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

PMSN: A Parallel Multi-Compartment Spiking Neuron for Multiscale Temporal Processing.

IEEE transactions on neural networks and learning systems·2026

Same author

Maternal cold exposure improves offspring metabolic health via a milk lithocholic acid-microbiota-Th17 axis.

NPJ biofilms and microbiomes·2026

Same author

Advances in intraoperative margin assessment for solid tumors: Toward a new era of personalized precision surgery.

European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology·2026

Same author

Straw Return and Tillage Regulate Soil N Pool via Modifying Soil Conditions and Bacterial Communities in Coastal Saline-Alkaline Land.

Microorganisms·2026

Same author

Exopolysaccharide-rosmarinic acid complex as a phosphate replacer: dual improvement of oxidative stability and gel properties in myofibrillar proteins.

Food chemistry: X·2026

Same author

Correction: Research on curing reaction kinetics and curing process of hydroxy-terminated polybutadiene (HTPB) propellants.

Scientific reports·2026

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: Feb 24, 2026

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

MSGM: a multi-scale spatiotemporal graph Mamba for EEG emotion recognition.

Hanwen Liu¹, Yifeng Gong¹, Zuwei Yan²

¹The School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen, China.

Frontiers in Neuroscience

|February 23, 2026

Summary

The Multi-Scale Spatiotemporal Graph Mamba (MSGM) enhances electroencephalography (EEG) emotion recognition by modeling brain dynamics efficiently. This novel approach achieves high accuracy and real-time performance for mobile health applications.

Keywords:

Mamba electroencephalogram (EEG)emotion recognition graph neural networks multi-scale

More Related Videos

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

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

Published on: October 24, 2012

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

Published on: July 31, 2016

Related Experiment Videos

Last Updated: Feb 24, 2026

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

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

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

Published on: October 24, 2012

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

Published on: July 31, 2016

Area of Science:

Neuroscience
Computer Science
Artificial Intelligence

Background:

Electroencephalography (EEG) based emotion recognition is crucial for mobile health and affective computing.
Existing methods struggle with the trade-off between complex brain dynamics modeling and computational efficiency for edge deployment.
Current approaches often overlook multi-scale temporal dynamics and hierarchical spatial brain connectivity.

Purpose of the Study:

To introduce the Multi-Scale Spatiotemporal Graph Mamba (MSGM) for efficient and robust EEG-based emotion recognition.
To address limitations in modeling complex spatiotemporal brain activity and computational overhead in existing methods.
To facilitate real-time clinical monitoring and affective interaction through edge-deployable AI.

Main Methods:

Proposed MSGM utilizes multi-window temporal segmentation for relative power spectral density (rPSD) feature extraction.
Employs bimodal global and local graphs refined by multi-depth Graph Convolutional Networks (GCNs) to model hierarchical brain connectivity.
Integrates a single-layer MSST-Mamba module for linear computational complexity and efficient state-space modeling.

Main Results:

MSGM achieved competitive accuracy and F1 scores across SEED, THU-EP, and FACED datasets under subject-independent protocols (e.g., 83.43% accuracy on SEED).
Demonstrated millisecond-level inference (151 ms) on an NVIDIA Jetson Xavier NX edge device, confirming real-time suitability.
Showcased robust generalization and efficiency due to the single MSST-Mamba layer architecture.

Conclusions:

MSGM effectively captures complex spatiotemporal brain dynamics with low computational overhead, suitable for real-time applications.
The framework integrates neuroanatomical priors into state-space modeling for improved accuracy and interpretability.
Future work will focus on multimodal integration and optimizing hierarchical spatial modeling for cross-subject variability.