José Maria Marques Cação

I hold a master’s degree in Mechanical Engineering from the University of Aveiro, completed in 2023 with a final grade of 18/20. My master’s thesis, titled “Intelligent Assistant – Development of Algorithms for Monitoring Energy Consumption on the Shop Floor, Bosch”, was awarded with the highest grade of 20/20. Such work focused on developing an intelligent assistant to optimise energy consumption in industrial settings, leveraging technologies such as Digital Twins and Machine Learning (ML) data processing. During the final year of my master’s, I worked as a researcher in the Augmanity project (POCI-01-0247-FEDER-04610), and I am currently a researcher in the Agenda ILLIANCE project (C644919832-00000035 | Project no. 46), both in collaboration with Bosch Termotecnologia S.A. Simultaneously, I am enrolled in the Doctoral Programme in Mechanical Engineering at the University of Aveiro, where my research focuses on data analysis with strong emphasis on applied industrial research, exploring industrial process digitalisation through ML approaches for data processing, as well as Explainable AI (XAI) for increased interpretability. My academic and research career has been particularly focused on industry-oriented innovation and dissemination, where I have already authored and co-authored multiple scientific publications. The first one is available at the University of Aveiro repository (RIA), focused on non-linear optimisation techniques titled “Resolução de problemas com recurso a um algoritmo de otimização GRASP híbrido”. Focused on my current industry-related research, I have co-authorship in a paper published in the Sensors journal, MDPI, titled “Industrial Internet of Things over 5G: A Practical Implementation” (DOI: 10.3390/s23115199). Furthermore, I have already authored and presented papers at four international conferences. Those were the 5th and 6th “International Conference on Industry 4.0 and Smart Manufacturing” (ISM 2023 and ISM 2024, respectively), the “9th International Conference on Internet of Things, Big Data and Security” (IoTBDS 2024), and the “7th International Conference on Technologies for the Wellbeing and Sustainable Manufacturing Solutions” (TEchMA 2024). From these, three contributions were already published in conference proceedings: “Intelligent Assistant for Smart Factory Management” (ISM 2024, DOI: 10.1016/j.procs.2024.01.096), “Optimising Data Processing in Industrial Settings: A Comparative Evaluation of Dimensionality Reduction Approaches” (IoTBDS 2024, DOI: 10.5220/0012734000003705), and “Machine Learning-driven Fault Identification and Classification: a Two-Step Approach for Industrial Applications” (ISM 2024, DOI: 10.1016/j.procs.2025.01.169). Furthermore, from these presentations, I was honoured with the “Best Paper Award” at ISM 2023 and “Best Oral Presentation” award at TEchMA 2024. This emphasises the relevance of my investigative work and its positive impact on the scientific community. My current research focuses on industrial time series data analysis, process digitalisation and optimisation based on ML and Deep Learning (DL) methodologies, and exploration of XAI techniques for enhanced model and data interpretability applied to manufacturing contexts. In alignment with this work, I also currently have a journal paper under peer-review at the “Journal of Industrial Information Integration” (CiteScore = 22.3, Impact Factor = 10.4), comprising a systematic review on XAI approaches explored for industrial fault detection and diagnosis.