Ensemble and Personalized Transformer Models for Subject Identification and Relapse Detection in E-Prevention Challenge
Salvatore Calcagno, Raffaele Mineo, Daniela Giordano, Concetto Spampinato
Abstract
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 2 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">nd</sup> on the subject identification task (with an accuracy of 93.85%) and 1 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">st</sup> 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.
BibTeX
@inproceedings{icassp2023_ensembleandperso,
title = {Ensemble and Personalized Transformer Models for Subject Identification and Relapse Detection in E-Prevention Challenge},
author = {Salvatore Calcagno and Raffaele Mineo and Daniela Giordano and Concetto Spampinato},
booktitle = {ICASSP 2023},
year = {2023}
}