Decoding a hand Grasped Movement using electroencephalography EEG

Abstract

The central objective of this thesis is to investigate the EEG dynamics associated with hand-grasped movements, utilizing a standardized protocol to gain insights into the neural mechanisms underlying movement intention and execution. The study aims to decode slow cortical potential patterns, quantify changes in oscillatory rhythms, and to identify changes in movement direction while also evaluating the efficiency of the dataset for Brain-Computer Interface (BCI) application through machine learning algorithms. Recent advances in neuro-prosthetics indicate potential approaches for enhancing the standard of living for persons who experience motor impairments. These neuroprosthetic gadgets controlled by thought via Brain-Computer Interfaces (Wolpaw and McFarland, 1994; McFarland and Wolpaw, 2008) will be extremely beneficial for Activities of Daily Living (ADL). Decoding brain activity for such ADL activities and its relevance in non-invasive BCIs have recently been widely investigated for rehabilitation and understanding dysfunctions. Neurophysiology signals such as Electroencephalography (EEG), Local Field Potentials (LFP) and functional Magnetic Resonance Imaging (fMRI) have aided in the prediction/identification and treatment of many neurological conditions. EEG has become a popular choice for non-invasive BCIs considering the signal quality, reliability, mobility, and lower cost with high temporal resolution. EEG also has played a significant role in studying neural oscillations related to sensation, cognitive and motor functions. One of the simple daily activities in all humans is hand-grasped movement. Understanding the functionality of human hand movement (Liu et al., 2021) is vital in rehabilitation, prosthetics, and robotics. Some of the major issues like neuronal activity of the grasping process (Sereno and Maunsell, 1998; Castiello, 2005), cortical depictions of hand movement-related muscles (Schieber and Hibbard, 1993), and an accurate kinematic model of a human hand (Stillfried and van der Smagt,2010.