A5055061804- Semiconductor materials and devices
- Machine Learning in Materials Science
- Metal and Thin Film Mechanics
- Aerosol Filtration and Electrostatic Precipitation
- Diamond and Carbon-based Materials Research
- Catalysis and Oxidation Reactions
- Particle Dynamics in Fluid Flows
- Forecasting Techniques and Applications
- Thin-Film Transistor Technologies
- Heat Transfer and Optimization
- Business Process Modeling and Analysis
- Modeling, Simulation, and Optimization
- Heat Transfer and Boiling Studies
- Software Engineering Research
- Retinal Imaging and Analysis
- Complex Systems and Decision Making
- Manufacturing Process and Optimization
- Probabilistic and Robust Engineering Design
- Model Reduction and Neural Networks
- Catalytic Processes in Materials Science
- Groundwater flow and contamination studies
- Machine Learning and Algorithms
- Statistical and Computational Modeling
- ZnO doping and properties
- Gas Sensing Nanomaterials and Sensors
University of Luxembourg
2022-2024
National Technical University of Athens
2022-2024
Centre National de la Recherche Scientifique
2021-2022
Centre Interuniversitaire de Recherche et d’Ingénierie des Matériaux
2021-2022
Université Toulouse III - Paul Sabatier
2021-2022
Institut National Polytechnique de Toulouse
2022
Université de Toulouse
2021
Laboratoire de Génie Chimique
2021
Silicon oxynitride (SiOxNy) thin films are widely encountered in today's major key enabling technologies. Exhibiting tunable properties dependent on the nitrogen content, they attract attention applications requiring thermal stability, high dielectric constant, corrosion resistance, surface passivation, and effective ion diffusion barrier. Identification of minimum desired level incorporation for each application is important simultaneously optimizing material deposition process. In this...
This study introduces a machine learning framework tailored to large-scale industrial processes characterized by plethora of numerical and categorical inputs. The aims (i) discern critical parameters influencing the output (ii) generate accurate out-of-sample qualitative quantitative predictions production outcomes. Specifically, we address pivotal question significance each input in shaping process outcome, using an Chemical Vapor Deposition (CVD) as example. initial objective involves...
This work introduces a comprehensive approach utilizing data-driven methods to elucidate the deposition process regimes in Chemical Vapor Deposition (CVD) reactors and interplay of physical mechanism that dominate each one them. Through this work, we address three key objectives. Firstly, our methodology relies on outcomes, derived by detailed CFD model, identify clusters "outcomes" corresponding distinct regimes, wherein relative influence input variables undergoes notable shifts....
This work introduces a machine learning framework that allows the investigation of influence reaction centers on metabolic state astrocyte cells. The proposed ML takes advantage spatial data stemming from numerical simulations for different center configurations and following: (i) Discovery cell groups similar states configuration within each group. approach an analysis importance specific location potentially critical cell. (ii) Qualitative prediction energetic (based [ATP]: [ADP])...
Important variables of processes are, in many occasions, categorical, i.e. names or labels representing, e.g. categories inputs, types reactors a sequence steps. In this work, we use Large Language Models (LLMs) to derive embeddings such inputs that represent their actual meaning, reflect the ``distances" between categories, how similar dissimilar they are. This is marked difference from current standard practice using binary, one-hot encoding replace categorical with sequences ones and...