I am a Research Associate at Imperial College London (UK) affiliated with the Department of Mathematics, the Dementia Research Institute and Imperial College Business School.
My research deals with the analysis of complex systems that can be abstracted as networks or graphs. In particular, I work on applications and development of graph theoretical tools. On the theoretical front, I am exploring the connection between graph theory and deep learning. By combining graphs, graph embeddings, feature extraction and deep learning, I aim to reveal the methods through which we can learn complex geometries using deep learning methods. On the application front, I show the benefit of modelling complex systems in areas including biology, economics and medicine, as networks and using graph theoretic measures to extract useful information.
I also work on time-series analysis methodologies, such as massive feature extraction or deep learning tools, to reveal insights into mechanisms of diseases or to segment human behaviours.
I studied Physics at the University of Bristol with a focus on superconductors. Afterwards, I spent a brief year working for a wind turbine company on brake technologies. Subsequently, I joined Imperial College for an MRes PhD in Chemical Biology under the supervision of Prof. Mauricio Barahona, Prof. David Klug, Prof. Keith Willison and Prof. Sophia Yaliraki. In 2017, I moved to the Department of Mathematics to join the Centre for Mathematical Precision Healthcare as a Research Associate under the supervision of Prof. Mauricio Barahona. I collaborate on projects with the Department of Medicine, Department of Chemistry and Imperial College Business School.
et al., 2022, Prediction of hospital-onset COVID-19 infections using dynamic networks of patient contact: an international retrospective cohort study., Lancet Digit Health, Vol:4, Pages:e573-e583
Peach R, Arnaudon A, Barahona M, 2022, Relative, local and global dimension in complex networks, Nature Communications, Vol:13, ISSN:2041-1723
et al., 2022, Predicting hospital-onset COVID-19 infections using dynamic networks of patient contact: an international retrospective cohort study, The Lancet Digital Health, ISSN:2589-7500
et al., 2022, Improved contact tracing using network analysis and spatial-temporal proximity, IMED conference, ELSEVIER SCI LTD, Pages:S20-S20, ISSN:1201-9712