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

Abstract

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%.

Interactive Timeline Approach for Contextual Spatio-Temporal ECT Data Investigation

“…This approach could be beneficial, especially for further exploration of the unexpected information found by some participants in the data during pulsation analysis, as discussed in Section 6 of this paper. Although EEG interfaces are still not mature enough to be fully effective in professional contexts, they could be used to research neurocognitive workload reduction [ 62 , 63 , 64 ]. Our tests are limited to a laboratory setting, yet there is not much difference between real conditions and our study scenario.…”

A Multichannel Convolutional Neural Network Architecture for the Detection of the State of Mind Using Physiological Signals from Wearable Devices

“…The architecture shows 5 different input channels for ECG, EMG, respiration, BVP, and accelerometer, respectively. The reason for going forward in separating the channels for different biosignals lies with the fact that the initial feature learning using convolutional neural network for a particular biosignal is being kept discrete with respect to other biosignals for preventing the initial information mixing between individuals [24, 25]. Therefore, the features corresponding to each biosignal such as ECG (4 features), EMG (3 features), respiration (3 features), BVP (3 features), and an accelerometer (15 features) have been coupled respectively and passed along the respective channels.…”

Towards Big Data Solutions for Industrial Tomography Data Processing

“…In this sector one of the most important computational tasks is fraud detection, which unlike most statistical data analysis, concerns itself with data in motion, with real time emphasis. Some AI application require enormous collections of data to be stored, prepared and processed by machine learning such as the EEG annotation data [13], industrial emergency states detection [14] [15] or medical augmented reality future diagnosis [16].…”