Jia-Yang Song — accepted AI-conference papers

2025

Low-Rank Tucker Decomposition of Multi-Subject Complex-Valued fMRI Data

Bin-Hua Zhao, Qiu-Hua Lin, Yue Han, Jia-Yang Song, Yan-Wei Niu, Vince D. Calhoun

ICASSP 2025accepted

Tucker decomposition has shown advantages in simultaneously extracting group shared and individual features for studying brain function from multi-subject fMRI data. However, Tucker decomposition of complex-valued fMRI data is challenging, since the data are highly noisy, and imposing sparsity const…

Cited by 0 Source ↗Scholar ↗

2021

Sparse Representation of Complex-Valued fMRI Data Based on Hard Thresholding of Spatial Source Phase

Jia-Yang Song, Miao-Ying Qi, Dun-Pei Lv, Chao-Ying Zhang, Qiu-Hua Lin, Vince D. Calhoun

ICASSP 2021accepted

Spatial source phase (SSP), derived from complex-valued functional magnetic resonance imaging (fMRI) data by data-driven methods, has unique capacity of identifying blood oxygenation-level dependent (BOLD)-related voxels from noisy voxels regardless of their amplitudes. However, the use of SSP const…

Cited by 0 Source ↗Scholar ↗