A hybrid EEG classification model using layered cascade deep learning architecture.
Med Biol Eng Comput
; 62(7): 2213-2229, 2024 Jul.
Article
en En
| MEDLINE
| ID: mdl-38507121
ABSTRACT
The problem of multi-class classification is always a challenge in the field of EEG (electroencephalogram)-based seizure detection. The traditional studies focus on computing or learning a set of features from EEG to distinguish between different patterns. However, the extraction of characteristic information becomes increasingly difficult as the number of EEG types increases. To address this issue, a creative EEG classification technique is proposed by employing a principal component analysis network (PCANet) coupled with phase space reconstruction (PSR) and power spectrum density (PSD). We have introduced the PSR and PSD to prepare the inputs, where dynamic and frequency information are exposed from deep within PCANet. It is remarkable that a layered cascade strategy is designed to make a powerful deep learner according to the rule of one network vs one task (OVO). The proposed method has achieved greater effects than the individual models and shown superior performance in comparison with state-of-the-art algorithms, which present 98.0% of sensitivity, 99.90% of specificity, and 99.07% of accuracy. Our ensemble PCANet model works in an assembly line-like manner, obviating the need for hand-craft features. Results demonstrate that the proposed scheme can greatly enhances the accuracy and robustness of seizure detection from EEG signals.
Palabras clave
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Asunto principal:
Convulsiones
/
Algoritmos
/
Procesamiento de Señales Asistido por Computador
/
Análisis de Componente Principal
/
Electroencefalografía
/
Aprendizaje Profundo
Límite:
Humans
Idioma:
En
Revista:
Med Biol Eng Comput
Año:
2024
Tipo del documento:
Article
País de afiliación:
China
Pais de publicación:
Estados Unidos