Classification of motor imagery EEG using deep learning increases performance in inefficient BCI users

Abstract

Motor Imagery Brain-Computer Interfaces (MI-BCIs) are AI-driven systems that capture brain activity patterns associated with mental imagination of movement and convert them into commands for external devices. Traditionally, MI-BCIs operate on Machine Learning (ML) algorithms, which require extensive signal processing and feature engineering to extract changes in sensorimotor rhythms (SMR). In recent years, Deep Learning (DL) models have gained popularity for EEG classification as they provide a solution for automatic extraction of spatio-temporal features in the signals. However, past BCI studies that employed DL models, only attempted them with a small group of participants, without investigating the effectiveness of this approach for different user groups such as inefficient users. BCI inefficiency is a known and unsolved problem within BCI literature, generally defined as the inability of the user to produce the desired SMR patterns for the BCI classifier. In this study, we evaluated the effectiveness of DL models in capturing MI features particularly in the inefficient users. EEG signals from 54 subjects who performed a MI task of left- or right-hand grasp were recorded to compare the performance of two classification approaches; a ML approach vs. a DL approach. In the ML approach, Common Spatial Patterns (CSP) was used for feature extraction and then Linear Discriminant Analysis (LDA) model was employed for binary classification of the MI task. In the DL approach, a Convolutional Neural Network (CNN) model was constructed on the raw EEG signals. Additionally, subjects were divided into high vs. low performers based on their online BCI accuracy and the difference between the two classifiers’ performance was compared between groups. Our results showed that the CNN model improved the classification accuracy for all subjects within the range of 2.37 to 28.28%, but more importantly, this improvement was significantly larger for low performers. Our findings show promise for employment of DL models on raw EEG signals in future MI-BCI systems, particularly for BCI inefficient users who are unable to produce desired sensorimotor patterns for conventional ML approaches.

Review of public motor imagery and execution datasets in brain-computer interfaces

“…The SSVEP and P300 paradigm parameters have been considered to have a significant 10.3389/fnhum.2023.1134869 effect on performance and much research has been conducted on them (Gonsalvez and Polich, 2002;Zhu et al, 2010;Han et al, 2022). However, in MI BCI, a similar cue-based experiment has been used continuously in the past (Pfurtscheller and Neuper, 1997) and in recent studies (Tibrewal et al, 2022), although MI parameters may also influence signal quality or BCI performance. Indeed, few studies have attempted to investigate the MI paradigm's effect.…”

KCS-FCnet: Kernel Cross-Spectral Functional Connectivity Network for EEG-Based Motor Imagery Classification

“…Additionally, further analysis of the inter-class variability will be conducted, specifically focusing on how each subject performs within different runs of the experiment. We aim to understand if subjects learn to execute motor imagery tasks as they progress through the runs and whether this results in better performance in subsequent runs [ 52 , 53 ]. Furthermore, we plan to analyze subject-specific filters, specifically looking at the activity of the filter waves concerning brain frequency bands such as Theta, Alpha, Beta, and Gamma.…”

Intracortical Hindlimb Brain–Computer Interface Systems: A Systematic Review

“…Moreover, in [47] and [52], classifying pedal press duration was done using ISI-based and PSTH-based classifiers respectively and had high and relatively similar true positive rates. However, although promising results have been obtained using deep neural networks in discrete BCIs [117]- [119], none of the included studies used these methods for hindlimb high-level movement parameters.…”