RT info:eu-repo/semantics/article
T1 EEG-Inception: A Novel Deep Convolutional Neural Network for Assistive ERP-Based Brain-Computer Interfaces
A1 Santamaría Vázquez, Eduardo
A1 Martínez Cagigal, Víctor
A1 Vaquerizo Villar, Fernando
A1 Hornero, Roberto
K1 Brain-computer interfaces
K1 Event-related potentials
K1 P300
K1 Deep learning
K1 Convolutional Neural Networks
K1 Inception
K1 Transfer learning
AB In recent years, deep-learning models gained attention for electroencephalography (EEG) classification tasks due to their excellent performance and ability to extract complex features from raw data. In particular, convolutional neural networks (CNN) showed adequate results in brain-computer interfaces (BCI) based on different control signals, including event-related potentials (ERP). In this study, we propose a novel CNN, called EEG-Inception, that improves the accuracy and calibration time of assistive ERP-based BCIs. To the best of our knowledge, EEG-Inception is the first model to integrate Inception modules for ERP detection, which combined efficiently with other structures in a light architecture, improved the performance of our approach. The model was validated in a population of 73 subjects, of which 31 present motor disabilities. Results show that EEG-Inception outperforms 5 previous approaches, yielding significant improvements for command decoding accuracy up to 16.0%, 10.7%, 7.2%, 5.7% and 5.1% in comparison to rLDA, xDAWN + Riemannian geometry, CNN-BLSTM, DeepConvNet and EEGNet, respectively. Moreover, EEG-Inception requires very few calibration trials to achieve state-of-the-art performances taking advantage of a novel training strategy that combines cross-subject transfer learning and fine-tuning to increase the feasibility of this approach for practical use in assistive applications.
PB IEEE
YR 2020
FD 2020-12-30
LK https://uvadoc.uva.es/handle/10324/65991
UL https://uvadoc.uva.es/handle/10324/65991
LA spa
NO IEEE Transactions on Neural Systems and Rehabilitation Engineering, Diciembre, 2020, vol. 28 (12), pp. 2773 - 2782.
DS UVaDOC
RD 17-jul-2024