Search research articles

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

Home
Emotion Recognition Using Spectral-spatial Attention Multi-temporal Scale Network: Eeg Study.

Home
Emotion Recognition Using Spectral-spatial Attention Multi-temporal Scale Network: Eeg Study.

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

Preparation of apigenin-loaded microspheres and their effects against Porphyromonas gingivalis.

Odontology·2026

Same author

A cross-modal framework for evaluating the mental health benefits of urban and natural landscapes in sustainable cities: an empirical study based on undergraduate students.

BMC psychology·2026

Same author

Pediococcus acidilactici PA53 Improves Emotional Well-Being and Gut Health While Modulating Microbiota Composition in Older Adults: A Randomized, Double-Blind, Placebo-Controlled Trial.

The Journal of nutrition·2026

Same author

Long-term economic value analysis of reducing postoperative air leak following lung resection.

Journal of thoracic disease·2026

Same author

Clinical practice guidelines for prognosis and follow-up of early-stage breast cancer patients: Chinese Society of Breast Surgery (CSBrS) practice guidelines (2026 edition) Chinese Society of Breast Surgery, Chinese Society of Surgery, Chinese Medical Association.

Translational breast cancer research : a journal focusing on translational research in breast cancer·2026

Same author

Propofol Exerts Cerebroprotective Effects Against Cerebral Infarction by Up-Regulating TRIM67 to Mediate VDAC1 Ubiquitination and Degradation.

Chemical biology & drug design·2026

Same journal

A quantitative and precision‑oriented neuronal reconstruction approach based on data grading.

Brain informatics·2026

Same journal

Evaluating multi-level membership inference risk in federated EEG learning.

Brain informatics·2026

Same journal

Single-cell reconstruction of whole-brain efferent projections from mouse ventral posteromedial thalamus.

Brain informatics·2026

Same journal

RDoC-informed explainable AI as a paradigm for multilevel Alzheimer's disease diagnosis and progression prediction: a systematic review.

Brain informatics·2026

Same journal

Synergistic and redundant information dynamics exhibit dissociable alterations across schizophrenia and neurodevelopmental conditions.

Brain informatics·2026

Same journal

A feasibility study on inferring connectivity changes in frontal lobes of MDD patients via spectral DCM.

Brain informatics·2026

See all related articles

Related Experiment Video

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

Emotion recognition using spectral-spatial attention multi-temporal scale network: EEG study.

Zhe Tao¹, Guanghao Huang², Leilei Ma³

¹Institute for Future, School of Automation, Qingdao University, Qingdao, 266071, China.

Brain Informatics

|June 3, 2026

View abstract on PubMed

Summary

This summary is machine-generated.

This study introduces a novel Spectral-Spatial Attention Multi-Temporal Scale Network (SSA-MTSNet) for accurate emotion recognition from electroencephalography (EEG) signals. The SSA-MTSNet effectively captures complex EEG dynamics, achieving high classification accuracies.

Keywords:

Attention mechanism Electroencephalogram (EEG)Emotion recognition Multi-temporal scale Spatio-temporal modeling

Related Experiment Videos

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

Area of Science:

Neuroscience
Artificial Intelligence
Signal Processing

Background:

Electroencephalography (EEG) is a cost-effective, non-invasive method for emotion classification.
Existing EEG-based emotion recognition methods face challenges in capturing spatial-spectral dependencies and multi-temporal dynamics.

Purpose of the Study:

To propose a novel Spectral-Spatial Attention Multi-Temporal Scale Network (SSA-MTSNet) for enhanced emotion classification using EEG signals.
To address limitations in capturing spatial-spectral dependencies and multi-temporal dynamics in EEG data.

Main Methods:

Developed the SSA-MTSNet, integrating spectral-spatial attention, multi-temporal scale spatio-temporal convolution, and Long Short-Term Memory (LSTM) modules.
Preserved electrode topology while enhancing signal frequencies and inter-region brain interactions using attention mechanisms.
Captured short- and long-term emotional cues via multi-temporal scale convolution and LSTM for sequence modeling.

Main Results:

Achieved high average accuracies: 98.34% on SEED and 91.79% on SEED-IV datasets.
Demonstrated strong performance on the DEAP dataset for valence (95.13%) and arousal (95.30%) classification.
The model showed competitive performance across diverse experimental paradigms and emotion labeling strategies.

Conclusions:

The SSA-MTSNet effectively models complementary spectral, spatial, and temporal EEG information for robust emotion recognition.
The proposed network offers a significant advancement in EEG-based emotion classification accuracy and reliability.
This approach holds promise for various applications requiring accurate and efficient emotion detection.