Dr Fernando E. Casado
Dr Fernando E. Casado works as a Research Associate at the Personal Robotics Lab (PRL) since March 2023. He received his BSc degree in Computer Science from the University of Santiago de Compostela (USC) in 2017, being awarded the prizes for the best academic record and thesis. In 2018, he studied for the MSc degree in Artificial Intelligence Research offered by Menéndez Pelayo International University (UIMP). In November 2022, he received his PhD at USC, obtaining the highest grade and the Cum Laude distinction. In his thesis, he developed new continual federated machine learning strategies, robust to scenarios where multiple devices or data owners collaborate over time to obtain a shared model. In particular, Fernando focused on situations involving heterogeneous and non-stationary data, as well as concept drift. The proposed algorithms were translated into different applications, including human activity recognition in smartphones and active assistance to robotic wheelchair users. The latter was developed in 2021 during a visit to the PRL.
Fernando's current research interests involve multi-robot and multi-user machine learning to model, adapt and personalise robotic behaviours for trustworthy human-robot interaction.
- Casado, F. E., Lema, D., Iglesias, R., Regueiro, C. V., & Barro, S. (2023). Ensemble and continual federated learning for classification tasks. Machine Learning, 1-41.
- Criado, M. F., Casado, F. E., Iglesias, R., Regueiro, C. V., & Barro, S. (2022). Non-IID data and Continual Learning processes in Federated Learning: A long road ahead. Information Fusion, 88, 263-280.
- Casado, F. E., Lema, D., Criado, M. F., Iglesias, R., Regueiro, C. V., & Barro, S. (2022). Concept drift detection and adaptation for federated and continual learning. Multimedia Tools and Applications, 1-23.
- Casado, F. E., Rodríguez, G., Iglesias, R., Regueiro, C. V., Barro, S., & Canedo-Rodríguez, A. (2020). Walking recognition in mobile devices. Sensors, 20(4), 1189.
- Casado, F. E., & Demiris, Y. (2022, October). Federated Learning from Demonstration for Active Assistance to Smart Wheelchair Users. In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 9326-9331). IEEE.