Profile

Overview

A Senior Research Software Engineer (SRSE) in the Research Software Engineering Group at Exeter.

Qualifications

PhD Computer Science, University of Exeter

MSci Computer Science and Mathematics, University of Exeter

Career

During her MSci, Fliss worked on a project in collaboration with the Royal Devon and Exeter Hospital looking into automating the identification of cancerous tumours in the head and neck, as well as the delineation of the operable region. She also completed an internship at the Met Office. More specifically, she was an intern for the Analysis, Visualisation and Data (AVD) Team and contributed a new aggregator to Iris, an open source Python package for analysing and visualising meteorological and oceanographic data sets.

For her PhD, Fliss undertook interdisciplinary research with the University of Exeter Medical School’s Mental Health Research Group. The aims of the research were to investigate the use of machine learning for distinguishing between people with and without dementia, as well as differentiating between key dementia subtypes where appropriate; and to gain an understanding of the inherent structure of dementia data to ultimately investigate disease signatures. The research prompted the development of two machine learning approaches, and gave rise to what could be deemed valuable findings concerning dementia and its diagnosis.

Since joining the RSE Group at Exeter, Fliss has been involved in the following projects:

• Project Bluebird - Advancing probabilistic machine learning to deliver safer, more efficient, and predictable air traffic control.
• Cornwall FLOW Accelerator - Aiming to underpin the deployment of 1000MW worth of offshore wind by 2030, developing a low carbon footprint approach to floating offshore wind (FLOW) operations.
• Precision Analysis - Aiming to distinguish between women with ductal carcinoma in situ (DCIS) who will develop breast cancer and those who won't, which could ultimately save many women from unnecessary cancer treatment.
• Quantum Machine Learning for Fraud Detection - Scoping the potential of quantum machine learning algorithms for fraud detection to inform the quantum effort at HSBC.
• NetClamp - Generating collective rhythms in biological neural networks using mathematical models and an experimental rig.
• Amusing Arepo - Creating an interface to Arepo in AMUSE (the Astrophysical Multipurpose Software Environment).
• Eden Model Code Review - Advising a student on their codebase for their PhD project.

Back to top