会议论文

英文

IEEE International Conference on Acoustics, Speech and Signal Processing. Proceedings

1520-6149

2022

3933-3937

47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

International Conference on Acoustics Speech and Signal Processing ICASSP

MAY 22-27, 2022

Singapore, SINGAPORE

[Kuang, Li-Dan;Wang, Biao;Zhang, Hao-Peng;Zhang, Jianming;Li, Wenjun;Li, Feng] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha 410114, Peoples R China.^[Lin, Qiu-Hua] Dalian Univ Technol, Sch Informat & Commun Engn, Dalian 116024, Peoples R China.^[Calhoun, Vince D.] Emory Univ, Georgia Inst Technol, Georgia State Univ, Triinst Ctr Translat Res Neuroimaging & Data Sci, Atlanta, GA 30322 USA.

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

978-1-6654-0540-9

10.1109/ICASSP43922.2022.9746404

National Natural Science Foundation of China [61901061, 61871067, 61379012, 61972056]; Natural Science Foundation of Hunan Province [2020JJ5603]; Research Foundation of Education Bureau of Hunan Province [19C0031]; Postgraduate Research Innovation Project of Changsha University of Science and Technology [CX20201SS75]; NSF [2112455, 0840895, 0715022]; NIH [R01MH104680, R01MH107354, R01EB005846]; Fundamental Research Funds for the Central Universities, China [DUT20ZD220]

本校为第一机构

The decomposition of multi-subject fMRI data using rank-(L,L,1,1) block term decomposition (BTD) can preserve higher-way data structure and is more robust to noise effects by decomposing shared spatial maps (SMs) into a product of two rank-L loading matrices. However, since the number of whole-brain voxels is very large and rank L is larger than 1, the rank-(L,L,1,1) BTD requires high computation and memory. Therefore, we propose an accelerated rank-(L,L,1,1) BTD algorithm based upon the method of alternating least squares (ALS). We speed up updates of loading matrices by reducing fMRI data in...