Sep 2026· International journal of electrical and computer engineering systems· Vol 17, pp. 599-610· 0 citations
TL;DR
This work presents an attention-enhanced CNN-LSTM model for emotion recognition from EEG in the SEED benchmark dataset (three classes: positive, neutral, negative) and indicates competitive performance and underscores the usefulness of complementary spectral and hemispheric signal fusion before attention-directed spatiotemporal modeling.
Abstract
EEG emotion recognition offers a direct path to the analysis of affective brain states. This work presents an attention-enhanced CNN-LSTM model for emotion recognition from EEG in the SEED benchmark dataset (three classes: positive, neutral, negative). The suggested method combines Power Spectral Density (PSD), Differential Entropy (DE), and hemispheric asymmetry descriptors (ASM, DASM, RASM) into a single input description, which is trained through a hybrid architecture in which a CNN learns the patterns of spatial channels, stacked LSTM layers learn the patterns of temporal dependencies, and a temporal attention block highlights the most informative time segments. The model has an accuracy of 98.63% in 5-fold cross-validation across subjects, with averaged precision, recall, and F1-score exceeding 98.6. Compared with solutions from representative published SEEDs listed in Table 1, these findings indicate competitive performance and underscore the usefulness of complementary spectral and hemispheric signal fusion before attention-directed spatiotemporal modeling.
BACKGROUND
EEG provides direct neural measurements with high temporal resolution for emotion recognition. However, many spectrogram-based approaches process channels independently or integrate channel information only at later stages.
NEW METHOD
We propose a stacked spectrogram representation that vertically concaten...
G. Son· Journal of Neuroscience Meth...· 1 citation
This paper presents an explainable CNN–Transformer framework for subject-independent EEG emotion recognition, where the CNN component learns local temporal and spatial patterns, while the Transformer encoder uses self-attention to model relationships across the learned representation.
Venkatalakshmi M, B. M, Pavithra M et al.· International Research Journ...· 0 citations
It is shown that gated recurrent architectures can provide strong classification performance while maintaining relatively lower architectural complexity than graph- and Transformer-based approaches and highlights the potential of GRU-based models for resource-efficient EEG emotion-recognition systems.
Naveen Saini· International journal of tec...· 0 citations
It is suggested that gated recurrent networks model the temporal structure of EEG signals more effectively than a purely convolutional model, while remaining substantially lighter than the graph-and Transformer-based architectures increasingly reported in this field.
Background: In most existing EEG-based emotion recognition studies, the spatial configuration of electroencephalography (EEG) electrodes is not adequately preserved, and conventional single-scale convolutional neural networks (CNNs) have limited ability to capture both local and global spatial patterns. To address thes...
Xiao-Qin Lian, Ran Liang, Chao Gao et al.· Brain Science· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.