On-Device Transfer Learning for Personalising Psychological Stress Modelling using a Convolutional Neural Network
This work addresses the problem of limited generalizability in stress modeling for individuals, offering a personalized solution that could enable better interventions, though it is incremental in applying transfer learning to this domain.
The paper tackles the challenge of personalizing stress detection models by proposing an on-device transfer learning approach using a 1D CNN, which improves cross-domain performance by leveraging a base model trained on data from 20 participants and small real-world personal datasets.
Stress is a growing concern in modern society adversely impacting the wider population more than ever before. The accurate inference of stress may result in the possibility for personalised interventions. However, individual differences between people limits the generalisability of machine learning models to infer emotions as people's physiology when experiencing the same emotions widely varies. In addition, it is time consuming and extremely challenging to collect large datasets of individuals' emotions as it relies on users labelling sensor data in real-time for extended periods. We propose the development of a personalised, cross-domain 1D CNN by utilising transfer learning from an initial base model trained using data from 20 participants completing a controlled stressor experiment. By utilising physiological sensors (HR, HRV EDA) embedded within edge computing interfaces that additionally contain a labelling technique, it is possible to collect a small real-world personal dataset that can be used for on-device transfer learning to improve model personalisation and cross-domain performance.