Reducing Calibration Efforts in RSVP Tasks With Multi-Source Adversarial Domain Adaptation
文献类型:期刊论文
作者 | Wei, Wei1,3; Qiu, Shuang3; Ma, Xuelin1,3; Li, Dan1,3; Wang, Bo1,3; He, Huiguang2,3 |
刊名 | IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING |
出版日期 | 2020-11-01 |
卷号 | 28期号:11页码:2344-2355 |
ISSN号 | 1534-4320 |
关键词 | Electroencephalography Calibration Correlation Brain modeling Task analysis Feature extraction Visualization EEG RSVP-based BCI calibration reduction multi-source domain adaptation correlation metric learning |
DOI | 10.1109/TNSRE.2020.3023761 |
通讯作者 | He, Huiguang(huiguang.he@ia.ac.cn) |
英文摘要 | Rapid Serial Visual Presentation (RSVP)-based Brain-Computer Interface (BCI) is an efficient information detection technology by detecting event-related brain responses evoked by target visual stimuli. However, a time-consuming calibration procedure is needed before a new user can use this system. Thus, it is important to reduce calibration efforts for BCI applications. In this article, we propose a multi-source conditional adversarial domain adaptation with the correlation metric learning (mCADA-C) framework that utilizes data from other subjects to reduce the data requirement from the new subject for training the model. This model utilizes adversarial training to enable a CNN-based feature extraction network to extract common features from different domains. A correlation metric learning (CML) loss is proposed to constrain the correlation of features based on class and domain to maximize the intra-class similarity and minimize inter-class similarity. Also, a multi-source framework with a source selection strategy is adopted to integrate the results of multiple domain adaptation. We constructed an RSVP-based dataset that includes 11 subjects each performing three RSVP experiments on three different days. The experimental results demonstrate that our proposed method can achieve 87.72% cross-subject balanced-accuracy under one block calibration. The results indicate our method can realize a higher performance with less calibration efforts. |
WOS关键词 | SERIAL VISUAL PRESENTATION ; COMPUTER ; BCI ; MANIFOLD |
资助项目 | National Natural Science Foundation of China[61976209] ; National Natural Science Foundation of China[81701785] ; National Natural Science Foundation of China[61906188] ; Strategic Priority Research Program of CAS[XDB32040200] ; CAS International Collaboration Key Project[173211KYSB20190024] |
WOS研究方向 | Engineering ; Rehabilitation |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000589256200001 |
资助机构 | National Natural Science Foundation of China ; Strategic Priority Research Program of CAS ; CAS International Collaboration Key Project |
源URL | [http://ir.ia.ac.cn/handle/173211/41738] |
专题 | 类脑智能研究中心_神经计算及脑机交互 |
通讯作者 | He, Huiguang |
作者单位 | 1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100864, Peoples R China 3.Chinese Acad Sci, Natl Lab Pattern Recognit, Res Ctr Brain Inspired Intelligence, Inst Automat, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Wei, Wei,Qiu, Shuang,Ma, Xuelin,et al. Reducing Calibration Efforts in RSVP Tasks With Multi-Source Adversarial Domain Adaptation[J]. IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING,2020,28(11):2344-2355. |
APA | Wei, Wei,Qiu, Shuang,Ma, Xuelin,Li, Dan,Wang, Bo,&He, Huiguang.(2020).Reducing Calibration Efforts in RSVP Tasks With Multi-Source Adversarial Domain Adaptation.IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING,28(11),2344-2355. |
MLA | Wei, Wei,et al."Reducing Calibration Efforts in RSVP Tasks With Multi-Source Adversarial Domain Adaptation".IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 28.11(2020):2344-2355. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。