Our paper "A Self-Supervised Learning Approach for Detecting Non-Psychotic Relapses Using Wearable-based Digital Phenotyping" is accepted at ICASSP 2024.

I am happy to announce that our paper “A Self-Supervised Learning Approach for Detecting Non-Psychotic Relapses Using Wearable-based Digital Phenotyping” got accepted at this year’s ICASSP Conference, which will be held in Seoul, South Korea from April 14 to April 19! Our paper focuses on a deep learning-based method for the early detection of non-psychotic relapses based on data from wearable devices collected from patients with non-psychotic disorders. This is a joint work with S. Eleftheriou, C. Nikou and T. Giannakopoulos conducted as part of our research in the Mutimedia Analysis Group of NCSR “Demokritos”. We will have the chance to present our work in a few months from now in Seoul.