A Hierarchical Approach for Decoding Human Reach-and-Grasp Activities based on EEG Signals

Physically disabled patients such as the paralyzed, amputees and stroke patients find it difficult to perform daily activities on their own. A Brain-Computer Interface (BCI) using Electroencephalography (EEG) signals is an option for the rehabilitation of these patients. The BCI function can be enhanced by decoding the movements from a limb through an intuitive control of the prosthetic arm. However, decoding them with the traditional classifiers is a challenging task. In this paper, a two-stage hierarchical framework is proposed for the decoding of reach-and-grasp actions. In stage-l, the action signals are separated from rest segments based on power spectral density features and a fine k-nearest neighbor classifier (FKNN). In stage-2, the signals identified as action are further classified into palmar and lateral type reach-and-grasp actions using the mean absolute value features with the FKNN classifier. In comparison with the existing classifiers, the proposed method has a superior performance of 85.38% test accuracy.