Latin American Journal of Computing
Not a member yet
191 research outputs found
Sort by
Classification of Failure Using Decision Trees Induced by Genetic Programming
Get PDFFault classification in industrial processes is of paramount importance, as it allows the implementation of preventive and corrective measures before catastrophic failures occur, which can result in significant repair costs and production loss, for example. Therefore, the purpose of this study was to develop a classification model by merging the concepts of Decision Trees with Genetic Programming. To accomplish this, the proposed model randomly generates a set of decision trees using the adapted Tennessee Eastman dataset. The generation of these trees does not rely on classical construction logic; instead, they employ an approach where the structure and characteristics of the trees are randomly determined and adjusted throughout the evolutionary process. This approach enables a broader exploration of the search space and may lead to diverse solutions. The results obtained were moderate, largely due to the high number of target classes for classification (21 classes), resulting in the creation of complex trees. The average accuracy on the test data was 0.75, indicating the need to implement new alternatives and enhancements in the algorithm to improve the results.Fault classification in industrial processes is of paramount importance, as it allows the implementation of preventive and corrective measures before catastrophic failures occur, which can result in significant repair costs and production loss, for example. Therefore, the purpose of this study was to develop a classification model by merging the concepts of Decision Trees with Genetic Programming. To accomplish this, the proposed model randomly generates a set of decision trees using the adapted Tennessee Eastman dataset. The generation of these trees does not rely on classical construction logic; instead, they employ an approach where the structure and characteristics of the trees are randomly determined and adjusted throughout the evolutionary process. This approach enables a broader exploration of the search space and may lead to diverse solutions. The results obtained were moderate, largely due to the high number of target classes for classification (21 classes), resulting in the creation of complex trees. The average accuracy on the test data was 0.75, indicating the need to implement new alternatives and enhancements in the algorithm to improve the results
A Comparative Study Between the Brazilian Stock Market and Cryptocurrencies
Get PDFThe Brazilian Stock Market has been experiencing an increase in trading volume, and this shows an improvement in indices. This phenomenon is due to the adoption of Corporate Governance practices, improvement in institutional environments, and greater liquidity in national markets. In this scenario, blockchain technology has become popular in recent years, with various applications, ensuring transaction identification, authenticity, reliability, transparency, equity, and interoperability, along with the emergence of smart contracts. However, the most well-known cryptocurrency is Bitcoin, followed by Ethereum, which was the first to allow the use of smart contracts, and Solana, created in 2018, already holds the fourth position, with great expectations for future growth. The popularization of this asset class may represent an investment opportunity; on the other hand, there is research on its possible relationship with other markets and assets, such as gold, the dollar, or even the Dow Jones index. However, the literature on this subject lacks broader research regarding the Brazilian economy, which, being less stable than those markets known as strong, may present different results. This is the aim of the research to compare three cryptocurrencies (Bitcoin, Ethereum, and Solana) with the Brazilian stock market by means of the non-parametric statistical test Kolmogorov-Smirnov.The Brazilian Stock Market has been experiencing an increase in trading volume, and this shows an improvement in indices. This phenomenon is due to the adoption of Corporate Governance practices, improvement in institutional environments, and greater liquidity in national markets. In this scenario, blockchain technology has become popular in recent years, with various applications, ensuring transaction identification, authenticity, reliability, transparency, equity, and interoperability, along with the emergence of smart contracts. However, the most well-known cryptocurrency is Bitcoin, followed by Ethereum, which was the first to allow the use of smart contracts, and Solana, created in 2018, already holds the fourth position, with great expectations for future growth. The popularization of this asset class may represent an investment opportunity; on the other hand, there is research on its possible relationship with other markets and assets, such as gold, the dollar, or even the Dow Jones index. However, the literature on this subject lacks broader research regarding the Brazilian economy, which, being less stable than those markets known as strong, may present different results. This is the aim of the research to compare three cryptocurrencies (Bitcoin, Ethereum, and Solana) with the Brazilian stock market by means of the non-parametric statistical test Kolmogorov-Smirnov
Explorando Temas en Recursos Educativos Abiertos de Tecnologías de la Información a través del Algoritmo LDA
Get PDFThis paper explores the application of machine learning and text mining techniques to discover OER issues in the context of Engineering Education. Applying the LDA (Latent Dirichlet Allocation) algorithm, themes are extracted from OER, it is possible to consider them as additional metadata. This augmentation serves to enhance the description and categorization of OER. Furthermore, this study introduces a methodology to automatically identify topics in open educational resources. In this research, a dataset of 80 OER was obtained from the Skills Commons repository. The highest coherence value achieved at 0.42, emerged when the number of topics was 9 in the LDA model. These nine topics are closely associated with Information Technology Education.Este artículo aplica el algoritmo Latent Dirichlet Allocation, LDA, como una técnica de aprendizaje de máquina y minería de texto para descubrir temas en OER en el contexto de la educación en ingeniería. El algoritmo LDA permite extraer temas, en este estudio los temas que se extraen de OER pueden ser considerados como metadatos adicionales que enriquecerán la descripción y clasificación de los mismos. Además, se define una metodología para la identificación automática de temas en los recursos educativos abiertos. En esta investigación, se utiliza un dataset de 80 OER extraído del repositorio Skills Commons. El valor más alto de coherencia es 0.42, cuando el número de temas en el modelo LDA es 9. Estos nueve temas están relacionados con Educación en Tecnologías de la Información
Forensic Investigation in Robots
Get PDFIntegrating robots into industrial automation has led to a revolutionary transformation in executing complex tasks, harnessing precision and efficiency. The Robot Operating System (ROS) has played a significant role in driving this advancement. ROS Bag files in robots are crucial for preserving data, as they provide a format for recording and playing back ROS message data. These files serve as a comprehensive log of a robot\u27s sensory inputs and operational activities, enabling detailed analysis and reconstruction of the robot\u27s interactions and performance over time. However, there have been instances where security considerations were overlooked, giving rise to concerns about unauthorized access, data theft, and malicious actions. This research investigates the forensic potential of data generated by robots, with a particular focus on ROS Bag data. By analyzing ROS Bag data, we aim to uncover how such information can be used in forensic investigations to reconstruct events, diagnose system failures, and verify compliance with operational protocols. The components of the ROS ecosystem were examined, identifying the challenges in parsing ROS Bag files and underscoring the need for specialized tools. This analysis highlights the security risks associated with plain text communication within legacy ROS systems, emphasizing the importance of encryption. While providing valuable insights, this research calls for further exploration, tool development, and enhanced security practices in robotics and digital forensics, aiming to lay the foundation for effective crime resolution involving robots.Integrating robots into industrial automation has led to a revolutionary transformation in executing complex tasks, harnessing precision and efficiency. The Robot Operating System (ROS) has played a significant role in driving this advancement. ROS Bag files in robots are crucial for preserving data, as they provide a format for recording and playing back ROS message data. These files serve as a comprehensive log of a robot\u27s sensory inputs and operational activities, enabling detailed analysis and reconstruction of the robot\u27s interactions and performance over time. However, there have been instances where security considerations were overlooked, giving rise to concerns about unauthorized access, data theft, and malicious actions. This research investigates the forensic potential of data generated by robots, with a particular focus on ROS Bag data. By analyzing ROS Bag data, we aim to uncover how such information can be used in forensic investigations to reconstruct events, diagnose system failures, and verify compliance with operational protocols. The components of the ROS ecosystem were examined, identifying the challenges in parsing ROS Bag files and underscoring the need for specialized tools. This analysis highlights the security risks associated with plain text communication within legacy ROS systems, emphasizing the importance of encryption. While providing valuable insights, this research calls for further exploration, tool development, and enhanced security practices in robotics and digital forensics, aiming to lay the foundation for effective crime resolution involving robots
Exploring Digital Twins of Nonlinear Systems through Meta-Modeling with Echo State Networks
Get PDFEffective process monitoring, and control rely on precise dynamic models that can capture the inherent nonlinearities of chemical systems. However, rigorous modeling of complex industrial processes can be computationally demanding. Meta modeling using machine learning methodologies offers a viable approach to generate computationally efficient surrogate representations. Specifically, Echo State Networks (ESNs) are a promising neural network approach for meta-modeling nonlinear dynamical systems. ESNs simplify training through fixed input weights while they focus learning on output weights. This study explores the development of ESN-based digital twins for a nonlinear dynamic process. An ESN is employed to construct a meta-model of a simulated continuously stirred tank reactor with biochemical kinetic. The network was trained on input-output data obtained from the simulation of an ordinary differential equation system, and the performance was evaluated both in-sample and out-of-sample. The results indicate that the ESN meta-model can successfully approximate the underlying dynamics, accurately capturing temporal evolution. A closed-loop digital twin deployment using the ESN surrogate also showed reliable behavior. This work presents initial steps toward developing digital twins of chemical processes using ESN-driven meta-modeling. The findings suggest ESNs can effectively generate computationally efficient surrogate representations of nonlinear dynamical systems. Such digital twins hold promise for online process monitoring and optimized control of industrial plants.Effective process monitoring, and control rely on precise dynamic models that can capture the inherent nonlinearities of chemical systems. However, rigorous modeling of complex industrial processes can be computationally demanding. Meta modeling using machine learning methodologies offers a viable approach to generate computationally efficient surrogate representations. Specifically, Echo State Networks (ESNs) are a promising neural network approach for meta-modeling nonlinear dynamical systems. ESNs simplify training through fixed input weights while they focus learning on output weights. This study explores the development of ESN-based digital twins for a nonlinear dynamic process. An ESN is employed to construct a meta-model of a simulated continuously stirred tank reactor with biochemical kinetic. The network was trained on input-output data obtained from the simulation of an ordinary differential equation system, and the performance was evaluated both in-sample and out-of-sample. The results indicate that the ESN meta-model can successfully approximate the underlying dynamics, accurately capturing temporal evolution. A closed-loop digital twin deployment using the ESN surrogate also showed reliable behavior. This work presents initial steps toward developing digital twins of chemical processes using ESN-driven meta-modeling. The findings suggest ESNs can effectively generate computationally efficient surrogate representations of nonlinear dynamical systems. Such digital twins hold promise for online process monitoring and optimized control of industrial plants
Attack Taxonomy Methodology Applied to Web Services
Get PDFWith the rapid evolution of attack techniques and attacker targets, companies and researchers question the applicability and effectiveness of security taxonomies. Although the attack taxonomies allow us to propose a classification scheme, they are easily rendered useless by the generation of new attacks. Due to its distributed and open nature, web services give rise to new security challenges. The purpose of this study is to apply a methodology for categorizing and updating attacks prior to the continuous creation and evolution of new attack schemes on web services. Also, in this research, we collected thirty-three (33) types of attacks classified into five (5) categories, such as brute force, spoofing, flooding, denial-of-services, and injection attacks, in order to obtain the state of the art of vulnerabilities against web services. Finally, the attack taxonomy is applied to a web service, modeling through attack trees. The use of this methodology allows us to prevent future attacks applied to many technologies, not only web services.Con la rápida evolución de las técnicas de ataque y los objetivos de los atacantes, las empresas y los investigadores cuestionan la aplicabilidad y eficacia de las taxonomías de seguridad. Si bien las taxonomías de ataque nos permiten proponer un esquema de clasificación, son fácilmente inutilizadas por la generación de nuevos ataques. Debido a su naturaleza distribuida y abierta, los servicios web plantean nuevos desafíos de seguridad. El propósito de este estudio es aplicar una metodología para categorizar y actualizar ataques previos a la continua creación y evolución de nuevos esquemas de ataque a servicios web. Asimismo, en esta investigación recolectamos treinta y tres (33) tipos de ataques clasificados en cinco (5) categorías, tales como fuerza bruta, suplantación de identidad, inundación, denegación de servicios y ataques de inyección, con el fin de obtener el estado del arte de las vulnerabilidades contra servicios web. Finalmente, se aplica la taxonomía de ataque a un servicio web, modelado a través de árboles de ataque. El uso de esta metodología nos permite prevenir futuros ataques aplicados a muchas tecnologías, no solo a servicios web
A study on the impact of data balance on rainfall prediction through artificial neural networks using surface microwave radiometers
Get PDFThe National Institute for Space Research (INPE) has been a partner in significant projects that conduct atmospheric investigations impacting various sectors, such as the Amazon Tall Tower Observatory (ATTO) project. Since 2009, the project has conducted studies on the interactions between climate and the Amazon forest. ATTO has played an essential role in providing large volumes of data obtained by meteorological sensors, contributing to a deeper understanding of the atmospheric dynamics of the region. In a landscape where Artificial Intelligence-based rainfall forecast models gain prominence, this study explores the imbalance of data from the ATTO Campina field experiment and its influence on short-term rainfall forecasts using Artificial Neural Networks (ANNs). Metrics such as MAE, RMSE, and POD, as well as FAR indices, were applied in the assessment and revealed the connection between data balance and forecast results. More balanced data or data with greater weights for different rainfall ranges yield better results. The study emphasizes the importance of reliable data for training rain forecast models, aiming to improve the dexterity of these models. This approach is fundamental to increase the reliability of these models in real environments.The National Institute for Space Research (INPE) has been a partner in significant projects that conduct atmospheric investigations impacting various sectors, such as the Amazon Tall Tower Observatory (ATTO) project. Since 2009, the project has conducted studies on the interactions between climate and the Amazon forest. ATTO has played an essential role in providing large volumes of data obtained by meteorological sensors, contributing to a deeper understanding of the atmospheric dynamics of the region. In a landscape where Artificial Intelligence-based rainfall forecast models gain prominence, this study explores the imbalance of data from the ATTO Campina field experiment and its influence on short-term rainfall forecasts using Artificial Neural Networks (ANNs). Metrics such as MAE, RMSE, and POD, as well as FAR indices, were applied in the assessment and revealed the connection between data balance and forecast results. More balanced data or data with greater weights for different rainfall ranges yield better results. The study emphasizes the importance of reliable data for training rain forecast models, aiming to improve the dexterity of these models. This approach is fundamental to increase the reliability of these models in real environments
Método ANN-MoC para Problemas Inversos de Transporte Transitorio en un Dominio Unidimensional
No full textTransport problems of neutral particles have important applications in engineering and medical fields, from safety and quality protocols to optical medical procedures. In this paper, the ANN-MoC approach is proposed to solve the inverse transient transport problem of estimating the absorption coefficient from scalar flux measurements at the boundaries of the model domain. The central idea is to fit an Artificial Neural Network (ANN) using samples generated by direct solutions computed by a Method of Characteristics (MoC) solver. The direct solver validation is performed on a manufactured solution problem. Two inverse problems are then presented for testing the ANN-MoC method. In the first, a homogeneous medium is assumed, and, in the second, the medium is heterogeneous with a piecewise constant absorption coefficient. We show that the method can achieve good estimates, with accuracy depending on that of the direct solver. We also include a test of sensibility by studying the propagation of noise on the input data. The results highlight the potential of the proposed method to be applied to a broader range of inverse transport problems.Transport problems of neutral particles have important applications in engineering and medical fields, from safety and quality protocols to optical medical procedures. In this paper, the ANN-MoC approach is proposed to solve the inverse transient transport problem of estimating the absorption coefficient from scalar flux measurements at the boundaries of the model domain. The central idea is to fit an Artificial Neural Network (ANN) using samples generated by direct solutions computed by a Method of Characteristics (MoC) solver. The direct solver validation is performed on a manufactured solution problem. Two inverse problems are then presented for testing the ANN-MoC method. In the first, a homogeneous medium is assumed, and, in the second, the medium is heterogeneous with a piecewise constant absorption coefficient. We show that the method can achieve good estimates, with accuracy depending on that of the direct solver. We also include a test of sensibility by studying the propagation of noise on the input data. The results highlight the potential of the proposed method to be applied to a broader range of inverse transport problems
Estimation of Spatially Dependent Coefficients in Heterogeneous Media in Diffusive Heat Transfer Problems
Get PDFThis article addresses the solution to the inverse problem in a one-dimensional transient partial differential equation with a source term, commonly encountered in heat transfer modeling for diffusion problems. The equation is utilized in a dimensionless form to derive a more general solution that is applicable across various contexts. The Transition Markov Chain Monte Carlo (TMCMC) method is utilized to estimate spatially variable thermophysical properties within the equation. This approach involves transitioning between probability densities, gradually refining the prior distribution to approximate the posterior distribution. The results indicate the effectiveness of the TMCMC method in addressing this inverse problem, offering a robust methodology for estimating spatially variable coefficients.This article addresses the solution to the inverse problem in a one-dimensional transient partial differential equation with a source term, commonly encountered in heat transfer modeling for diffusion problems. The equation is utilized in a dimensionless form to derive a more general solution that is applicable across various contexts. The Transition Markov Chain Monte Carlo (TMCMC) method is utilized to estimate spatially variable thermophysical properties within the equation. This approach involves transitioning between probability densities, gradually refining the prior distribution to approximate the posterior distribution. The results indicate the effectiveness of the TMCMC method in addressing this inverse problem, offering a robust methodology for estimating spatially variable coefficients
Editorial
Get PDFWe are pleased to share Volume 11, Issue 2 of the Latin American Journal of Computing (LAJC) with you. This edition includes a selection of pioneering research articles that demonstrate the latest advancements in the computer science field. Each paper included in this volume represents rigorous academic research and innovative problem-solving methods. We believe that the insights and discoveries presented here will significantly contribute to the field, stimulate insightful discussions, and inspire future innovations.
This issue begins with three articles that explore advanced methodologies in process monitoring, heat transfer, and robotics. The first article investigates the use of Echo State Networks (ESNs) to create digital twins for nonlinear dynamic chemical processes, demonstrating the potential of ESNs in generating efficient surrogate models for real-time process monitoring and control. The second article addresses the inverse problem in heat transfer modeling using the Transition Markov Chain Monte Carlo method, showcasing its effectiveness in estimating spatially variable thermophysical properties. Next, Janarthanan et al. explore the potential of data generated by robots, specifically focusing on ROS Bag files used in the Robot Operating System (ROS). The study highlights security concerns, such as unauthorized access and data theft, due to plain text communication in legacy ROS systems.
This issue also delves into the critical applications of artificial intelligence and machine learning in various scientific and industrial domains. The fourth article presents the ANN-MoC approach for solving inverse transient transport problems, showcasing its potential in engineering and medical fields by accurately estimating absorption coefficients from scalar flux measurements. Next, another study explores the impact of data balance on short-term rainfall forecasts using Artificial Neural Networks (ANNs) with data from the Amazon Tall Tower Observatory (ATTO). This research emphasizes the necessity of balanced data to improve the accuracy and reliability of meteorological models, highlighting the broader implications for environmental monitoring and prediction. Additionally, the volume includes an innovative fault classification model for industrial processes, merging Decision Trees with Genetic Programming to enhance preventive and corrective measures.
Finally, we explore financial markets and technological advancements. One article compares the Brazilian stock market with cryptocurrencies like Bitcoin, Ethereum, and Solana, using the Kolmogorov-Smirnov test to examine their relationships and potential investment opportunities. The last study uses machine learning and the Grey Wolf Optimization meta-heuristic to predict Brazil\u27s electricity demand, showcasing advanced regression models for accurate energy consumption forecasting.
We hope that the diverse range of topics and innovative approaches presented in this volume will inspire your own research endeavors. The advancements in computational intelligence, machine learning, and data analysis showcased here underscore the transformative potential of these technologies in addressing real-world challenges. As we continue to explore the frontiers of computer science, we invite you to join us in pushing the boundaries of knowledge within our scientific community. Together, we can drive progress and make meaningful contributions to the field.Nos complace compartir con ustedes el Volumen 11, Número 2 de la Revista Latinoamericana de Computación (LAJC). Esta edición incluye una selección de artículos de investigación pioneros que demuestran los últimos avances en el área de las Ciencias de la Computación. Cada artículo incluido en este volumen representa una investigación académica rigurosa y métodos innovadores de resolución de problemas. Creemos que las ideas e investigaciones presentadas aquí contribuirán significativamente al área, estimularán discusiones e inspirarán futuras innovaciones.
Este número comienza con tres artículos que exploran metodologías avanzadas en la monitorización de procesos, transferencia de calor y robótica. El primer artículo investiga el uso de Redes de Estado Eco (ESNs) para crear gemelos digitales de procesos químicos dinámicos no lineales, demostrando el potencial de las ESNs en la generación de modelos sustitutos eficientes para la monitorización y control de procesos en tiempo real. El segundo artículo aborda el problema inverso en la modelación de transferencia de calor utilizando el método de la Cadena de Markov de Monte Carlo de Transición, mostrando su efectividad en la estimación de propiedades termofísicas variables en el espacio. A continuación, Janarthanan et al. exploran el potencial de los datos generados por robots, enfocándose específicamente en los archivos ROS Bag utilizados en el Sistema Operativo de Robots (ROS). El estudio destaca problemas de seguridad, como el acceso no autorizado y el robo de datos, debido a la comunicación en texto plano en los sistemas ROS heredados.
Este número también profundiza en las aplicaciones críticas de la inteligencia artificial y el aprendizaje automático en varios dominios científicos e industriales. El cuarto artículo presenta el enfoque ANN-MoC para resolver problemas inversos de transporte transitorio, mostrando su potencial en los campos de la ingeniería y la medicina mediante la estimación precisa de coeficientes de absorción a partir de mediciones de flujo escalar. A continuación, otro estudio explora el impacto del equilibrio de datos en las previsiones a corto plazo de precipitaciones utilizando Redes Neuronales Artificiales (ANNs) con datos del Observatorio de la Torre Alta del Amazonas (ATTO). Esta investigación enfatiza la necesidad de datos equilibrados para mejorar la precisión y confiabilidad de los modelos meteorológicos, destacando las implicaciones más amplias para la monitorización y predicción ambiental. Además, el volumen incluye un modelo innovador de clasificación de fallos para procesos industriales, que combina Árboles de Decisión con Programación Genética para mejorar las medidas preventivas y correctivas.
Finalmente, exploramos los mercados financieros y los avances tecnológicos. Un artículo compara el mercado de valores brasileño con criptomonedas como Bitcoin, Ethereum y Solana, utilizando la prueba no paramétrica de Kolmogorov-Smirnov para examinar sus relaciones y oportunidades de inversión potenciales. El último estudio utiliza el aprendizaje automático y la metaheurística de Optimización del Lobo Gris para predecir la demanda de electricidad en Brasil, mostrando modelos de regresión avanzados para pronosticar con precisión el consumo de energía.
Esperamos que la diversa gama de temas y enfoques innovadores presentados en este volumen inspire sus propias investigaciones. Los avances en inteligencia computacional, aprendizaje automático y análisis de datos aquí expuestos subrayan el potencial transformador de estas tecnologías para abordar desafíos del mundo real. Mientras continuamos explorando las fronteras de las ciencias de la computación, los invitamos a empujar juntos los límites del conocimiento dentro de nuestra comunidad científica. Juntos, podemos impulsar el progreso y hacer contribuciones significativas al campo