AUTHOR=Juan Javier V. , Martínez Rubén , Iáñez Eduardo , Ortiz Mario , Tornero Jesús , Azorín José M. TITLE=Exploring EEG-based motor imagery decoding: a dual approach using spatial features and spectro-spatial Deep Learning model IFNet JOURNAL=Frontiers in Neuroinformatics VOLUME=18 YEAR=2024 URL=https://www.frontiersin.org/journals/neuroinformatics/articles/10.3389/fninf.2024.1345425 DOI=10.3389/fninf.2024.1345425 ISSN=1662-5196 ABSTRACT=Introduction

In recent years, the decoding of motor imagery (MI) from electroencephalography (EEG) signals has become a focus of research for brain-machine interfaces (BMIs) and neurorehabilitation. However, EEG signals present challenges due to their non-stationarity and the substantial presence of noise commonly found in recordings, making it difficult to design highly effective decoding algorithms. These algorithms are vital for controlling devices in neurorehabilitation tasks, as they activate the patient's motor cortex and contribute to their recovery.

Methods

This study proposes a novel approach for decoding MI during pedalling tasks using EEG signals. A widespread approach is based on feature extraction using Common Spatial Patterns (CSP) followed by a linear discriminant analysis (LDA) as a classifier. The first approach covered in this work aims to investigate the efficacy of a task-discriminative feature extraction method based on CSP filter and LDA classifier. Additionally, the second alternative hypothesis explores the potential of a spectro-spatial Convolutional Neural Network (CNN) to further enhance the performance of the first approach. The proposed CNN architecture combines a preprocessing pipeline based on filter banks in the frequency domain with a convolutional neural network for spectro-temporal and spectro-spatial feature extraction.

Results and discussion

To evaluate the approaches and their advantages and disadvantages, EEG data has been recorded from several able-bodied users while pedalling in a cycle ergometer in order to train motor imagery decoding models. The results show levels of accuracy up to 80% in some cases. The CNN approach shows greater accuracy despite higher instability.