Julia A. Meister

Welcome to my page!

I am a PhD Student researching uncertainty quantification and Confident Machine Learning for Digital Health, focusing on real-world applications. Supervised by Dr Khuong Nguyen, I joined the University of Brighton after completing my BSc and MSc degrees at Royal Holloway, University of London.

News:

• March 2023 - Winner of the Bronze Sustainability Award in the Parliamentary and Scientific Committee's STEM for BRITAIN 2023 competition.
• Jan 2023 - Journal article "Assessing long-term medical remanufacturing emissions with Life Cycle Analysis", published by MDPI.
• Dec 2022 - Senior Research Support Assistant, developing a Knowledge Graph to extract data relationships from social media automatically. In collaboration with Ziggi Analytics (UK).
• Nov 2022 - Won the Best Poster Award at the Machine Learning for Healthcare conference, organised by the Institute of Physics in London.
• Aug 2022 -
  • Published the proceedings paper "Cough-based COVID-19 detection with audio quality clustering and confidence measure based learning". Presented at the COPA 2022 conference, where it won the Best Student Paper Award.
  • Published the proceedings paper "Audio feature ranking for sound-based COVID-19 patient detection", presented at the EPIA 2022 conference.
• July 2022 - Published the proceedings paper "A novel cough audio segmentation framework for COVID-19 detection", presented at the ODAK 2022 conference.
• June 2022 - Winner of the "3 Minute Thesis" (3MT) competition. Represented the University of Brighton at the UK national quarter-final.
• Apr 2022 - Research Officer, developed novel uncertainty quantification method for Deep Learning algorithms with widespread applications for risk-sensitive prediction tasks.
• Feb 2022 - Research Officer on a 6-month joint project with the NHS (England), AMDR (USA), and Innovative Health (USA). Built carbon footprint models to support sustainable medical device procurement.
• Oct 2021 - Presented research findings for automatic detection of COVID-19 coughs at the IRSH 2021 conference.
• July 2021 - Supervised and supported a Brighton undergraduate student's research activities as part of the Santander-funded "Global Challenges" grant.
• Apr 2021 - 1 of 7 winners of the Santander-funded "Global Challenges" grant, in collaboration with Dr Khuong Nguyen, Prof Zhiyuan Luo, and Cardisio (Germany), an industry practitioner specialising in Machine Learning for healthcare.
• Jan 2021 - Joined the University of Brighton as a PhD student.
• Dec 2020 - Awarded MSc in Data Science and Analytics, thesis titled "Conformal Predictors for detecting harmful respiratory events".

Given a Machine Learning prediction, how confident are you that it is correct?

Often, we assume that models will be about as successful on future samples as they are on their training data. Without uncertainty quantification, ML's application in the safety-critical healthcare setting can be unreliable.

In contrast, Confidence ML associates individual predictions with confidence levels to provide guaranteed error probabilities per sample. My research centres on developing and improving ML techniques to provide confident and efficient predictions for Digital Health applications.

Keywords: Digital Health • Confidence Machine Learning • Data Science and Analytics