Neural Activities Classification of Human Inhibitory Control Using Hierarchical Model

Area of Science:

• Neuroscience
• Cognitive Science
• Biomedical Engineering

Background:

• Human inhibitory control is crucial for daily activities and is linked to the P300 neural marker.
• The P300 wave is a potential indicator for Attention Deficit Hyperactivity Disorder (ADHD) and a stop command in Brain-Computer Interfaces (BCI).
• Electroencephalography (EEG) can detect brain dynamics, including P300 waves in specific brain regions associated with response inhibition.

Purpose of the Study:

• To develop a hierarchical classification model for identifying neural activities related to human inhibition.
• To investigate the efficacy of the phase-locking value (PLV) method in selecting relevant brain regions for inhibition classification.
• To classify successful versus failed inhibitory responses using EEG data.

Main Methods:

• Utilized electroencephalography (EEG) to record brain activity during inhibitory tasks.
• Employed the phase-locking value (PLV) method to identify coupled brain regions associated with response inhibition.
• Developed a hierarchical classification model incorporating pattern recognition algorithms, specifically quadratic discriminant analysis (QDA).

Main Results:

• The PLV method effectively selected coupled brain regions crucial for inhibition detection.
• Quadratic Discriminant Analysis (QDA) achieved an average classification accuracy of 94.44% in distinguishing successful from failed inhibitions.
• The study successfully classified neural activities underlying human inhibition.

Conclusions:

• Neural activities associated with human inhibition, particularly the P300 wave, can be reliably detected and classified using EEG.
• These findings support the use of neural inhibition markers as stop commands in BCI technologies.
• The study highlights the potential of EEG-based analysis for identifying ADHD symptoms in clinical research.