Researchers in Residence
LEAP’s team of Researchers in Residence provide in-house capability to our Research and Fellowship programmes. As part of the Hub’s funding calls, applicants can request up to 20% FTE of one of the researchers for consultation and/or secondment onto projects.
Each team member has a specific focus (Data Science, Human Computer Interaction and Software Development) however there are areas where their expertise crosses over. We’ve compiled their experience below to help support requests for their time from potential funding applicants.
The researcher team can be contacted directly by emailing: leap-researchers-in-residence@bristol.ac.uk
Nawid Keshtmand
Researcher-in-residence: Data Science
- Experience in working with traditional machine learning algorithms such as Linear discriminant analysis, Support Vector Machines and decisions trees for the purpose of classifying hand gestures using mechanomyography signals.
- Experience in anomaly detection in deep learning models, particularly self-supervised learning models. This includes properties of anomalous data as well as approaches to detect anomalies.
- Experience working in areas related to machine learning explainability, particularly in the area of counterfactual explanations. This includes using the framework of counterfactuals to explain why a data point is considered anomalous. Additionally, Nawid has worked on using counterfactuals for Intensive Care unit data, where counterfactuals are used evaluate the trajectory of a patient.
Emily Nielsen
Researcher-in-residence: Human Computer Interaction (HCI)
- Experience designing and conducting user studies with patients (questionnaires, workshops, focus groups, interviews).
- Experience collaborating with industry and healthcare professionals in exploring and shaping solutions to healthcare problems.
- Experience creating low-fidelity probes and prototypes for evaluation (e.g., paper-based prototypes, Figma prototypes, simple web development).
- Experience creating representational artefacts to facilitate multi-stakeholder problem solving [cooney2018] (e.g., diagram of patient journey to identify opportunities for improvement).
- Experience with participant recruitment, promotion and outreach for hard-to-reach populations.
- Experience using qualitative (e.g., thematic analysis) and quantitative analysis techniques (e.g., statistical tests, time-series and Shewhart chart analysis).
Miquel Perello Nieto
Researcher-in-residence: Data Science
- Experience in working with a range of machine learning algorithms including classification problems (multiclass, time series), deep learning, weak labels and missing value imputation.
- Experience in data mining, including exploratory tools, visualisation methods, clustering, relational and non-relational databases.
- Experience in AI, including search algorithms, explainability methods, utilising ontologies and knowledge bases.
- Experience working in digital health, involving discussions with clinicians to find reasonable solutions to real health problems, design, implementation and evaluation of the generated ideas.
- Experience with high-performance computing (e.g. designing highly parallel experiments that can be run in computing clusters).
- Experience with embedded systems such as real-time operating systems and other embedded devices, including communication protocols between hardware and software nodes.
Matthew Wragg
Researcher-in-residence: Software Development
- Experience with a wide range of technologies (web, mobile, AR/VR etc.) and software engineering practices (version control, testing, documentation etc.)
- Experience creating software for use in studies with human participants.
- Experience creating systems with interdisciplinary collaborators (artists, clinicians, academics etc.)
- Experience with 3D modelling and printing techniques.
- Experience interviewing patients/clinicians (including transcription, analysis).
- Experience conducting observational studies of human interaction with systems.
- Experience designing and conducting longitudinal research.
- Experience analysing qualitative data (video analysis/thematic analysis etc.) and quantitative data (statistics, power analysis etc.)
- Experience creating ethics applications for studies with human participants and for handling highly sensitive patient health related data.