Ensemble and personalized Transformer models for subject identification and relapse detection in e-Prevention Challenge

In this short paper, we present the devised solutions for the subject identification and relapse detection tasks, which are part of the e-Prevention Challenge hosted at the ICASSP 2023 conference [1] [2] [3]. We specifically design an ensemble scheme of six models - five transformer-based ones and a CNN model - for the identification of subjects from wearable devices, while a personalized - one for each subject - scheme is used for relapse detection in psychotic disorder. Our final submitted solutions yield top performance on both tracks of the challenge: we ranked 2nd on the subject identification task (with an accuracy of 93.85%) and 1st on the relapse detection task (with a ROC-AUC and PR-AUC of about 0.65). Code and details are available at https://github.com/perceivelab/e-prevention-icassp-2023.