Multi-subject data augmentation for target subject semantic decoding with deep multi-view adversarial learning

doi:10.1016/j.ins.2020.09.012

CORC > 自动化研究所 > 中国科学院自动化研究所 > 类脑智能研究中心 > 神经计算及脑机交互

	Multi-subject data augmentation for target subject semantic decoding with deep multi-view adversarial learning
	Li, Dan 1,3,4; Du, Changde 1,3,4,5; Wang, Shengpei 1,3,4; Wang, Haibao 1,3,4; He, Huiguang 1,2,3,4
刊名	INFORMATION SCIENCES
	2021-02-08
卷号	547 页码:1025-1044
关键词	Data augmentation Semantic decoding Multi-view adversarial learning Sparse reconstruction relation
ISSN号	0020-0255
DOI	10.1016/j.ins.2020.09.012
通讯作者	He, Huiguang(huiguang.he@ia.ac.cn)
英文摘要	Functional magnetic resonance imaging (fMRI) is widely used in the field of brain semantic decoding. However, as fMRI data acquisition is time-consuming and expensive, the number of samples is usually small in the existing fMRI datasets. It is difficult to build an accurate brain decoding model for a subject with insufficient fMRI data. The majority of semantic decoding methods focus on designing predictive model with limited samples, while less attention is paid to fMRI data augmentation. Leveraging data from related but different subjects can be regarded as a new strategy to improve the performance of predictive model. There are two challenges when using information from different subjects: 1) feature mismatch; 2) distribution mismatch. In this paper, we propose a multi-subject fMRI data augmentation method to address the above two challenges, which can improve the decoding accuracy of the target subject. Specifically, the subject information can be translated from one to another by using multiple subject-specific encoders, decoders and discriminators. The encoder maps each subject to a shared latent space, solving the feature mismatch problem. The decoders and discriminators form multiple generative adversarial network architectures, which solves the distribution mismatch problem. Meanwhile, to ensure that the representation of the latent space preserves information of the input space, our method not only minimizes the local data reconstruction loss, but also preserves the sparse reconstruction (semantic) relation over the whole dataset of the input space. Extensive experiments on three fMRI datasets demonstrate the effectiveness of the proposed method. (C) 2020 Elsevier Inc. All rights reserved.
资助项目	National Natural Science Foundationof China[61976209] ; National Natural Science Foundationof China[62020106015] ; CAS Inte rnational Collaboration Key Project[173211KYSB20190024] ; Strategic Priority Research Program of CAS[XDB32040000]
WOS关键词	PATTERN-ANALYSIS ; VOXEL SELECTION ; IMAGES
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER SCIENCE INC
WOS记录号	WOS:000590678700002
资助机构	National Natural Science Foundationof China ; CAS Inte rnational Collaboration Key Project ; Strategic Priority Research Program of CAS
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/42680]
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, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Inst Automat, Res Ctr Brain Inspired Intelligence, Beijing 100190, Peoples R China 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 5.Huawei Cloud BU EI Innovat Lab, Beijing 100085, Peoples R China
推荐引用方式 GB/T 7714	Li, Dan,Du, Changde,Wang, Shengpei,et al. Multi-subject data augmentation for target subject semantic decoding with deep multi-view adversarial learning[J]. INFORMATION SCIENCES,2021,547:1025-1044.
APA	Li, Dan,Du, Changde,Wang, Shengpei,Wang, Haibao,&He, Huiguang.(2021).Multi-subject data augmentation for target subject semantic decoding with deep multi-view adversarial learning.INFORMATION SCIENCES,547,1025-1044.
MLA	Li, Dan,et al."Multi-subject data augmentation for target subject semantic decoding with deep multi-view adversarial learning".INFORMATION SCIENCES 547(2021):1025-1044.