ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Multiple Scale Convolutional Few-Shot Learning Networks for Online P300-Based BrainComputer Interface and Its Application to Patients With Disorder of Consciousness

Pan, Jiahui*; Cai, Honghua; Huang, Haiyun; He, Yanbin; Li, Yuanqing*
IEEE Transactions on Instrumentation and Measurement2023DOI: 10.1109/TIM.2023.3267367
1被引12阅读
引用收藏
分享

摘要

P300 brain-computer interfaces (BCIs) have significant potential for detecting and assessing residual consciousness in patients with disorders of consciousness (DoC) but are limited by insufficient data collected from them. In this study, a multiple scale convolutional few-shot learning (MSCNN-FSL) network was proposed to detect and recognize small sample P300 signals. A multiple scale convolutional neural network (MSCNN) was developed to learn different scale features from different scales of receptive fields to obtain more information from electroencephalograms (EEGs). Then, a prototypical network with cosine distance was introduced as a classifier to classify small sample P300 signals. The MSCNN-FSL was evaluated in two independent online BCI experiments. In the first P300 speller experiment, the presented network achieves good character recognition performance with average accuracies of 98.02% +/- 1.70%. In the second experiment, eight healthy controls achieved photograph recognition performance with average accuracies of 98.75% +/- 1.49%, and three of the 12 patients with DoC achieved more than 64% online accuracies with significance. Our results indicated that the proposed MSCNN-FSL could correctly assess the three patients who may have residual consciousness but were misdiagnosed by the coma recovery scale-revised (CRS-R). Clinical evaluation after two months did prove our BCI assessment results for the three patients.

学科与关键词

关键词
Feature extractionElectroencephalographyConvolutionVisualizationConvolutional neural networksBehavioral sciencesTrainingBrain-computer interface (BCI)disorder of consciousness (DoC)few-shot learning (FSL)multiple scale convolutional neural network (MSCNN)P300
相关
加载中…

文献加载失败,请重试

重试

发表信息

论文状态
公开发表
期刊
IEEE Transactions on Instrumentation and Measurement
发表日期
2023
卷期
第 72 卷
页码
2510616
DOI
10.1109/TIM.2023.3267367
语言
ENGLISH
成果收录
SCIE
资助标注
Science and Technology Innovation (STI) [2022ZD0208900]; National Natural Science Foundation of China [62076103]; Key Realm Research and Development Program of Guangzhou [202007030005]

作者

  • P

    Pan, Jiahui (通讯) (第一作者)

  • C

    Cai, Honghua

查看全部 5 位作者收起作者
  • H

    Huang, Haiyun

  • H

    He, Yanbin

  • L

    Li, Yuanqing (通讯)

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417