Fábio Lopes obtained his BSc and MSc from the University of Coimbra in Coimbra, Portugal, where he studied Biomedical Engineering with specialisation in Clinical Informatics and Bioinformatics. His MSc thesis was focused on clinical natural language processing using machine learning algorithms. After finishing his MSc, he started his PhD in Informatics Engineering. His work was carried out at the Adaptive Computation group, Centre for Informatics and Systems of the University of Coimbra, Portugal and at the Epilepsy Center, Department of Neurosurgery, University Medical Center Freiburg, Germany. During his PhD, Fábio focused on improving current state-of-the-art approaches to denoise electroencephalograms. Furthermore, he worked on developing seizure prediction models able to adapt to different types of data distributions. Both tasks were developed using deep learning algorithms.

Fábio joined the Atomistic Simulations group of the nanotech@surfaces Laboratory at Empa in October 2023 and is currently working on developing a metadata schema using openBIS.

Data Science, Artificial Intelligence, Machine Learning, Biosignal Time-series Analysis, Natural Language Processing

F. Lopes, J. Agnelo, C.A. Teixeira, N. Laranjeiro, J. Bernardino, J. (2020). Automating orthogonal defect classification using machine learning algorithms. Future generation computer systems, 102, 932-947. DOI: 10.1016/j.future.2019.09.009

F. Lopes, C. Teixeira, H.G. Oliveira, (2019). Contributions to clinical named entity recognition in Portuguese. In Proceedings of the 18th BioNLP Workshop and Shared Task (pp. 223-233). DOI: 10.18653/v1/W19-5024

F. Lopes, A., Leal, J. Medeiros, M.F. Pinto, A. Dourado, M. Dümpelmann, C. Teixeira (2021). Automatic electroencephalogram artifact removal using deep convolutional neural networks. IEEE Access, 9, 149955-149970. DOI: 10.1109/ACCESS.2021.3125728

F. Lopes, A. Leal, M.F. Pinto, A. Dourado, A. Schulze-Bonhage, M. Dümpelmann, C. Teixeira (2023). Removing artefacts and periodically retraining improve performance of neural network-based seizure prediction models. Scientific Reports, 13(1), 5918. DOI: 10.1038/s41598-023-30864-w