related to enhanced molecular potency. Additionally, the imidazopyrazine nucleus was compared to a known inhibitor of the Aurora Kinase enzyme, an important target in cancer therapy. Thus, strategic imidazopyrazines were subjected to comparative molecular dynamics calculations, providing inferences about their possible mechanisms of action. The QSAR model allows for the design and prediction of nine new analogues with favourable predicted IC50 values. Molecular dynamics simulations and the estimated binding energies are consistent with the ranking of activities presented by representatives of the series.