Advancing biomedical engineering: Leveraging Hjorth features for electroencephalography signal analysis

Area of Science:

• Biomedical Engineering
• Neuroscience
• Machine Learning

Background:

• Electroencephalography (EEG) signal analysis is crucial for understanding neural functions.
• Biomedical engineering leverages advanced signal processing for medical innovation.

Purpose of the Study:

• To explore the potential of EEG signals from the MILimbEEG dataset for machine learning-based task recognition and diagnosis.
• To apply Hjorth Parameters for advanced feature extraction from EEG data.

Main Methods:

• Acquisition of EEG signals from electrodes 1 to 16 in the time-domain.
• Feature extraction using Hjorth Parameters: Activity, Mobility, and Complexity.
• Correlation analysis and examination of clustering behaviors within the EEG data.

Main Results:

• Identified emergent patterns within the EEG signals using Hjorth Parameters.
• Demonstrated the potential of extracted features for machine learning applications.
• Highlighted the significance of signal processing in biomedical diagnostics.

Conclusions:

• Hjorth Parameters offer valuable features for EEG signal analysis.
• Integration of these features can improve diagnostic precision and task recognition in biomedical engineering.
• This research supports the advancement of efficient and accurate biomedical diagnostics through signal processing.