A convolutional neural network for steady state visual evoked potential classification under ambulatory environment

Abstract

The robust analysis of neural signals is a challenging problem. Here, we contribute a convolutional neural network (CNN) for the robust classification of a steady-state visual evoked potentials (SSVEPs) paradigm. We measure electroencephalogram (EEG)-based SSVEPs for a brain-controlled exoskeleton under ambulatory conditions in which numerous artifacts may deteriorate decoding. The proposed CNN is shown to achieve reliable performance under these challenging conditions. To validate the proposed method, we have acquired an SSVEP dataset under two conditions: 1) a static environment, in a standing position while fixated into a lower-limb exoskeleton and 2) an ambulatory environment, walking along a test course wearing the exoskeleton (here, artifacts are most challenging). The proposed CNN is compared to a standard neural network and other state-of-the-art methods for SSVEP decoding (i.e., a canonical correlation analysis (CCA)-based classifier, a multivariate synchronization index (MSI), a CCA combined with k-nearest neighbors (CCA-KNN) classifier) in an offline analysis. We found highly encouraging SSVEP decoding results for the CNN architecture, surpassing those of other methods with classification rates of 99.28% and 94.03% in the static and ambulatory conditions, respectively. A subsequent analysis inspects the representation found by the CNN at each layer and can thus contribute to a better understanding of the CNN’s robust, accurate decoding abilities.

EEG-based brain–computer interfaces

“…A variety of spatial and temporal filtering methods have been applied to feature extraction. These include interest in currently popular algorithms such as convolutional neural networks [37]. Many recent studies have used data-driven spatial filtering methods such as common spatial patterns [38] and source imaging methods [39].…”

Decoding Visual Responses based on Deep Neural Networks with Ear-EEG Signals

“…Since these artifacts are much larger in amplitude than the brain signal that contains the user's intent, it is difficult to catch properly the meaning of intention. Therefore, decoding human intention in the ambulatory environment is tried these days [4][5][6][7] using movement artifact removal methods [8,9] and deep neural networks [7,[10][11][12][13][14][15][16][17] to robust the artifacts and increase the performance.…”

“…BCI paradigms are mainly developed to motor imagery [22][23][24][25][26][27], ERP [28][29][30][31][32], and steady-state visual evoked potential (SSVEP) [6,7,[32][33][34]. ERP and SSVEP are visual responses and are widely used to recognize human intention because their patterns in EEG signals are relatively huge and they showed reliable performance when it comes to accuracy and response time with only a few EEG channels comparing to other BCI paradigms.…”

Neural Oscillations for Encoding and Decoding Declarative Memory using EEG Signals

“…[12][13][14][15][16][17], however the use of fMRI can be somehow inconvenient to use in daily life applications due to its size and its cost. On the other hand, EEG is a portable and inexpensive device to acquire brain signals, which make it very suitable for use in real-life [18][19][20]. Previous studies related to understand the memory process also involve the use of these devices [21][22][23].…”