Home // BRAININFO 2016, The First International Conference on Neuroscience and Cognitive Brain Information // View article

Classification of Hand Flexion/Extension Using High-density ECoG

Authors:
Tianxiao Jiang
Tao Jiang
Taylor Wang
Shenshen Mei
Qingzhu Liu
Yunlin Li
Xiaofei Wang
Sujit Prabhu
Zhiyi Sha
Nuri Ince

Keywords: High-density ECoG; Time-frequency map; CSP; LDA.

Abstract:
Grasping is one of the most important hand movements performed in daily life and therefore a hand neuroprosthetic should be able to achieve this function with high accuracy. Electrocorticogram (ECoG) recorded from standard clinical electrodes has been proposed as a potential control signal in brain–machine interfaces (BMIs) and used to provide information about executed motor activity such as arm movement direction and individual finger movements. Here, we investigate the value of ECoG recorded from human motor cortex with high density electrodes to distinguish between hand flexion and extension in single trial level for a hand neuroprosthetic. Two subjects were asked to execute spontaneous hand extension and flexion during the recording. Event-related desynchronization (ERD) and event-related synchronization (ERS) in low-frequency band (LFB: 8-32 Hz) and high-frequency band (HFB: 60-200 Hz) were observed in both subjects during these executed movements. ECoG signal was bandpass filtered in three subbands, alpha (8-13 Hz), beta (13-32 Hz) and gamma (60-200 Hz) for classification. A common spatial pattern (CSP) algorithm fused with linear discriminant analysis (LDA) was used to distinguish between executed movements. In both subjects, the gamma band yielded classification accuracies close to 100%. Alpha and beta bands provided poor classification results with higher latency compared to gamma band. These results suggested that the gamma band spatial patterns of motor cortex captured with high-density ECoG can effectively distinguish between hand extension and flexion. High-density ECoG can be a promising modality to drive a neural prosthetic which can help paralyzed patients to regain crucial daily hand functions.

Pages: 1 to 4

Copyright: Copyright (c) IARIA, 2016

Publication date: November 13, 2016

Published in: conference

ISSN: 2519-8653

ISBN: 978-1-61208-526-5

Location: Barcelona, Spain

Dates: from November 13, 2016 to November 17, 2016