Imagined Speech State Classification for Robust Brain-Computer Interface

TL;DR

This paper compares traditional machine learning and deep learning models for imagined speech detection using EEG data, finding deep learning models, especially EEGNet, significantly outperform traditional methods in accuracy and reliability.

Contribution

It demonstrates the superiority of deep learning models over traditional classifiers for imagined speech EEG classification, advancing BCI system development.

Findings

Deep learning models achieved higher accuracy than traditional classifiers.

EEGNet reached an accuracy of 0.7080 and F1 score of 0.6718.

Traditional classifiers showed limited feature extraction capabilities.

Abstract

This study examines the effectiveness of traditional machine learning classifiers versus deep learning models for detecting the imagined speech using electroencephalogram data. Specifically, we evaluated conventional machine learning techniques such as CSP-SVM and LDA-SVM classifiers alongside deep learning architectures such as EEGNet, ShallowConvNet, and DeepConvNet. Machine learning classifiers exhibited significantly lower precision and recall, indicating limited feature extraction capabilities and poor generalization between imagined speech and idle states. In contrast, deep learning models, particularly EEGNet, achieved the highest accuracy of 0.7080 and an F1 score of 0.6718, demonstrating their enhanced ability in automatic feature extraction and representation learning, essential for capturing complex neurophysiological patterns. These findings highlight the limitations of conventional machine learning approaches in brain-computer interface (BCI) applications and advocate for adopting deep learning methodologies to achieve more precise and reliable classification of detecting imagined speech. This foundational research contributes to the development of imagined speech-based BCI systems.