LSTM multichannel neural networks in mental task classification

Purpose The purpose of this paper is to apply recurrent neural networks (RNNs) and more specifically long-short term memory (LSTM)-based ones for mental task classification in terms of BCI systems. The authors have introduced novel LSTM-based multichannel architecture model which proved to be highly promising in other fields, yet was not used for mental tasks classification. Design/methodology/approach Validity of the multichannel LSTM-based solution was confronted with the results achieved by a non-multichannel state-of-the-art solutions on a well-recognized data set. Findings The results demonstrated evident advantage of the introduced method. The best of the provided variants outperformed most of the RNNs approaches and was comparable with the best state-of-the-art methods. Practical implications The approach presented in the manuscript enables more detailed investigation of the electroencephalography analysis methods, invaluable for BCI mental tasks classification. Originality/value The new approach to mental task classification, exploiting LSTM-based RNNs with multichannel architecture, operating on spatial features retrieving filters, has been adapted to mental tasks with noticeable results. To the best of the authors’ knowledge, such an approach was not present in the literature before.

Multi-Channel Convolutional Neural Networks Architecture Feeding for Effective EEG Mental Tasks Classification

Mental tasks classification is increasingly recognized as a major challenge in the field of EEG signal processing and analysis. State-of-the-art approaches face the issue of spatially unstable structure of highly noised EEG signals. To address this problem, this paper presents a multi-channel convolutional neural network architecture with adaptively optimized parameters. Our solution outperforms alternative methods in terms of classification accuracy of mental tasks (imagination of hand movements and speech sounds generation) while providing high generalization capability (∼5%). Classification efficiency was obtained by using a frequency-domain multi-channel neural network feeding scheme by EEG signal frequency sub-bands analysis and architecture supporting feature mapping with two subsequent convolutional layers terminated with a fully connected layer. For dataset V from BCI Competition III, the method achieved an average classification accuracy level of nearly 70%, outperforming alternative methods. The solution presented applies a frequency domain for input data processed by a multi-channel architecture that isolates frequency sub-bands in time windows, which enables multi-class signal classification that is highly generalizable and more accurate (∼1.2%) than the existing solutions. Such an approach, combined with an appropriate learning strategy and parameters optimization, adapted to signal characteristics, outperforms reference single- or multi-channel networks, such as AlexNet, VGG-16 and Cecotti’s multi-channel NN. With the classification accuracy improvement of 1.2%, our solution is a clear advance as compared to the top three state-of-the-art methods, which achieved the result of no more than 0.3%.