The 8th International Conference on System Reliability and Safety
Sicily, Italy - November 20-22, 2024

Marcio Moura, Federal University of Pernambuco, Brazil

My host institution is the Federal University of Pernambuco (UFPE), where I am associate professor and I’ve developed two general roles. First, I am the research leader at the Center for Risk Analysis, Reliability Engineering and Environmental Modeling (CEERMA), which is a multi and interdisciplinary lab, where students at all levels have carried out their research projects since 2008. Indeed, I believe that my colleagues and I have built at CEERMA a pretty collaborative and team-working environment to develop rigorous research. Thus, we encourage our students and fellows to establish mutual and meaningful connections, which I think it is fundamental and paramount to a productive workplace. Besides this role, I’ve also been a senior visiting professor at The Garrick Institute for the Risk Sciences, University of California, Los Angeles.

My research interests include the following major topics: More specifically, I have worked on Fault Diagnosis and Prognosis of Failure, Machine and Deep Learning, Accelerated Life Testing, Stochastic Processes, Dynamic Complex Systems, Soft Computing, and Modeling and Simulation Techniques.

Secondly, I teach courses for both undergraduate and post-graduate students. I particularly like my involvement in all education levels because I believe, in this way, we could quickly transfer the new findings developed by MD and PhD candidates directly to undergrad students. I think the faster we move our research results in this direction, the more prepared our students are to grapple with their challenges. For undergrad students, I am currently teaching two courses 1) Machine and Deep Learning Models Applied to Reliability Engineering; 2) Techniques for Simulating Industrial Processes, while I am the instructor of the following courses for MD and PhD candidates: 1) Reliability Engineering; 2) Advances in Reliability Engineering; 3) Stochastic Processes. For more details on my work, you can check out these links: ResearcherID; ResearchGate; ORCID; Scopus; Google Scholar.

Speech Title: Multimodal Data-driven Approaches for Inferring Drowsiness from Machine Learning Models in Industrial Environments with Critical Safety Systems

Abstract: Catastrophic accidents have been an issue in complex industries like oil and gas (O&G), chemical, and nuclear sectors, despite ongoing efforts to improve safety. While physical systems have advanced, human factors such as fatigue, drowsiness, and inattention remain significant risks, leading to reduced performance, errors in judgment, and an increased likelihood of accidents. Fatigue-related factors—poor rest, sleep deprivation, night shifts, stress, and prolonged monotony—are common in safety-critical environments and frequently result in drowsiness and lapses in attention. However, the subjective nature of self-reported drowsiness presents a challenge in detecting early signs to reduce potential risks and prevent accidents in organizations where safety and environmental concerns are paramount. Thus, this thesis presents an all-encompassing framework addressing human reliability challenges in safety-critical industrial systems through several key contributions. First, it explores the application of machine learning (ML) and quantum machine learning (QML) for electroencephalogram (EEG) signal analysis, leveraging ensemble models and advanced neural network architectures to improve accuracy in detecting drowsiness. The introduction of variational quantum algorithms applied to EEG data analysis, which highlights quantum computing’s potential to process large, complex datasets in industrial safety contexts, emerges as one of novel contribution of this work. Second, the thesis proposes a data fusion approach that combines physiological and visual (EEG and facial) data to enhance the robustness of drowsiness detection systems. This fusion is implemented at both the decision and feature levels, with experimental results showing significant improvements in recall and accuracy compared to single-modality approaches. Third, the development of a real-time web-based application, DrowsinessNET, integrates the detection model into a practical tool for monitoring drowsiness in high-risk environments such as control rooms in the O&G industry. This application highlights the feasibility of applying advanced detection models in real-world scenarios. Finally, a simulator-based experiment was conducted to assess operator performance in automated O&G operations, particularly focusing on the impact of automation-related factors such as overconfidence, boredom, and inattention. The experiment reveals that automation can induce human errors and reduce attentiveness in monotonous tasks, further emphasizing the critical need for integrating human reliability technologies in safety-critical systems. By advancing the state of the art in human reliability, this thesis contributes to the field by proposing multimodal data-driven models (ML/QML/DL), data fusion techniques, and practical applications to prevent accidents and enhance safety in high-risk industries. Keywords: EEG, O&G, Data fusion, Computer Vision, Machine Learning, Deep Learning, Quantum Machine Learning.