Candidate:

Eliseu Moura Pereira

Date, Time and Location:

17^th of June 2025, 10:00, Sala de Atos, Faculdade de Engenharia da Universidade do Porto

President of the Jury:

Carlos Miguel Ferraz Baquero-Moreno, Full Professor, Department of Informatics Engineering, Faculdade de Engenharia da Universidade do Porto.

Members:

Pedro Nicolau Faria da Fonseca (PhD), Assistant Professor, Department of Electronics, Telecommunications and Computer Science, Universidade de Aveiro;

Paulo Jorge Pinto Leitão (PhD), Principal Coordinating Professor, Department of Electrical Engineering, Instituto Politécnico de Bragança;

André Monteiro de Oliveira Restivo (PhD), Associate Professor, Department of Informatics Engineering, Faculdade de Engenharia da Universidade do Porto;

Gil Manuel Magalhães de Andrade Gonçalves (PhD), Associate Professor with Habilitation, Department of Informatics Engineering, Faculdade de Engenharia da Universidade do Porto (Supervisor).

The thesis was co-supervised by João Pedro Correia dos Reis (PhD), Assistant Researcher, Department of Electrical and Computer Engineering, Faculdade de Engenharia da Universidade do Porto.

Abstract:

Cyber-Physical Production Systems (CPPSs) integrate computation, communication, and control technologies, delivering the flexibility needed for dynamic shop floor reconfiguration and efficient manufacturing. A factory with higher shop floor flexibility has the advantage of higher product customization or changeover, when compared to traditional industries. They manifest this advantage mainly when the industry introduces a new product or because the shop floor produces highly variable products needing constant reconfiguration. Several manufacturers adopt such production philosophy, like in the automotive industry, where a high variability of car models and specifications requires different setups/configurations of the shop floor to manufacture them. In sequential production lines, like car assembly lines, reconfigurable CPPSs play an essential role because processing one product can affect the entire production performance, requiring a shop floor reconfiguration to optimize their execution. A significant challenge in CPPSs arises when reacting to changing conditions, such as new products or requirements, reconfiguration is needed. Current systems rely on manual intervention, leading to significant delays, especially in large industries where reprogramming hundreds of machines can take days or weeks. This thesis addresses this issue by proposing a platform that automatically optimizes software assignment to resources, speeding up development, deployment, and reconfiguration, enabling CPPSs to adapt to external disturbances quickly.

With the purpose of accelerating the development, reconfiguration, and execution of software in CPPSs, this thesis aims to optimize Function Blocks (FBs) assignment to the devices existent in an IEC 61499-based Cyber-Physical System (CPS), reducing the total execution time (reconfiguration time plus FB pipeline execution time). With this main goal, the thesis resulted in the development of 3 tools: 1) the Dynamic Intelligent Architecture for Software and Modular Reconfiguration (DINASORE), that enables the development, execution and manual reconfiguration of IEC 61499-based CPSs, 2) the Task Resources Estimator and Allocation Optimizer (TREAO),  that simulates and optimizes the tasks/FBs assignment to the CPS machines, recommending suitable software layouts for the CPS characteristics, and 3) the Task Assignment Optimization and Synchronization Engine (T-Sync), which integrates the previous two tools in a solution and optimizes in run-time the FBs assignment to the devices existent in an IEC 61499-based CPS.

Integrating these tools in T-Sync resulted in a differentiating solution because it 1) allows online FB assignment to optimize the CPS execution continuously and 2) improves the transparency and interoperability between FBs across IEC 61499-based devices. With this solution, the performance (total execution time) running FBs in reconfigurable CPSs improved by 30% in a simulated environment and 61% in a CPS. In addition to T-Sync improving total execution time, DINASORE enhances reconfiguration efficiency and flexibility, while TREAO streamlines CPS development by optimizing task and FB assignments to available resources. Besides the mentioned ones, during this thesis, other algorithms were implemented and tested for task assignment optimization, and other tools were developed to increase the interoperability and portability in CPSs. The future work envisions the automatic generation of FB pipelines from structured requirements, with formal specifications like UML diagrams, consequently integrating TREAO, manufacturing process simulators, and T-Sync to iteratively validate, optimize, simulate factory layouts, and deploy CPS software with enhanced flexibility and adaptability.

Keywords: Cyber-Physical Production Systems; IEC 61499; Machine Learning; Task Assignment.

Candidate:

Leonardo da Silva Ferreira

Date, Time and Location:

13th of June 2025, 9:30, Sala de Atos, Faculdade de Engenharia da Universidade do Porto

President of the Jury:

Pedro Nuno Ferreira da Rosa da Cruz Diniz, PhD, Full Professor, Department of Informatics Engineering, Faculdade de Engenharia da Universidade do Porto

Members:

Pedro Manuel Henriques da Cunha Abreu, PhD, Associate Professor with habilitation, Department of Informatics Engineering, Faculdade de Ciência e Tecnologia da Universidade de Coimbra;

Paulo Jorge Freitas de Oliveira Novais, PhD, Full Professor, Department of Computer Science, Escola de Engenharia da Universidade do Minho;

Carlos Manuel Milheiro de Oliveira Pinto Soares, PhD, Associate Professor, Department of Informatics Engineering, Faculdade de Engenharia da Universidade do Porto;

Ana Paula Cunha da Rocha, PhD, Associate Professor, Department of Informatics Engineering, Faculdade de Engenharia da Universidade do Porto;

Daniel Augusto Gama de Castro Silva, PhD, Assistant Professor, Department of Informatics Engineering, Faculdade de Engenharia da Universidade do Porto (Supervisor).

The thesis was co-supervised by Professor Mikel Uriarte Itzazelaia, Associate Professor at the Escuela de Ingeniería de Bilbao, Universidad del País Vasco.

Abstract:

With the dynamic evolution of the internet, particularly in domains such as multimedia services, cloud computing, internet of things, virtualization, and artificial intelligence, companies have witnessed significant expansion in their market and services. However, this growth has also exposed numerous vulnerabilities that threaten the confidentiality, integrity, and availability of organizational and personal data. As information technology analysts work to address security system alerts, artificial intelligence has introduced new avenues for breaching security, ranging from simple, low-cost methods to highly sophisticated attacks. Low-cost approaches include phishing and password spraying, which exploit human error and weak password practices. In contrast, more complex threats include advanced persistent attacks and zero-day exploits, which require significant expertise and resources, often disrupting critical systems. Many organizations rely on cybersecurity helpdesk centers, internal or outsourced, to manage incidents. However, these centers often struggle to respond effectively due to data overload and a lack of qualified operators.

This dissertation addresses the shortage of skilled operators and the high volume of incidents in helpdesk operations by developing a ticket management assistant to support human operators in resolving incidents. The framework integrates a context-aware recommender system that identifies the fastest analyst-procedure pair for each incident and continually improves with each treatment followed. To ensure data privacy, this recommender system is trained using artificial data generated by a custom synthetic data generator. Furthermore, this thesis explores the possibility of enhancing this assistant with automated machine learning functionalities to predict incoming tickets. This feature could help managers anticipate workloads and proactively adjust the composition of the security teams.

The development of this framework is supported by the collaboration with a cybersecurity company, S21sec, which provides anonymized historical incident treatment data structures and taxonomies. However, synthetic data generation techniques are essential due to the absence of granular information on incident resolution and related parameters in the shared data set, which also requires privacy. The implemented generator builds artificial datasets that can mimic distributions similar to those observed in the real dataset while emulating real-world behaviours, including ticket prioritization, scheduling, and treatment.

The artificial data generator is evaluated for its efficiency in replicating real-world datasets using similarity measures such as Hellinger distance and Kullback-Leibler divergence. Furthermore, several ticket scheduling scenarios are explored, varying operators’ numbers and distribution across three work shifts. The results demonstrate that this framework can replicate ticket distributions and treatment durations observed in real datasets. Additionally, it allows for the simulation of real-world helpdesk operations, providing a solid foundation for exploring diverse operational contexts without compromising privacy. The analysis of the ticket scheduling consistently shows that scenarios characterized by a high shift imbalance and fewer operators lead to longer wait times and more tickets scheduled for later treatment.

The recommender system is assessed from two perspectives: scalability and impact on ticket treatment. The first phase uses various test datasets with different sizes and numbers of operators, analyzed with metrics such as the average recommendation time and memory usage. In contrast, the impact on ticket treatment is examined by considering improvements in ticket waiting times before being allocated to an operator and the response time required for their resolution, using different recommendation acceptance degrees. The results indicate that the number of operators the recommender system utilizes has a slightly larger impact on its scalability than the number of test tickets. Both features show a similar linear growth pattern regarding the referred metrics, but the number of operators has a larger slope. Integrating this recommender system into the ticket treatment reduced the average response time by 37.9\% to 45.1\% and the average wait time by 62.2\% to 63.2\%, assuming operators always accept the recommendations. With varying recommendation acceptance rates, the average wait time remains constant, while the response time improvement ranges from 0.4\% to 11.7\%.

The potential application of automated machine learning for predictive analysis is explored through a case study, comparing the system’s recommended team dimensionality decisions with expected outcomes. The case study evaluates the system based on prediction accuracy and its ability to suggest team size adjustments. Among the tested dataset distributions, models trained in three years of data outperformed those trained on four years, showing a better mean average error using real data on ticket frequency throughout the year. Regarding team dimensionality recommendations, including hiring or dismissing operators, the tool-based on automated machine learning frequently proposed decisions closely aligned with those that could have been proposed in the same period.

Collectively, these results show that the proposed framework can optimize ticket treatment workflows in real-world applications, leading to more efficient use of resources and reduced operational delays. Furthermore, its ability to simulate real-world operations without compromising privacy allows security operations centers to test several scenarios and refine their strategies.

Keywords: Helpdesk; Ticket; Cybersecurity; Synthetic Data; Recommendation Systems.

Candidate:

Pedro Rodrigo Caetano Strecht Ribeiro

Date, Time and Location:

13th of June 2025, 15:00, Sala de Atos, Faculdade de Engenharia, Universidade do Porto 

President of the Jury:

Rui Filipe Lima Maranhão de Abreu, PhD, Full Professor, Department of Informatics Engineering, Faculdade de Engenharia, Universidade do Porto 

Members:

Johannes Fürnkranz, PhD, Full Professor, Department of Computer Science of the Institute for Application-Oriented Knowledge Processing at the Johannes Kepler University Linz, Austria;

José María Alonso Moral, PhD, Full Professor, Department of Electronics and Computing, Escuela Técnica Superior de Ingeniería de la Universidad de Santiago de Compostela, Spain;

José Luís Cabral de Moura Borges, PhD, Associate Professor, Department of Industrial Engineering and Management, Faculdade de Engenharia, Universidade do Porto;

João Pedro Carvalho Leal Mendes Moreira, PhD, Associate Professor, Department of Informatics Engineering, Faculdade de Engenharia, Universidade do Porto (Supervisor).

The thesis was co-supervised by Carlos Manuel Milheiro de Oliveira Pinto Soares, PhD, Associate Professor, Department of Informatics Engineering, Faculdade de Engenharia, Universidade do Porto. 

Abstract:

This thesis investigates the challenges and opportunities presented by the increasing trend of using multiple specialized models, referred to as operational models, to address complex data analysis problems. While such an approach can enhance predictive performance for specific sub-problems, it often leads to fragmented knowledge and difficulties understanding overarching organizational phenomena. This research focuses on synthesizing the knowledge embedded within a collection of decision tree models chosen for their inherent interpretability and suitability for knowledge extraction. For example, a company with chain stores or a university with diverse programs, each using dedicated prediction models (sales or dropout, respectively). While these localized models are important, a global perspective is valuable organization-wide. However, managing many operational models, especially for cross-program/store analysis, can be overwhelming.

A methodology framed within a comprehensive framework is introduced to merge sets of operational models into consensus models. These consensus models are directed towards higher level decision-makers, enhancing the interpretability of knowledge generated by the operational models. The framework, named Inmplode, addresses common challenges in model merging and presents a highly customizable process. This process features a generic workflow and adaptable components, detailing alternative approaches for each subproblem encountered in the merging process.

The framework was applied to four public datasets from diverse business areas and a case study in education using data from the University of Porto. Different model merging approaches were explored in each case, illustrating various process instantiations. The model merging process revealed that the resulting consensus models are frequently incomplete, meaning they cannot cover the entire decision space, which can undermine their intended purpose. To address the issue of incompleteness, two novel methodologies are explored: one relies on the generation of synthetic datasets followed by decision tree training. At the same time, the other uses a specialized algorithm designed to construct a decision tree directly from aggregated (i.e., symbolic) data.

The effectiveness of these methodologies in generating complete consensus models from incomplete rule sets is evaluated across the five datasets. Empirical results demonstrate the feasibility of overcoming the incompleteness issue, contributing to knowledge synthesis and decision tree modeling. However, tradeoffs were identified between completeness and interpretability, predictive performance, and the fidelity of consensus models.

Overall, this research addresses a critical gap in the literature by providing a comprehensive framework for synthesizing knowledge from multiple decision tree models, focusing on overcoming the challenge of incompleteness. The conclusions have implications for organizations seeking to use specialized models while maintaining a holistic understanding of the analyzed phenomenon.

Keywords: interpretability; rule-based models; model merging framework; decision trees; completeness.

Candidate:
Alexandre Resende Clément

Date, Time and Location:
5th of June 2025, 14:30, Sala de Atos, Faculdade de Engenharia, Universidade do Porto

President of the Jury:
António Fernando Vasconcelos Cunha Castro Coelho, PhD, Associate Professor with Habilitation, Department of Informatics Engineering, Faculdade de Engenharia, Universidade do Porto

Members:
Marcelo Mortensen Wanderley, PhD, Full Professor, Department of Music Research, Schulich School of Music, McGill University, Canadá;
Damián Keller, PhD, Associate Professor, Centro de Educação, Letras e Artes da Universidade Federal do Acre, Brasil;
Sofia Carmen Faria Maia Cavaco, PhD, Assistant Professor, Informatics Department, Faculdade de Ciências e Tecnologia, Universidade NOVA de Lisboa;
Rui Pedro Amaral Rodrigues, PhD, Associate Professor, Department of Informatics Engineering, Faculdade de Engenharia, Universidade do Porto;
Gilberto Bernardes de Almeida, PhD, Department of Informatics Engineering, Faculdade de Engenharia, Universidade do Porto (Supervisor).

Abstract:

“This thesis explores the potential of mobile handheld devices as tools for digital musical instrument interaction and participatory performance. Guided by the principles of ubiquitous music and intuitive interaction, the research investigates how mobile handheld devices can address challenges and unlock opportunities in contemporary music-making through participatory frameworks, gesture mappings, and multimodal feedback. Three experiments form the foundation of this study. The first describes and evaluates a system that enables large-scale audience participation in multimedia performances. It highlights the ability of mobile handheld devices to engage users and foster collaboration but reveals challenges in designing intuitive interactions for untrained participants. The second experiment examines how users instinctively map gestures to core musical parameters, such as pitch, duration, and amplitude, identifying natural trends – and the influence of musical training and experience on interaction strategies. The third focuses on evaluating the impact of multimodal feedback, combining auditory, visual, and haptic modalities, in note pitch tuning tasks.
The findings underscore the importance of designing standardised interaction guidelines and integrating multimodal feedback to make digital musical instruments more accessible and intuitive. Experiment 1 showed that the lack of a unified interaction model limited intuitive engagement, highlighting the need for standards that balance individual creativity with group intent. Experiment 2 found clear user preferences for gesture mappings of onset, pitch, and duration, shaped by cultural familiarity, and supporting context-aware design. Experiment 3 showed that while multimodal feedback had little immediate effect on accuracy, it improved user confidence and may aid long-term learning. This research advances the understanding of how mobile handheld devices can support participatory and creative music-making, contributing to the development of inclusive, user-friendly, and versatile musical tools.”