Macroscopic EEG Reveals Discriminative Low-Frequency Oscillations in Plan-to-Grasp Visuomotor Tasks

2025-10-21

AI Summary

Current understanding of the macro-scale neural mechanisms underlying non-invasive EEG-based discrimination among grasp types—precision grip, power grip, and no-grasp—during natural visuomotor tasks remains incomplete. Method: We employed a filter bank common spatial pattern (FBCSP) framework to extract band-specific features from 0.5–8 Hz low-frequency oscillations—identified herein as a sustained neural signature spanning both grasp planning and execution—and classified grasp intentions using support vector machines (SVM), with SVM coefficients used to quantify feature relevance. Contribution/Results: Our approach achieves 75.3–77.8% accuracy in discriminating precision versus power grip—significantly surpassing the 61.1% attained by movement-related cortical potential (MRCP)-based methods—and 93.3% accuracy in grasp versus no-grasp classification. This work establishes a novel paradigm for naturalistic motor intention decoding from EEG and identifies a robust, low-frequency oscillatory biomarker with high discriminative power across grasp conditions.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Intelligent Robots: Manipulation
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

The vision-based grasping brain network integrates visual perception with cognitive and motor processes for visuomotor tasks. While invasive recordings have successfully decoded localized neural activity related to grasp type planning and execution, macroscopic neural activation patterns captured by noninvasive electroencephalography (EEG) remain far less understood. We introduce a novel vision-based grasping platform to investigate grasp-type-specific (precision, power, no-grasp) neural activity across large-scale brain networks using EEG neuroimaging. The platform isolates grasp-specific planning from its associated execution phases in naturalistic visuomotor tasks, where the Filter-Bank Common Spatial Pattern (FBCSP) technique was designed to extract discriminative frequency-specific features within each phase. Support vector machine (SVM) classification discriminated binary (precision vs. power, grasp vs. no-grasp) and multiclass (precision vs. power vs. no-grasp) scenarios for each phase, and were compared against traditional Movement-Related Cortical Potential (MRCP) methods. Low-frequency oscillations (0.5-8 Hz) carry grasp-related information established during planning and maintained throughout execution, with consistent classification performance across both phases (75.3-77.8%) for precision vs. power discrimination, compared to 61.1% using MRCP. Higher-frequency activity (12-40 Hz) showed phase-dependent results with 93.3% accuracy for grasp vs. no-grasp classification but 61.2% for precision vs. power discrimination. Feature importance using SVM coefficients identified discriminative features within frontoparietal networks during planning and motor networks during execution. This work demonstrated the role of low-frequency oscillations in decoding grasp type during planning using noninvasive EEG.

Problem

• Investigating grasp-specific neural activity using EEG neuroimaging
• Decoding grasp type planning and execution with low-frequency oscillations
• Comparing EEG classification methods for visuomotor task discrimination

Innovation

• Using EEG neuroimaging to capture grasp-specific brain activity
• Applying FBCSP technique to extract discriminative frequency features
• Employing SVM classification for binary and multiclass grasp scenarios