Människocentrerade adaptiva system
Hur kan adaptiva och affektmedvetna system stödja lärande och välbefinnande utan att övertolka glesa, intima signaler?
System som anpassar sig efter människor behöver vara ärliga om hur lite de vet om personen framför sig.
My doctoral research sat here: machine learning on wearable sensor data to monitor the mental health of frontline healthcare workers. The useful finding was as much about limits as about accuracy. Signals from the body are sparse, noisy and deeply contextual, and a model that performs well on a cohort can still be the wrong instrument for an individual decision.
The same tension runs through adaptive learning systems, which I worked on earlier in education settings: personalisation is only as good as the model of the learner, and that model is always thinner than the learner.
Utvalda arbeten
- PolicyAI in health: how smart technology is breaking new frontiers in medical careFörfattare, Digital Skills and Jobs Platform, European Commission2026
- ArtikelData preprocessing and machine learning in wearable data analysis: assessing efficacy and challenges for mental health monitoring of healthcare professionalsFörfattare, Université Paris Cité2024
- ArtikelThe Alternate Education for the 21st CenturyMedförfattare, 2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)2019
- RapportCHI, a knowledge-sharing digital platform powered by machine learningFörfattare, UNESCO MGIEP2019
Forskningsprojekt
Bärbara sensordata och vårdpersonals välbefinnande
Doktorandforskning om huruvida data från bärbara sensorer kan stödja bevakning av psykisk ohälsa hos vårdpersonal i frontlinjen, och var metoden brister.
Nästa / Område
Datastyrning för system i allmänhetens tjänst