Abstract
Biomedical engineering stands at the forefront of medical innovation, with electroencephalography (EEG) signal analysis providing critical insights into neural functions. This paper delves into the utilization of EEG signals within the MILimbEEG dataset to explore their potential for machine learning-based task recognition and diagnosis. Capturing the brain’s electrical activity through electrodes 1 to 16, the signals are recorded in the time-domain in microvolts. An advanced feature extraction methodology harnessing Hjorth Parameters—namely Activity, Mobility, and Complexity—is employed to analyze the acquired signals. Through correlation analysis and examination of clustering behaviors, the study presents a comprehensive discussion on the emergent patterns within the data. The findings underscore the potential of integrating these features into machine learning algorithms for enhanced diagnostic precision and task recognition in biomedical applications. This exploration paves the way for future research where such signal processing techniques could revolutionize the efficiency and accuracy of biomedical engineering diagnostics.