Your browser doesn't support javascript.
loading
Lightweight attention mechanisms for EEG emotion recognition for brain computer interface.
Gunda, Naresh Kumar; Khalaf, Mohammed I; Bhatnagar, Shaleen; Quraishi, Aadam; Gudala, Leeladhar; Venkata, Ashok Kumar Pamidi; Alghayadh, Faisal Yousef; Alsubai, Shtwai; Bhatnagar, Vaibhav.
Afiliación
  • Gunda NK; Information Technology Management, Campbellsville Univeristy, Campbellsville, KY, United States. Electronic address: ngunda6695@ucumberlands.edu.
  • Khalaf MI; Department of computer science, Al Maarif University College, Al Anbar 31001, Iraq. Electronic address: m.i.khalaf@uoa.edu.iq.
  • Bhatnagar S; Department of Computer Science and Engineering, Manipal Institute of Technology Bengaluru, Manipal Academy of Higher Education, Manipal, India. Electronic address: shaleen.bhatnagar@manipal.edu.
  • Quraishi A; M. D. Research, Interventional Treatment Institute, Al Anbar, TX, United States. Electronic address: aadamquraishi@yahoo.com.
  • Gudala L; Valparaiso University, United States. Electronic address: leeladhargudala9@gmail.com.
  • Venkata AKP; Department of Information Technology, University of the Cumberlands, United States. Electronic address: ashokpamidi@outlook.com.
  • Alghayadh FY; Computer Science and Information Systems Department, College of Applied Sciences, AlMaarefa University, Riyadh, Saudi Arabia. Electronic address: fghayadh@um.edu.sa.
  • Alsubai S; Department of Computer Science, College of Computer Engineering and Sciences in Al-Kharj, Prince Sattam bin Abdulaziz University, P.O. Box 151, Al-Kharj 11942, Saudi Arabia. Electronic address: drShtwaiAlsubai@gmail.com.
  • Bhatnagar V; Department of Computer Applications, Manipal University Jaipur, India. Electronic address: vaibhav.bhatnaga15@gmail.com.
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. NEW

METHODS:

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 95.18 % accuracy on the SEED dataset. COMPARISON WITH EXISTING

METHODS:

Moreover, it reduced the number of parameters by 98 % 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.
Asunto(s)
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

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
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

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