A5052419642- Manufacturing Process and Optimization
- Constraint Satisfaction and Optimization
- Design Education and Practice
- Explainable Artificial Intelligence (XAI)
- Additive Manufacturing Materials and Processes
- Welding Techniques and Residual Stresses
- Scheduling and Optimization Algorithms
- Semantic Web and Ontologies
- Multi-Agent Systems and Negotiation
- BIM and Construction Integration
- Model-Driven Software Engineering Techniques
- Advanced Manufacturing and Logistics Optimization
- AI-based Problem Solving and Planning
- Data Management and Algorithms
- Structural Engineering and Vibration Analysis
- Neural Networks and Applications
- Engineering and Information Technology
- Cognitive Science and Education Research
- High Entropy Alloys Studies
- Vibration Control and Rheological Fluids
- Transportation Planning and Optimization
- Non-Destructive Testing Techniques
- Additive Manufacturing and 3D Printing Technologies
- Structural Health Monitoring Techniques
- Imbalanced Data Classification Techniques
Universidade do Estado do Rio de Janeiro
2025
Cranfield University
2023
University of Lisbon
1997-2019
Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento
2003-2019
Instituto Superior Técnico
1996-2003
Pontifical Catholic University of Rio de Janeiro
2003
Instituto Politécnico de Lisboa
1997-2001
Imperial College London
1997
University of London
1997
There have been several research works proposing new Explainable AI (XAI) methods designed to generate model explanations having specific properties, or desiderata, such as fidelity, robustness, human-interpretability. However, are seldom evaluated based on their true practical impact decision-making tasks. Without that assessment, might be chosen that, in fact, hurt the overall performance of combined system ML + end-users. This study aims bridge this gap by XAI Test, an...
Although recurrent neural networks (RNNs) are state-of-the-art in numerous sequential decision-making tasks, there has been little research on explaining their predictions. In this work, we present TimeSHAP, a model-agnostic explainer that builds upon KernelSHAP and extends it to the domain. TimeSHAP computes feature-, timestep-, cell-level attributions. As sequences may be arbitrarily long, further propose pruning method is shown dramatically decrease both its computational cost variance of...
Wire-arc directed energy deposition (DED) is suitable for depositing large-scale metallic components at high rates. In order to further increase productivity and efficiency by reducing overall manufacturing time, higher rates are desired. However, the conventional gas metal arc (GMA) based wire-arc DED, characterised input, normally results in remelting reheating relatively rates, process deteriorating mechanical performance. this study, a novel DED with combination of GMA an external cold...
This research evaluated the valorization of pine cone residue as an efficient, low-cost, and eco-friendly biosorbent for removal Cr⁶⁺ from aqueous solutions. Pine cones were characterized by techniques Brunauer-Emmett-Teller (BET), Attenuated total reflectance Fourier-transform infrared spectroscopy (ATR-FTIR), X-ray diffraction (XRD), Scanning electron microscopy (SEM). Firstly, experimental design was performed to optimize adsorption conditions, investigating influence three primary...
Cold wire gas metal arc (CWGMA) additive manufacturing (AM) is more productive and beneficial than the common electric processes currently used in (WAAM). Adding a non-energised to (GMA) system makes it possible overcome process limitation decouple energy input from material feed rate. Two novel control methods were proposed, namely, power travel speed control, which can keep required geometry accuracy WAAM through broad range of thermal conditions. The reinforcement area bead kept constant...
This paper presents a distributed dynamic object model that is aligned with the concept of design history in context problem solving activities. A proposed as an enabling feature for CAD (computer-aided design) allowing teams to work cooperatively, accessing and exchanging information at run time engineering environment. The architecture environment allows artefact properties be associated any relevant aspect process, including those related specification, but also organisation hierarchy,...
The paper addresses a model, framework, and an implemented system for supporting design activities where the use of case-based reasoning may reveal particular appropriateness. In proposed environment, special attention is given to synthesis solutions by means adaptation. A pragmatic combination number artificial intelligence (AI) techniques, considering (CBR) as framing concept, enables implementation that conveniently supports most designers’ cognitive needs. highway bridges was chosen...
Conference paper written by Jorge C.-R. Andrade, João Bento and Francisco Virtuoso presented at IABSE Congress: Structural Engineering for Meeting Urban Transportation Challenges, Lucerne, Switzerland, 18-21 September 2000.