Files and links (1)
SubmittedarXiv.org - Non-exclusive license to distribute, Open
Conference proceeding
Interpretable SincNet-based Deep Learning for Emotion Recognition from EEG brain activity
2021 43RD ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY (EMBC), v 2021, pp 412-415
Nov 2021
PMID: 34891321
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
Machine learning methods, such as deep learning, show promising results in the medical domain. However, the lack of interpretability of these algorithms may hinder their applicability to medical decision support systems. This paper studies an interpretable deep learning technique, called SincNet. SincNet is a convolutional neural network that efficiently learns customized band-pass filters through trainable sinc-functions. In this study, we use SincNet to analyze the neural activity of individuals with Autism Spectrum Disorder (ASD), who experience characteristic differences in neural oscillatory activity. In particular, we propose a novel SincNet-based neural network for detecting emotions in ASD patients using EEG signals. The learned filters can be easily inspected to detect which part of the EEG spectrum is used for predicting emotions. We found that our system automatically learns the high-alpha (9-13 Hz) and beta(13-30 Hz) band suppression often present in individuals with ASD. This result is consistent with recent neuroscience studies on emotion recognition, which found an association between these band suppressions and the behavioral deficits observed in individuals with ASD. The improved interpretability of SincNet is achieved without sacrificing performance in emotion recognition.
Metrics
Details
- Title
- Interpretable SincNet-based Deep Learning for Emotion Recognition from EEG brain activity
- Creators
- Juan Manuel Mayor-Torres - University of TrentoMirco Ravanelli - Mila - Quebec Artificial Intelligence InstituteSara E. Medina-DeVilliers - Stony Brook UniversityMatthew D. Lerner - Stony Brook UniversityGiuseppe Riccardi - University of Trento
- Publication Details
- 2021 43RD ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY (EMBC), v 2021, pp 412-415
- Series
- IEEE Engineering in Medicine and Biology Society Conference Proceedings
- Publisher
- IEEE
- Number of pages
- 4
- Grant note
- R01MH110585 / NIMH; United States Department of Health & Human Services; National Institutes of Health (NIH) - USA; NIH National Institute of Mental Health (NIMH) 1531492 / National Science Foundation grant; National Science Foundation (NSF) AAF Fund for Communication
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- A.J. Drexel Autism Institute
- Web of Science ID
- WOS:000760910500096
- Scopus ID
- 2-s2.0-85122495851
- Other Identifier
- 991021862313304721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- International collaboration
- Web of Science research areas
- Engineering, Biomedical
- Engineering, Electrical & Electronic