Exploring differences for motor imagery using Teager energy operator-based EEG microstate analyses.

Area of Science:

• Neuroscience
• Biomedical Engineering
• Signal Processing

Background:

• Motor imagery tasks are crucial for brain-computer interfaces.
• Existing methods for differentiating motor imagery tasks have limitations.
• Electroencephalogram (EEG) microstate analysis offers potential for capturing brain dynamics.

Purpose of the Study:

• To develop and validate a novel method for differentiating two motor imagery tasks.
• To investigate the efficacy of EEG microstate parameters and Teager energy operator for task classification.
• To compare the performance of the proposed method against other classification techniques.

Main Methods:

• A novel method combining electroencephalogram microstate analysis and the Teager energy operator was developed.
• Microstate parameters, including occurrence, duration, coverage, and mean spatial correlation (Mspatcorr), were extracted.
• A Support Vector Machine (SVM) classifier was employed to differentiate between two motor imagery tasks using the extracted parameters.

Main Results:

• Significant differences (P < 0.05) were observed in microstate parameters between the two motor imagery tasks using a paired t-test.
• The proposed method achieved a high classification accuracy of 93.93% for distinguishing between the tasks.
• The SVM classifier utilizing microstate parameters demonstrated superior performance compared to alternative methods.

Conclusions:

• The novel method effectively captures differences between motor imagery tasks using EEG microstate parameters.
• The integration of EEG microstate analysis and Teager energy operator shows promise for brain-computer interface applications.
• The proposed approach offers a robust and accurate method for classifying motor imagery tasks.