Stacked Autoencoders for the P300 Component Detection

• Published in: Frontiers in neuroscience Vol. 11; p. 302
• Main Authors: Vařeka, Lukáš, Mautner, Pavel
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 30.05.2017; Frontiers Media S.A
• Subjects: Algorithms; Artificial intelligence; Brain research; brain-computer interfaces; Classification; Datasets; Deep learning; Discriminant analysis; EEG; Electroencephalography; Event-related potentials; Interfaces; Machine learning; Neural networks; Neuroscience; P300; Principal components analysis; Signal processing; stacked autoencoders; Wavelet transforms; deep learning; event-related potentials; brain-computer interfaces; machine learning; stacked autoencoders; P300
• ISSN: 1662-453X; 1662-4548; 1662-453X
• DOI: 10.3389/fnins.2017.00302

Novel neural network training methods (commonly referred to as deep learning) have emerged in recent years. Using a combination of unsupervised pre-training and subsequent fine-tuning, deep neural networks have become one of the most reliable classification methods. Since deep neural networks are especially powerful for high-dimensional and non-linear feature vectors, electroencephalography (EEG) and event-related potentials (ERPs) are one of the promising applications. Furthermore, to the authors' best knowledge, there are very few papers that study deep neural networks for EEG/ERP data. The aim of the experiments subsequently presented was to verify if deep learning-based models can also perform well for single trial P300 classification with possible application to P300-based brain-computer interfaces. The P300 data used were recorded in the EEG/ERP laboratory at the Department of Computer Science and Engineering, University of West Bohemia, and are publicly available. Stacked autoencoders (SAEs) were implemented and compared with some of the currently most reliable state-of-the-art methods, such as LDA and multi-layer perceptron (MLP). The parameters of stacked autoencoders were optimized empirically. The layers were inserted one by one and at the end, the last layer was replaced by a supervised softmax classifier. Subsequently, fine-tuning using backpropagation was performed. The architecture of the neural network was 209-130-100-50-20-2. The classifiers were trained on a dataset merged from four subjects and subsequently tested on different 11 subjects without further training. The trained SAE achieved 69.2% accuracy that was higher ( < 0.01) than the accuracy of MLP (64.9%) and LDA (65.9%). The recall of 58.8% was slightly higher when compared with MLP (56.2%) and LDA (58.4%). Therefore, SAEs could be preferable to other state-of-the-art classifiers for high-dimensional event-related potential feature vectors.