EEG-Based Motor Imagery Analysis: Primary and Secondary Band Frequencies Perspectives

Abstract

Motor imagery (MI) is one of the most widely used paradigms in brain-computer interface (BCI) systems based on electroencephalography (EEG), enabling communication and control through imagined movements. Based on several studies, conventional MI primary is based on alpha, beta, and gamma frequency bands. However, using only these three frequency bands does not fully capture the level of user concentration, which can be enhanced by incorporating two additional parameters: attention and meditation. These parameter can influence the quality of the MI signal but remain underexplored in previous studies. This study investigates the performance of MI classification in both the primary (alpha, beta, gamma) and additional secondary cognitive variables (attention and meditation). By integrating conventional frequency domain features with cognitive state measures, we provide a dual-perspective analysis of EEG-based MI. From the evaluation results using data collected from 5 healthy subjects performing motor imagery tasks of knee movement, knee-ankle movement, ankle movement, and relaxed conditions, our proposed method achieved an Average accuracy of 66,51% with a maximum precision of approximately 100%.

Access to Document

Other files and links

• Link to publication in Scopus

Fingerprint