Editorial: Affective brain-computer interface in emotion artificial intelligence and medical engineering

[...]the system needs to collect blink data of the previous round of subjects in advance, because different subjects have different blink ranges. [...]subsequent work may need to combine more robust algorithms to classify the blinking of different subjects to improve the performance of the system. [...

Full description

Saved in:
Bibliographic Details
Published inFrontiers in computational neuroscience Vol. 17; p. 1237252
Main Authors Lu, Zhaohua, Wang, Tingwen, Zhang, Ruirui
Format Journal Article
LanguageEnglish
Published Switzerland Frontiers Research Foundation 11.07.2023
Frontiers Media S.A
Subjects
Accuracy
Affect (Psychology)
affective brain-computer interface
Algorithms
Artificial intelligence
Brain
Brain mapping
brain network
Brain research
Computer applications
Computers
Editorials
Electrodes
Electroencephalography
emotion artificial intelligence
Emotional intelligence
Emotions
Functional magnetic resonance imaging
Human-computer interaction
Implants
Interfaces
Magnetic resonance imaging
medical engineering
Medical imaging
Medical research
Mental disorders
Methods
Neural networks
Neuroimaging
Neuroscience
Physiology
R&D
Research & development
Schizophrenia
Spatial discrimination
emotion artificial intelligence
medical engineering
brain network
neuroscience
affective brain-computer interface
Online AccessGet full text

Cover

More Information
Summary:[...]the system needs to collect blink data of the previous round of subjects in advance, because different subjects have different blink ranges. [...]subsequent work may need to combine more robust algorithms to classify the blinking of different subjects to improve the performance of the system. [...]oxygen-based brain imaging technology, such as functional magnetic resonance imaging (fMRI), has better spatial resolution and has been widely used in neuroimaging research, which is an important tool for researchers to explore the mechanisms of brain activity (Coupeau et al., 2022). To solve this problem, Fei et al. proposed a symmetric end-to-end trainable hybrid convolutional neural network (HC-Net) for the small-sample characteristics of MRI data and the properties of thick-layer scanning. [...]the experimental results of applying the model to task-based patients with schizophrenia suggest that it can be used as a stable biological reference standard for stability and noise immunity.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ObjectType-Editorial-2
ObjectType-Commentary-1
Edited and reviewed by: Si Wu, Peking University, China
ISSN:1662-5188
1662-5188
DOI:10.3389/fncom.2023.1237252