Classification of grasping tasks based on EEG-EMG coherence

TL;DR

This paper introduces a novel method using EEG-EMG coherence to classify different grasping tasks, effectively distinguishing object weight and surface friction with high accuracy, advancing activity recognition techniques.

Contribution

It presents a new application of cortico-muscular coherence for classifying motor tasks based on EEG and EMG signals, demonstrating high accuracy in object property recognition.

Findings

High classification accuracy over 0.8 for grasp types

Effective differentiation of object weight and surface friction

Provides insights into brain-muscle synchronization during tasks

Abstract

This work presents an innovative application of the well-known concept of cortico-muscular coherence for the classification of various motor tasks, i.e., grasps of different kinds of objects. Our approach can classify objects with different weights (motor-related features) and different surface frictions (haptics-related features) with high accuracy (over 0:8). The outcomes presented here provide information about the synchronization existing between the brain and the muscles during specific activities; thus, this may represent a new effective way to perform activity recognition.