Sistema Regional de Información
en línea para Revistas Científicas de América Latina,
el Caribe, España y Portugal

One of the key factors affecting educational quality in Higher Education Institutions is student dropout. A high dropout rate can indicate student dissatisfaction with the relevance and quality of the education they are receiving. Therefore, a pressing challenge for these institutions is to characterize the dropout rates of academic programs, as well as overall dropout rates, with the aim of identifying trends or potential future variations that could support strategic decision-making to mitigate student dropout. In this regard, it has been generally observed that predictive models have predominantly employed machine learning techniques to predict whether a student will drop out based on social, economic, academic, and demographic variables, without focusing on characterizing percentage variations or future dropout trends. Thus, this article proposes an ARIMA-based time series model as a contribution to the characterization of historical dropout rates at the University of Cartagena, Colombia, from 1998 to 2022, with the goal of forecasting dropout rates for future years. This study was developed through four methodological phases: P1. Creation of training and testing datasets, P2. Identification of the model parameters p, q, and d, P3. Adjustment of potential models, P4. assessment of the ARIMA model and P5. Forecasting future dropout rates. The results showed that the ARIMA model (p=1, d=2, q=0) provided the best fit, enabling predictions to be made up to the second semester of 2028. A key conclusion of the study is that the dropout rate at the University of Cartagena over the next four years is expected to hover around 6%, meaning that for every 100 students entering the university, approximately 6 will drop out.

Jamaica is a crop of significant agricultural value, recognized for its adaptability. Despite its high demand in international markets, cultivation has declined in Mexico due to challenges such as marketing issues, climate change, soil degradation, and competition from other crops. This study emphasizes the importance of responsible agricultural practices, particularly sustainability, which aims to reduce reliance on pesticides and chemical fertilizers. We investigated the responses of three Jamaica genotypes under conditions with and without fertilizer application. The proposed methodology included two multivariate descriptive analysis: principal component analysis to elucidate the phenotypic behavior of each genotype, and factor analysis to identify the interdependence among response variables. Results indicated that the Campeche genotype exhibited the highest yield, followed closely by Guerrero, demonstrating favorable responses under both experimental conditions.

Predictive policing is considered a high-stake context, where the main challenges in employing an AI solution are to ensure the privacy and fairness of the system while preserving high performance. This usually implies specific demands on the technologies used and their explainability. To alleviate the emerging impediments to adopt a recidivism model, this study exploresan approach employing synthetic data in combination with state-of-the-art NLP techniques, such as transformers-based models running locally. This approach enhances the representation of crimes while preserving data privacy. In particular, we focus on comparing several language models for multilabel classification in Spanish language and techniques such as data reduction, data augmentation and in-distribution validation. The resulting methodology shows the benefits and drawbacks of selecting each language model and highlights the ability of identify and alleviate populations where the model performs significantly worse than the average.

Mental stress is a widespread issue in modern society, significantly impacting individuals' well-being and productivity across various demographic groups. Detecting and managing mental stress is crucial to addressing its adverse effects on physical and psychological health. Traditional methods rely on subjective assessments, which may lack accuracy and scalability. This paper presents a systematic review exploring the use of methods that combine information (Fusion Techniques) from various wearable sensors to mental stress recognition by using machine learning algorithms.The focus was on identifying trends in classifiers, data fusion techniques, sensors, and evaluation metrics. The findings highlight Support Vector Machine (SVM) as the most effective classifier, followed by Random Forest (RF) and K-nearest Neighbors (KNN). ECG (Electrocardiogram) and EEG (Electroencephalogram) emerged as the most used sensors due to their ability to monitor cardiovascular and brain activity. Metrics such as accuracy, precision, and F1 score were predominant in evaluating model performance.The review reveals a strong preference for aggregating features extracted from diverse raw data sources which enhances robustness of mental stress detection by using machine learning algorithms. While existing studies demonstrate significant advancements, the findings indicate opportunities for further improvement in hybrid fusion techniques and real-world applications.

This paper proposes the definition of Smart Sport Psychology as the integration of advanced technologies, such as artificial intelligence (AI), machine learning and the Internet of Things (IoT), along with other emerging technologies, into the principles and practices of sport psychology. This approach uses smart devices, data analytics and virtual reality technologies to optimise athletes' mental and physical performance, personalise psychological interventions and improve athletes' overall well-being. Through a comprehensive literature review, we explore how these technologies can address common psychological problems among athletes, including stress, anxiety, motivation, mental recovery, concentration, self-confidence and psychological injury prevention. The results highlight the effectiveness of continuous monitoring, personalised interventions and real-time feedback, providing innovative, data-driven strategies to improve athletes' performance and well-being. The paper concludes that Smart Sport Psychology has the potential to transform the sport industry, offering effective and sustainable solutions for the holistic development of athletes. This review provides a conceptual and practical framework for the implementation of smart technologies in sport psychology, highlighting their importance and long-term benefits in the sport domain.

Corrosion is a critical problem that damages metal surfaces in different environments, with a significant economic impact and safety risks. It mainly affects industrial installations and people's physical integrity, which is why it is very important to detect it. In the present work, corrosion classification was carried out using image analysis with a library named LibAUC. In search of state-of-the-art, this library has been used in other areas, but not for corrosion. The methodology consisted of the following: collection of images, image preprocessing, modification of the library code for compatibility with updated libraries, adaptation of the deep model learning of melanoma classification for corrosion classification, execution of the model with training and validation images. The metric used for the performance of the model was the AUC (Area Under ROC), which achieved a value of 0.9973. It is concluded that the LibAUC library has a high performance for binary corrosion classification.

This research work focuses on the development of a device. Such a device could assist doctors in level 1 and 2 healthcare clinics in Mexico. Because, such clinics lack specialists. The device takes pictures of the patient's skin. The pictures allow to identify diseases and provide a preliminary diagnosis. With the pre-diagnosis it is possible to send the patient to the corresponding specialist. We built a Vision Transformer (VIT) model with a Raspberry Pi 4. The system leverages a dataset augmented by a Generative Adversarial Network (GAN) using Stable Diffusion. The addition of synthetic data significantly improved the performance metrics. Accuracy increased from 90.76% to 92.77%, and the macro average and weighted average F1 scores increased from 0.9076 to 0.9281. Also, improvements were observed in most disease categories. Thus, the model's capacity allows generalization, especially in underrepresented or challenging classes.

This research examines leader–team interactions in agile software development within a global context, with a focus on effort estimation. Drawing on principal–agent theory, we analyse the interaction on the assumption that the Scrum Master guides the development team under imperfect information. We model the interaction as a sequential game with incomplete information. In the first stage, the Scrum Master allocates resources to the development team; in the second stage, the team exerts effort. Both parties are characterised by types that capture their knowledge and skills. As these types are private information, we derive the Bayesian Nash equilibrium to determine the equilibrium effort levels.

Artificial intelligence has become an essential technology in industry 4.0. People's daily activities require its use more frequently. Society 5.0, known as the fifth industrial revolution, places people at the center of processes, coupled with the use of artificial intelligence, for the development of the industry.

The implementation of mathematical algorithms plays a fundamental role in computational efficiency. Sequential programming, which processes instructions in a linear manner, often struggles with large data volumes due to its inherent limitations. In contrast, parallel programming distributes tasks across multiple cores, significantly reducing processing times and improving overall performance. This paper presents a comparative analysis of both approaches and their relevance in Systems Engineering, where computational optimization is critical. To this end, we implement and evaluate the Sobel algorithm—commonly used for edge detection in images—in both sequential and parallel modes. The implementation is carried out in Python, leveraging the NumPy, OpenCV, and Multiprocessing libraries. This study analyzes the conditions under which parallelization enhances performance and identifies scenarios where process overhead may negate its benefits, thus establishing fundamental criteria for applying these techniques to solve mathematical problems in engineering. The source code is available on GitHub at: [GitHub Repository].