Luís Miguel Barata
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Luís Miguel Barata has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Eurico Lopes
Instituto Politécnico de Castelo Branco
4 shared publications - Ricardo Lopes da Silva
Department of Computer Science, Polytechnic University of Castelo Branco, 6000-084 Castelo Branco, Portugal
2 shared publications - Arminda Guerra Lopes
Instituto Politécnico de Castelo Branco
1 shared publication Eurico Lopes
1 shared publication- Franscisco Martins1 shared publication
João Afonso
Instituto Politécnico de Castelo Branco (IPCB)
1 shared publication
Latest Publications
- Open Access
- 10 November 2026
- Published by MDPI AG in Education Sciences
- Vol. 16 (11) , 1921
MoonPhase: An Instructional Framework for Portable Experiential Cybersecurity Learning in Engineering Education
In an age of pervasive connectivity and rapidly evolving cyber threats, cybersecurity has become a transversal competency in engineering education rather than a niche specialism. This paper presents MoonPhase, a multifunctional portable device based on a Raspberry Pi platform, designed to support experiential cybersecurity learning in engineering education contexts by integrating offensive, defensive, and educational modes into a single physical artefact. The work builds on a structured literature review, with study identification and selection documented using a PRISMA 2020-informed flow diagram, and a state-of-the-art analysis of portable cybersecurity tools to derive design requirements that balance realism, safety, and pedagogical alignment. MoonPhase combines sub-GHz replay capabilities, 2.4 GHz interference and monitoring, fake Wi-Fi access points, packet sniffing, and network scanning in a compact, menu-driven platform that can be deployed in regular laboratories and outreach workshops. The paper describes the hardware and software architecture of the device and its instructional framing, linking device functionalities to learning outcomes, laboratory activities, ethical reflection, and assessment. A preliminary educational pilot was conducted with 21 undergraduate students using a 90 min session and a one-group pre-test/post-test design. Mean knowledge scores increased from to , corresponding to an average gain of 2.38 points. A paired-samples t-test confirmed a statistically significant difference (, ), with a large within-participant effect size (Cohen’s ). Students also reported high levels of perceived authenticity (4.38/5), engagement (4.57/5), and self-reported ethical awareness (4.29/5). These exploratory results provide preliminary empirical support for the proposed instructional framework, while the small sample size and absence of a control group limit causal interpretation. MoonPhase is positioned as a replicable educational resource that brings students closer to realistic attack and defence scenarios in controlled settings.- 10 November 2026
- Published by MDPI AG in Education Sciences
- Vol. 16 (11) , 1921
Open AccessMoonPhase: An Instructional Framework for Portable Experiential Cybersecurity Learning in Engineering Education
In an age of pervasive connectivity and rapidly evolving cyber threats, cybersecurity has become a transversal competency in engineering education rather than a niche specialism. This paper presents MoonPhase, a multifunctional portable device based on a Raspberry Pi platform, designed to support experiential cybersecurity learning in engineering education contexts by integrating offensive, defensive, and educational modes into a single physical artefact. The work builds on a structured literature review, with study identification and selection documented using a PRISMA 2020-informed flow diagram, and a state-of-the-art analysis of portable cybersecurity tools to derive design requirements that balance realism, safety, and pedagogical alignment. MoonPhase combines sub-GHz replay capabilities, 2.4 GHz interference and monitoring, fake Wi-Fi access points, packet sniffing, and network scanning in a compact, menu-driven platform that can be deployed in regular laboratories and outreach workshops. The paper describes the hardware and software architecture of the device and its instructional framing, linking device functionalities to learning outcomes, laboratory activities, ethical reflection, and assessment. A preliminary educational pilot was conducted with 21 undergraduate students using a 90 min session and a one-group pre-test/post-test design. Mean knowledge scores increased from to , corresponding to an average gain of 2.38 points. A paired-samples t-test confirmed a statistically significant difference (, ), with a large within-participant effect size (Cohen’s ). Students also reported high levels of perceived authenticity (4.38/5), engagement (4.57/5), and self-reported ethical awareness (4.29/5). These exploratory results provide preliminary empirical support for the proposed instructional framework, while the small sample size and absence of a control group limit causal interpretation. MoonPhase is positioned as a replicable educational resource that brings students closer to realistic attack and defence scenarios in controlled settings. - Open Access
- 21 June 2026
- Published by Universidade Federal do Rio Grande do Sul in Revista de Informática Teórica e Aplicada
- Vol. 33 (3) , 45-58
Penetration Testing in Big Data Frameworks
Big Data systems are expanding rapidly, and frameworks like Hadoop and Spark are now central to that growth. Yet this expansion also raises new security challenges, particularly regarding how vulnerabilities are identified, assessed, and mitigated in complex, distributed environments. While the existing literature predominantly focuses on defensive mechanisms, systematic evidence on offensive approaches such as penetration testing remains limited. This paper presents a systematic literature review of security assessment practices for Hadoop and Spark between 2015 and 2025, with an emphasis on penetration-testing techniques in Big Data frameworks. Our search across major digital libraries retrieved 1578 records. After title and abstract screening, 46 articles were selected. Of these, 20 were considered relevant and read in full; among these, only four explicitly applied penetration testing to Hadoop or Spark deployments. The review reveals a shortage of realistic testing environments and standardized metrics for evaluating the effectiveness of mitigation strategies, alongside a strong reliance on generic security tools rather than specialized offensive frameworks. These findings underscore the need for dedicated, framework-aware penetration-testing solutions for Hadoop and Spark, reproducible testing protocols, and tighter integration between offensive assessments and proactive mitigation practices.
- 21 June 2026
- Published by Universidade Federal do Rio Grande do Sul in Revista de Informática Teórica e Aplicada
- Vol. 33 (3) , 45-58
Open AccessPenetration Testing in Big Data Frameworks
Big Data systems are expanding rapidly, and frameworks like Hadoop and Spark are now central to that growth. Yet this expansion also raises new security challenges, particularly regarding how vulnerabilities are identified, assessed, and mitigated in complex, distributed environments. While the existing literature predominantly focuses on defensive mechanisms, systematic evidence on offensive approaches such as penetration testing remains limited. This paper presents a systematic literature review of security assessment practices for Hadoop and Spark between 2015 and 2025, with an emphasis on penetration-testing techniques in Big Data frameworks. Our search across major digital libraries retrieved 1578 records. After title and abstract screening, 46 articles were selected. Of these, 20 were considered relevant and read in full; among these, only four explicitly applied penetration testing to Hadoop or Spark deployments. The review reveals a shortage of realistic testing environments and standardized metrics for evaluating the effectiveness of mitigation strategies, alongside a strong reliance on generic security tools rather than specialized offensive frameworks. These findings underscore the need for dedicated, framework-aware penetration-testing solutions for Hadoop and Spark, reproducible testing protocols, and tighter integration between offensive assessments and proactive mitigation practices.
- Open Access
- 18 June 2026
- Published by MDPI AG in Preprints.org
MoonPhase: A Conceptual and Instructional Framework for Portable Experiential Cybersecurity Learning in Engineering Education
In an age of pervasive connectivity and rapidly evolving cyber threats, cybersecurity has become a transversal competency in engineering education rather than a niche specialism. This paper presents MoonPhase, a multifunctional portable device based on a Raspberry Pi platform, designed to support experiential cybersecurity learning in engineering education contexts by integrating offensive, defensive and educational modes into a single physical artefact. The work builds on a PRISMA-based systematic literature review and a state-of-the-art analysis of portable cybersecurity tools to derive design requirements that balance realism, safety and pedagogical alignment. MoonPhase combines sub-GHz replay capabilities, 2.4 GHz interference and monitoring, fake Wi-Fi access points, packet sniffing and network scanning in a compact, menu-driven platform that can be deployed in regular laboratories and outreach workshops. The paper describes the hardware and software architecture of the device and, more importantly, its instructional framing, outlining learning outcomes, example lab sessions and assessment strategies focused on cybersecurity literacy, systems thinking and ethical awareness. This study reports on the design and implementation of MoonPhase and presents a detailed conceptual and evaluation framework; empirical evidence from classroom deployments will be addressed in subsequent work. The device is positioned as a replicable open educational resource that brings students closer to realistic attack and defence scenarios in controlled settings.
- 18 June 2026
- Published by MDPI AG in Preprints.org
Open AccessMoonPhase: A Conceptual and Instructional Framework for Portable Experiential Cybersecurity Learning in Engineering Education
In an age of pervasive connectivity and rapidly evolving cyber threats, cybersecurity has become a transversal competency in engineering education rather than a niche specialism. This paper presents MoonPhase, a multifunctional portable device based on a Raspberry Pi platform, designed to support experiential cybersecurity learning in engineering education contexts by integrating offensive, defensive and educational modes into a single physical artefact. The work builds on a PRISMA-based systematic literature review and a state-of-the-art analysis of portable cybersecurity tools to derive design requirements that balance realism, safety and pedagogical alignment. MoonPhase combines sub-GHz replay capabilities, 2.4 GHz interference and monitoring, fake Wi-Fi access points, packet sniffing and network scanning in a compact, menu-driven platform that can be deployed in regular laboratories and outreach workshops. The paper describes the hardware and software architecture of the device and, more importantly, its instructional framing, outlining learning outcomes, example lab sessions and assessment strategies focused on cybersecurity literacy, systems thinking and ethical awareness. This study reports on the design and implementation of MoonPhase and presents a detailed conceptual and evaluation framework; empirical evidence from classroom deployments will be addressed in subsequent work. The device is positioned as a replicable open educational resource that brings students closer to realistic attack and defence scenarios in controlled settings.
- Open Access
- 30 January 2026
- Published by IntechOpen
Federated Learning and its Role in Predictive Maintenance
Predictive maintenance (PdM) has emerged as a cornerstone of Industry 4.0, enabling organizations to anticipate equipment failures, optimize maintenance schedules, and reduce operational costs. The convergence of artificial intelligence (AI), the Industrial Internet of Things (IIoT), and advanced analytics has facilitated the transition from reactive and preventive maintenance to predictive and even prescriptive strategies. Within this context, federated learning (FL) offers a transformative approach to PdM by enabling collaborative model training across distributed and privacy-sensitive data sources without the need to centralize raw data. This chapter explores the integration of FL into PdM systems, highlighting its potential to improve sustainability and resilience in industrial maintenance. The discussion extends beyond technical mechanisms to include enabling technologies such as edge and fog computing, IIoT platforms, and blockchain. Furthermore, it addresses the sociotechnical implications of privacy-preserving AI in industrial environments, focusing on its role in supporting worker expertise and ensuring sustainable practices. Case studies, key challenges, and future research directions are presented to provide a comprehensive view of the field.
- 30 January 2026
- Published by IntechOpen
Open AccessFederated Learning and its Role in Predictive Maintenance
Predictive maintenance (PdM) has emerged as a cornerstone of Industry 4.0, enabling organizations to anticipate equipment failures, optimize maintenance schedules, and reduce operational costs. The convergence of artificial intelligence (AI), the Industrial Internet of Things (IIoT), and advanced analytics has facilitated the transition from reactive and preventive maintenance to predictive and even prescriptive strategies. Within this context, federated learning (FL) offers a transformative approach to PdM by enabling collaborative model training across distributed and privacy-sensitive data sources without the need to centralize raw data. This chapter explores the integration of FL into PdM systems, highlighting its potential to improve sustainability and resilience in industrial maintenance. The discussion extends beyond technical mechanisms to include enabling technologies such as edge and fog computing, IIoT platforms, and blockchain. Furthermore, it addresses the sociotechnical implications of privacy-preserving AI in industrial environments, focusing on its role in supporting worker expertise and ensuring sustainable practices. Case studies, key challenges, and future research directions are presented to provide a comprehensive view of the field.
- Open Access
- 16 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Computer Society
- Vol. 6, 1673-1685
Classification of Anomalies in Microservices Using an XGBoost-Based Approach With Data Balancing and Hyperparameter Tuning
Microservice architecture has emerged as a leading paradigm for decomposing large monolithic applications into smaller, autonomous services. Although this approach offers many advantages, its complexity, distributed nature, and substantial scale create significant challenges for monitoring and anomaly detection. The vast volume of generated data further exacerbates computational load and detection latency, complicating the identification of anomalies. This study analyses the impact of data balancing and hyperparameter tuning on anomaly classification in microservices and introduces ADMXGB - Anomaly Detection in Microservices using XGBoost, a XGBoost-based framework tailored for anomaly detection in microservices that seamlessly integrates data balancing with hyperparameter tuning. We propose guidelines to determine appropriate threshold values that balance sensitivity with false positives, and show that the framework is model-agnostic, enabling integration with different machine learning algorithms beyond XGBoost. Validation was performed using a four-stage process encompassing preprocessing, training, validation, and testing. ADMXGB demonstrated improvements in both Accuracy and F1-Score, reaching 99.96% in both metrics on the TraceRCA dataset, outperforming the baseline XGBoost method by a margin of 1.46% in Accuracy and 45.62% in F1-Score. Moreover, ADMXGB achieves reductions in execution time (-86.3%) and memory usage (-21.7%), while maintaining an acceptable CPU overhead. These findings highlight the robustness of ADMXGB in delivering high-accuracy classification in a microservice environment.
- 16 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Computer Society
- Vol. 6, 1673-1685
Open AccessClassification of Anomalies in Microservices Using an XGBoost-Based Approach With Data Balancing and Hyperparameter Tuning
Microservice architecture has emerged as a leading paradigm for decomposing large monolithic applications into smaller, autonomous services. Although this approach offers many advantages, its complexity, distributed nature, and substantial scale create significant challenges for monitoring and anomaly detection. The vast volume of generated data further exacerbates computational load and detection latency, complicating the identification of anomalies. This study analyses the impact of data balancing and hyperparameter tuning on anomaly classification in microservices and introduces ADMXGB - Anomaly Detection in Microservices using XGBoost, a XGBoost-based framework tailored for anomaly detection in microservices that seamlessly integrates data balancing with hyperparameter tuning. We propose guidelines to determine appropriate threshold values that balance sensitivity with false positives, and show that the framework is model-agnostic, enabling integration with different machine learning algorithms beyond XGBoost. Validation was performed using a four-stage process encompassing preprocessing, training, validation, and testing. ADMXGB demonstrated improvements in both Accuracy and F1-Score, reaching 99.96% in both metrics on the TraceRCA dataset, outperforming the baseline XGBoost method by a margin of 1.46% in Accuracy and 45.62% in F1-Score. Moreover, ADMXGB achieves reductions in execution time (-86.3%) and memory usage (-21.7%), while maintaining an acceptable CPU overhead. These findings highlight the robustness of ADMXGB in delivering high-accuracy classification in a microservice environment.
- Open Access
- 19 March 2025
- Published by Universidade Federal do Rio Grande do Sul in Revista de Informática Teórica e Aplicada
- Vol. 32 (2) , 83-93
Big Data in Healthcare: Possibilities and Challenges - A Systematic Literature Review
In today's world, the extensive use of Big Data emerges as a fundamental component in various sectors, and healthcare is no exception. This article explores the importance of using this data for the continuous improvement of patient care, providing them with a better quality of life. However, for this to happen, several challenges must be overcome, especially in data processing and analysis, and in this sector, it is crucial that their accuracy and integrity are not compromised, as they are related to life and death. In this study, we present a survey of technologies, possibilities, and challenges that arise in this field through a systematic review of various articles with cutting-edge approaches to the subject. Consequently, the advantages of using Big Data in healthcare will be highlighted, as well as the critical need to overcome the inherent challenges to achieve efficient and ethical implementation.
- 19 March 2025
- Published by Universidade Federal do Rio Grande do Sul in Revista de Informática Teórica e Aplicada
- Vol. 32 (2) , 83-93
Open AccessBig Data in Healthcare: Possibilities and Challenges - A Systematic Literature Review
In today's world, the extensive use of Big Data emerges as a fundamental component in various sectors, and healthcare is no exception. This article explores the importance of using this data for the continuous improvement of patient care, providing them with a better quality of life. However, for this to happen, several challenges must be overcome, especially in data processing and analysis, and in this sector, it is crucial that their accuracy and integrity are not compromised, as they are related to life and death. In this study, we present a survey of technologies, possibilities, and challenges that arise in this field through a systematic review of various articles with cutting-edge approaches to the subject. Consequently, the advantages of using Big Data in healthcare will be highlighted, as well as the critical need to overcome the inherent challenges to achieve efficient and ethical implementation.
- Open Access
- 11 March 2024
- Published by Universidade Federal do Rio Grande do Sul in Revista de Informática Teórica e Aplicada
- Vol. 31 (1) , 60-67
Predictive Maintenance based on Log Analysis: A Systematic Review
In today’s industries, the Maintenance process of machines and assets implies a significant part of the total operating cost. Many efforts have been made to reduce this cost by optimizing the process and evolving methods that allow information collection on equipment status, avoiding redundant interventions, and predicting the exact moment to perform a maintenance intervention. Using “intelligent” systems that collect data from the operation and remote management systems allows us to gather all the data and apply some methodologies capable of identifying expected behaviors based on past operations. We present a survey of technologies, techniques, and methodologies to give the knowledge background to develop a framework to minimize the occurrence of failures and optimize the process of Predictive Maintenance (PdM) based on the analysis of Log files collected from the various industrial equipment. Generally, these logs contain many records, and many of these records do not directly contribute to evaluating the operation’s machine status. Most of the studies included in this survey use machine learning techniques and focus a significant part of their research on data preprocessing, uniformization and clarification.
- 11 March 2024
- Published by Universidade Federal do Rio Grande do Sul in Revista de Informática Teórica e Aplicada
- Vol. 31 (1) , 60-67
Open AccessPredictive Maintenance based on Log Analysis: A Systematic Review
In today’s industries, the Maintenance process of machines and assets implies a significant part of the total operating cost. Many efforts have been made to reduce this cost by optimizing the process and evolving methods that allow information collection on equipment status, avoiding redundant interventions, and predicting the exact moment to perform a maintenance intervention. Using “intelligent” systems that collect data from the operation and remote management systems allows us to gather all the data and apply some methodologies capable of identifying expected behaviors based on past operations. We present a survey of technologies, techniques, and methodologies to give the knowledge background to develop a framework to minimize the occurrence of failures and optimize the process of Predictive Maintenance (PdM) based on the analysis of Log files collected from the various industrial equipment. Generally, these logs contain many records, and many of these records do not directly contribute to evaluating the operation’s machine status. Most of the studies included in this survey use machine learning techniques and focus a significant part of their research on data preprocessing, uniformization and clarification.
- Open Access
- 1 January 2023
- Published by Associacao Portuguesa de Sistemas de Informacao
Big Data and Traffic Data Analysis: Urban Traffic Forecasting and Management
The paper reviews different methodologies and technologies used in urban traffic management and analysis systems based on Big Data. Several techniques are discussed, such as the installation of sensors, IoT devices and surveillance cameras for data collection, the use of machine learning algorithms and technologies for vehicle identification and classification, the use of Map Reduce techniques for data processing, and the communication between several social network applications to obtain real-time data about the location and movement of users. In addition, models based on neural networks and algorithms such as ABC are proposed for signal change prediction and traffic flow management. The advantages and disadvantages of each approach and how they can be applied to improve urban traffic management and reduce vehicle pollution are highlighted.
- 1 January 2023
- Published by Associacao Portuguesa de Sistemas de Informacao
Open AccessBig Data and Traffic Data Analysis: Urban Traffic Forecasting and Management
The paper reviews different methodologies and technologies used in urban traffic management and analysis systems based on Big Data. Several techniques are discussed, such as the installation of sensors, IoT devices and surveillance cameras for data collection, the use of machine learning algorithms and technologies for vehicle identification and classification, the use of Map Reduce techniques for data processing, and the communication between several social network applications to obtain real-time data about the location and movement of users. In addition, models based on neural networks and algorithms such as ABC are proposed for signal change prediction and traffic flow management. The advantages and disadvantages of each approach and how they can be applied to improve urban traffic management and reduce vehicle pollution are highlighted.