Jove
Visualize
Contact Us

Related Concept Videos

JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies
  1. Home
  3. Music Emotion Recognition Based On Temporal Convolutional Attention Network Using Eeg.
  1. Home
  3. Music Emotion Recognition Based On Temporal Convolutional Attention Network Using Eeg.

Related Experiment Video

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.7K

Music emotion recognition based on temporal convolutional attention network using EEG.

Yinghao Qiao1,2,3, Jiajia Mu1,2,3, Jialan Xie1,2,3

  • 1School of Electronic and Information Engineering, Southwest University, Chongqing, China.

Frontiers in Human Neuroscience
|April 15, 2024

View abstract on PubMed

Summary
This summary is machine-generated.

This study introduces a novel electroencephalogram (EEG) model for accurate music emotion recognition. The CNN-SA-BiLSTM model achieves high classification accuracy, offering a promising framework for brain-computer interfaces.

Keywords:
BiLSTMCNNEEGmusic emotion recognitionself-attention

More Related Videos

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.7K
Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
08:22

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

Published on: April 26, 2024

1.8K

Related Experiment Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.7K
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.7K
Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
08:22

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

Published on: April 26, 2024

1.8K

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Music Psychology

Background:

  • Music powerfully evokes emotions, but subjective interpretation complicates emotion identification.
  • Accurate music emotion recognition is crucial for identifying emotional disturbances.

Purpose of the Study:

  • To develop an electroencephalogram (EEG)-based model for objective music emotion recognition.
  • To enhance emotion recognition by analyzing temporal EEG features and self-attention mechanisms.

Main Methods:

  • Created an EEG dataset using four music types: fear, happiness, calm, and sadness.
  • Extracted differential entropy features and employed a CNN-SA-BiLSTM model for temporal feature extraction.
  • Utilized a self-attention mechanism to improve recognition performance and validated through ablation studies.

Main Results:

  • Achieved classification accuracies of 93.45% for valence and 96.36% for arousal.
  • Demonstrated model generalization and reliability on the public DEAP EEG dataset.
  • Confirmed the impact of different EEG bands on music emotion recognition, aligning with neuroscience findings.

Conclusions:

  • The developed CNN-SA-BiLSTM model offers superior music emotion classification performance.
  • This framework shows significant potential for future brain-computer interface-based emotion recognition systems.