A Systematic Deep Learning Model Selection for P300-Based Brain–Computer Interfaces
研究了系统化模型选择结合主流深度学习架构来构建P300事件相关电位解码分类器的可行性，在4个数据集上测试了232个CNN、36个LSTM和320个混合CNN-LSTM模型，发现所构建模型可超越当前依赖领域知识的最优架构。
Predicting attention-modulated brain responses is a major area of investigation in brain–computer interface (BCI) research that aims to translate neural activities into useful control and communication commands. Such studies involve collecting electroencephalographic (EEG) data from subjects to train classifiers for decoding users’ mental states. However, various sources of inter or intrasubject variabilities in brain signals render training classifiers in BCI systems challenging. From a machine learning perspective, this model training generally follows a common methodology: 1) apply some type of feature extraction, which can be time-consuming and may require domain knowledge and 2) train a classifier using extracted features. The advent of deep learning technologies has offered unprecedented opportunities to not only construct remarkably accurate classifiers but also to integrate the feature extraction stage into the classifier construction. Although integrating feature extraction, which is generally domain-dependent, into the classifier construction is a considerable advantage of deep learning models, the process of architecture selection for BCIs generally depends on domain knowledge. In this study, we examine the feasibility of conducting a systematic model selection combined with mainstream deep learning architectures to construct accurate classifiers for decoding P300 event-related potentials. In particular, we present the results of 232 convolutional neural networks (CNNs) (4 datasets <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\times58$ </tex-math></inline-formula> structures), 36 long short-term memory cells (LSTMs) (4 datasets <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\times9$ </tex-math></inline-formula> structures), and 320 hybrid CNN-LSTM models (4 datasets <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\times80$ </tex-math></inline-formula> structures) of varying complexity. Our empirical results show that in the classification of P300 waveforms, the constructed predictive models can outperform the current state-of-the-art deep learning architectures, which are partially or entirely inspired by domain knowledge. The source codes and constructed models are available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/berdakh/P3Net</uri> .