Lightweight attention mechanisms for EEG emotion recognition for brain computer interface.
J Neurosci Methods
; 410: 110223, 2024 Oct.
Article
en En
| MEDLINE
| ID: mdl-39032522
ABSTRACT
BACKGROUND:
In the realm of brain-computer interfaces (BCI), identifying emotions from electroencephalogram (EEG) data is a difficult endeavor because of the volume of data, the intricacy of the signals, and the several channels that make up the signals. NEWMETHODS:
Using dual-stream structure scaling and multiple attention mechanisms (LDMGEEG), a lightweight network is provided to maximize the accuracy and performance of EEG-based emotion identification. Reducing the number of computational parameters while maintaining the current level of classification accuracy is the aim. This network employs a symmetric dual-stream architecture to assess separately time-domain and frequency-domain spatio-temporal maps constructed using differential entropy features of EEG signals as inputs.RESULT:
The experimental results show that after significantly lowering the number of parameters, the model achieved the best possible performance in the field, with a 95.18â¯% accuracy on the SEED dataset. COMPARISON WITH EXISTINGMETHODS:
Moreover, it reduced the number of parameters by 98â¯% when compared to existing models.CONCLUSION:
The proposed method distinct channel-time/frequency-space multiple attention and post-attention methods enhance the model's ability to aggregate features and result in lightweight performance.Palabras clave
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Asunto principal:
Procesamiento de Señales Asistido por Computador
/
Electroencefalografía
/
Emociones
/
Interfaces Cerebro-Computador
Límite:
Humans
Idioma:
En
Revista:
J Neurosci Methods
Año:
2024
Tipo del documento:
Article
Pais de publicación:
Países Bajos