CNN-based framework using spatial dropping for enhanced interpretation of neural activity in motor imagery classification

Abstract

Interpretation of brain activity responses using motor imagery (MI) paradigms is vital for medical diagnosis and monitoring. Assessed by machine learning techniques, identification of imagined actions is hindered by substantial intra-and inter-subject variability. Here, we develop an architecture of Convolutional Neural Networks (CNN) with an enhanced interpretation of the spatial brain neural patterns that mainly contribute to the classification of MI tasks. Two methods of 2D-feature extraction from EEG data are contrasted: Power Spectral Density and Continuous Wavelet Transform. For preserving the spatial interpretation of extracting EEG patterns, we project the multi-channel data using a topographic interpolation. Besides, we include a spatial dropping algorithm to remove the learned weights that reflect the localities not engaged with the elicited brain response. We evaluate two labeled scenarios of MI tasks: bi-class and three-class. Obtained results in an MI database show that the thresholding strategy combined with Continuous Wavelet Transform improves the accuracy and enhances the interpretability of CNN architecture, showing that the highest contribution clusters over the sensorimotor cortex with a differentiated behavior of rhythms µ and β.

Impact of Input Filtering and Architecture Selection Strategies on GRU Runoff Forecasting: A Case Study in the Wei River Basin, Shaanxi, China

“…The designs of the ANNs result in the diversity of their advancements and limitations [30]. For example, the convolutional neural networks have the kernel to recognize the spatial distribution pattern of data; consequently, it has been implemented commonly for imagery classification [31][32][33], however, the existence of pooling layers may cause the loss of abundant information [34]. The recurrent neural network (RNN) is a "loop" structure that has a state to store the information from the previous steps; thus, it can deal with the time-series data that has time dependency.…”

Deep and Wide Transfer Learning with Kernel Matching for Pooling Data from Electroencephalography and Psychological Questionnaires

“…For evaluation in discriminating MI tasks, the proposed transfer learning model is assessed on a trial basis. That is, we extract the feature sets per trial , incorporating a pair of EEG-based feature representation approaches ( ): Continuous Wavelet Transform (CWT) and Common Spatial Patterns (CSP), as recommended for Deep and Wide learning frameworks in [ 36 ].…”

Kernel-Based Phase Transfer Entropy with Enhanced Feature Relevance Analysis for Brain Computer Interfaces

“…Motor imagery (MI) is the process of mentally rehearsing a motor action, such as moving a limb, without actually executing it [43]. The BCI Competition IV database 2a [44] comprises EEG data from 9 healthy subjects recorded during an MI paradigm consisting of four different MI tasks, namely, imagining the movement of the left hand, the right hand, both feet, or the tongue.…”

“…By computing λ θ (x c → x c , f ) for each pairwise combination of channels in X n we obtain a connectivity matrix Λ( f ) ∈ R C×C (when c = c , we set λ θ (x c → x c , f ) = 0). For the MI database, we vary the values of f in the range from 8 Hz to 18 Hz, in 2 Hz steps, since activity in that frequency range has been associated with MI tasks [43]. Then we define two bandwidths of interest ∆ f ∈ {α ∈ [8 − 12], β l ∈ [14 − 18]} Hz.…”