Enhance decoding of pre-movement EEG patterns for brain-computer interfaces
The Characteristics and Locking Process of Nonlinear MEMS Gyroscopes
Evaluation of polarization field in InGaN/GaN multiple quantum well struc...
Growth Control of High-Performance InAs/GaSb Type-II Superlattices via Op...
High-Performance Germanium Waveguide Photodetectors on Silicon*
Nanoscale thermal transport across an GaAs/AlGaAs heterostructure interface
Investigation of modulation transfer function in InGaAs photodetector sma...
Seed-mediated growth of heterostructured Cu1.94S-MS (M = Zn, Cd, Mn) and ...
High-performance phosphorene electromechanical actuators
Recent Advances of Two-Dimensional Nanomaterials for Electrochemical Capa...

Resting-State-Based Spatial Filtering for an fNIRS-Based Motor Imagery Brain-Computer Interface



Author(s): Zheng, YC (Zheng, Yanchun); Zhang, D (Zhang, Dan); Wang, L (Wang, Ling); Wang, YJ (Wang, Yijun); Deng, H (Deng, Hao); Zhang, S (Zhang, Shen); Li, DY (Li, Deyu); Wang, DF (Wang, Daifa)

Source: IEEE ACCESS Volume: 7 Pages: 120603-120615 DOI: 10.1109/ACCESS.2019.2936434 Published: 2019

Abstract: Functional near-infrared spectroscopy (fNIRS) has attracted much attention in brain-computer interface (BCI) area due to its advantages of portability, robustness to electrical artifacts, etc. However, in practical applications, fNIRS-based BCI usually needs a labor-intensive and time-consuming training session (calibration procedure) to optimize the user-specific neural spatial and temporal patterns for further classification. Recently, studies revealed that neural spatial and temporal patterns extracted from user-specific resting-state brain signals were closely related to those of his/her task data. In this study, we proposed a resting-state independent component analysis (RSICA) based spatial filtering algorithm aiming at extracting individual task-related spatial and temporal brain patterns from the resting-state data. Specifically, independent component analysis (ICA) was applied to extract different independent components (ICs) from resting-state fNIRS data. The ICs with their spatial filter weights maximally lateralized over the sensorimotor regions were regarded as most relevant to motor imagery. These spatial filters were used to spatially filter the multi-channel motor imagery task data for feature extraction. Based on 8-minute resting-state data and a small training dataset (20 trials) from 10 participants, the proposed RSICA algorithm achieved an approximately 7% increase in left vs. right hand motor imagery classification accuracy, as compared to the conventional common spatial pattern (CSP)-based and shrinkage algorithms (69.8 +/- 12.1%, 63.3 +/- 10.3% and 63.4 +/- 11.8%, respectively). For acquiring a similar level of classification accuracy (i.e. 70%), the number of training data required could be reduced from 36 trials (CSP) to 22 trials (RSICA). As a relatively small training set is required to obtain a satisfactory performance, training burden is significantly reduced by RSICA, which might be useful for developing practical fNIRS-based motor imagery BCIs.

Accession Number: WOS:000498570600003

ISSN: 2169-3536

Full Text: https://ieeexplore.ieee.org/document/8807173


北京市海淀區清華東路甲35號 北京912信箱 (100083)




[email protected]

版權所有 中國科學院半導體研究所

備案號:京ICP備05085259號 京公網安備110402500052 中國科學院半導體所聲明

澳客彩票网欢迎进入 今日收市股评 今天的股市行情 股票查询一览表 股票下午几点开盘时 华昌达股票股吧 大智慧手机版官方下载 模拟炒股大赛平台 三祥新材股票 股票跌停当天还能涨 1000元怎么玩股