Deep learning-based multi-brain capsule network for Next-Gen Clinical Emotion recognition using EEG signals

Deep learning-based multi-brain capsule network for Next-Gen Clinical Emotion recognition using EEG signals

Deep learning techniques are crucial for next-generation clinical applications, particularly in Next-Gen Clinical Emotion recognition. To enhance classification accuracy, we propose an Attention mechanism based Capsule Network Model (At-CapNet) for Multi-Brain Region. EEG-tNIRS signals were collecte...

Full description

Saved in:
Bibliographic Details
Main Authors: Ritu Dahiya, Mamatha G, Shila Sumol Jawale, Santanu Das, Sagar Choudhary, Vinod Motiram Rathod, Bhawna Janghel Rajput
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Neuroscience Informatics
Subjects:
Clinical emotion recognition
Transactional NIRS
Capsule network
Deep learning
EEG
Online Access:http://www.sciencedirect.com/science/article/pii/S2772528625000184
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep learning techniques are crucial for next-generation clinical applications, particularly in Next-Gen Clinical Emotion recognition. To enhance classification accuracy, we propose an Attention mechanism based Capsule Network Model (At-CapNet) for Multi-Brain Region. EEG-tNIRS signals were collected using Next-Gen Clinical Emotion-inducing visual stimuli to construct the TYUT3.0 dataset, from which EEG and tNIRS features were extracted and mapped into matrices. A multi-brain region attention mechanism was applied to integrate EEG and tNIRS features, assigning different weights to features from distinct brain regions to obtain high-quality primary capsules. Additionally, a capsule network module was introduced to optimize the number of capsules entering the dynamic routing mechanism, improving computational efficiency. Experimental validation on the TYUT3.0 Next-Gen Clinical Emotion dataset demonstrates that integrating EEG and tNIRS improves recognition accuracy by 1.53% and 14.35% compared to single-modality signals. Moreover, the At-CapNet model achieves an average accuracy improvement of 4.98% over the original CapsNet model and outperforms existing CapsNet-based Next-Gen Clinical Emotion recognition models by 1% to 5%. This research contributes to the advancement of non-invasive neurotechnology for precise Next-Gen Clinical Emotion recognition, with potential implications for next-generation clinical diagnostics and interventions.
ISSN:2772-5286

Similar Items