Search research articles

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Regional variations in the diet of the South Polar Skua (Stercorarius maccormicki) in the Ross Sea region, Antarctica.

PloS one·2026

Same author

Calibration-free blood pressure estimation based on a convolutional neural network.

Psychophysiology·2023

Same author

Microplastics in gastrointestinal tracts of gentoo penguin (Pygoscelis papua) chicks on King George Island, Antarctica.

Scientific reports·2023

Same author

Applying Enhanced Real-Time Monitoring and Counting Method for Effective Traffic Management in Tashkent.

Sensors (Basel, Switzerland)·2023

Same author

A Robust End-to-End Deep Learning-Based Approach for Effective and Reliable BTD Using MR Images.

Sensors (Basel, Switzerland)·2022

Same author

Robust Human Activity Recognition by Integrating Image and Accelerometer Sensor Data Using Deep Fusion Network.

Sensors (Basel, Switzerland)·2022

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Nov 28, 2025

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

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

Published on: December 15, 2023

EEG-Based Emotion Classification Using Long Short-Term Memory Network with Attention Mechanism.

Youmin Kim¹, Ahyoung Choi¹

¹Department of Software, Gachon University, Seongnam 13120, Korea.

Sensors (Basel, Switzerland)

|December 1, 2020

Summary

This summary is machine-generated.

This study introduces a novel deep learning approach using long short-term memory networks and attention mechanisms to analyze emotional states from electroencephalogram (EEG) signals over time. The model achieves high accuracy in classifying valence and arousal, advancing emotion recognition research.

Keywords:

EEG deep learning emotion classification long short-term memory

More Related Videos

Brain Imaging Investigation of the Memory-Enhancing Effect of Emotion

Brain Imaging Investigation of the Memory-Enhancing Effect of Emotion

Published on: May 4, 2011

Central and Divided Visual Field Presentation of Emotional Images to Measure Hemispheric Differences in Motivated Attention

Central and Divided Visual Field Presentation of Emotional Images to Measure Hemispheric Differences in Motivated Attention

Published on: November 16, 2017

Related Experiment Videos

Last Updated: Nov 28, 2025

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

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

Published on: December 15, 2023

Brain Imaging Investigation of the Memory-Enhancing Effect of Emotion

Brain Imaging Investigation of the Memory-Enhancing Effect of Emotion

Published on: May 4, 2011

Central and Divided Visual Field Presentation of Emotional Images to Measure Hemispheric Differences in Motivated Attention

Central and Divided Visual Field Presentation of Emotional Images to Measure Hemispheric Differences in Motivated Attention

Published on: November 16, 2017

Area of Science:

Neuroscience
Computer Science
Psychology

Background:

Deep learning algorithms are increasingly used for emotion analysis via physiological signals like electroencephalogram (EEG).
However, sequence modeling that captures temporal dynamics in emotional signals remains underexplored.

Purpose of the Study:

To propose a long short-term memory (LSTM) network integrated with an attention mechanism for analyzing emotional changes over time.
To apply the peak-end rule from psychology to weight emotional states at critical moments within the sequence.

Main Methods:

Utilized 32-channel EEG data from the publicly available DEAP database.
Implemented an LSTM network with an attention mechanism to model temporal dependencies in emotional signals.
Conducted two-level (low/high) and three-level (low/middle/high) classification for valence and arousal.
Performed experiments with four-fold and ten-fold cross-validation, including comparisons with a CNN-LSTM hybrid model.

Main Results:

Achieved high accuracies, reaching up to 90.1% for valence and 87.9% for arousal in two-level classification (4-fold CV).
Attained accuracies of 83.5% for valence and 82.6% for arousal in three-level classification (4-fold CV).
Further improved performance with 10-fold cross-validation, reaching 91.8% for valence and 91.6% for arousal.

Conclusions:

The proposed LSTM network with an attention mechanism effectively models temporal dynamics for improved emotion recognition from EEG.
The integration of psychological principles, like the peak-end rule, enhances the model's ability to capture significant emotional shifts.
The findings demonstrate a promising approach for advanced, time-aware emotion analysis using deep learning and physiological signals.