miMamba: EEG-Based Emotion Recognition With Multi-Scale Inverted Mamba Models
- 10 July 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 16 (4) , 3266-3278
Abstract
EEG-based emotion recognition holds significant potential in the field of brain-computer interfaces. A key challenge is extracting discriminative spatiotemporal features from electroencephalogram (EEG) signals. Existing studies often rely on domain-specific time-frequency features and analyze temporal dependencies and spatial characteristics separately, neglecting the local-global relationships and the interaction in spatiotemporal dynamics. To address this, we propose a novel network called Multi-scale Inverted Mamba (miMamba), which consists of Multi-Scale Temporal Blocks (MSTB) and Temporal-Spatial Fusion Blocks (TSFB). Specifically, MSTBs are designed to capture both local details and global temporal dependencies across different scale subsequences. The TSFBs, implemented with an inverted Mamba structure, focus on the interaction between dynamic temporal dependencies and spatial characteristics. The primary advantage of miMamba lies in its ability to leverage transformed multi-scale EEG sequences, exploiting the interaction between temporal and spatial features without the need for domain-specific time-frequency feature extraction. Experiments show that using only four EEG channels, miMamba achieves remarkable average recognition accuracies for Valence and Arousal classification: 94.86% on the DEAP dataset, 94.94% on the DREAMER dataset, and 91.36% on the SEED dataset. These results underscore the model's superior performance in multidimensional emotion recognition tasks and its potential for practical applications in resource-constrained affective computing scenarios.Keywords
All Related Versions
Funding Information
- Shenzhen Technology University
- Binghamton University
- National Natural Science Foundation of China (62176165)
- Stable Support Projects for Shenzhen Higher Education Institutions (20220718110918001)
- Basic and Applied Basic Research Project of Guangdong Province (2022B1515130009)
- Special subject on Agriculture and Social Development, Key Research and Development Plan in Guangzhou (2023B03J0172)
This publication has 48 references indexed in Scilit:
- Multi-view domain-adaptive representation learning for EEG-based emotion recognitionInformation Fusion, 2023
- EESCN: A novel spiking neural network method for EEG-based emotion recognitionComputer Methods and Programs in Biomedicine, 2023
- Emotion recognition in EEG signals using deep learning methods: A reviewComputers in Biology and Medicine, 2023
- EEG emotion recognition using attention-based convolutional transformer neural networkBiomedical Signal Processing and Control, 2023
- EEG emotion recognition using improved graph neural network with channel selectionComputer Methods and Programs in Biomedicine, 2023
- Multi-channel EEG-based emotion recognition in the presence of noisy labelsScience China Information Sciences, 2022
- Subject independent emotion recognition using EEG signals employing attention driven neural networksBiomedical Signal Processing and Control, 2022
- Emotion recognition based on convolutional neural networks and heterogeneous bio-signal data sourcesInformation Fusion, 2022
- EEG-based emotion recognition using an end-to-end regional-asymmetric convolutional neural networkKnowledge-Based Systems, 2020
- Exploring temporal representations by leveraging attention-based bidirectional LSTM-RNNs for multi-modal emotion recognitionInformation Processing & Management, 2020