Embedded sparse representation of fMRI data via group-wise dictionary optimization

2016 ◽  
Author(s):  
Dajiang Zhu ◽  
Binbin Lin ◽  
Joshua Faskowitz ◽  
Jieping Ye ◽  
Paul M. Thompson
Keyword(s):  
Sparse Representation ◽  
Fmri Data

scholarly journals Brain State Decoding Based on fMRI Using Semisupervised Sparse Representation Classifications

2018 ◽  
Vol 2018 ◽  
pp. 1-12 ◽  
Author(s):  
Jing Zhang ◽  
Chuncheng Zhang ◽  
Li Yao ◽  
Xiaojie Zhao ◽  
Zhiying Long
Keyword(s):  
Sparse Representation ◽  
Supervised Learning ◽  
Reconstruction Error ◽  
Classification Performance ◽  
Semisupervised Learning ◽  
Fmri Data ◽  
Training Dataset ◽  
Brain State ◽  
Classification Techniques ◽  
Average Coefficient

Multivariate classification techniques have been widely applied to decode brain states using functional magnetic resonance imaging (fMRI). Due to variabilities in fMRI data and the limitation of the collection of human fMRI data, it is not easy to train an efficient and robust supervised-learning classifier for fMRI data. Among various classification techniques, sparse representation classifier (SRC) exhibits a state-of-the-art classification performance in image classification. However, SRC has rarely been applied to fMRI-based decoding. This study aimed to improve SRC using unlabeled testing samples to allow it to be effectively applied to fMRI-based decoding. We proposed a semisupervised-learning SRC with an average coefficient (semiSRC-AVE) method that performed the classification using the average coefficient of each class instead of the reconstruction error and selectively updated the training dataset using new testing data with high confidence to improve the performance of SRC. Simulated and real fMRI experiments were performed to investigate the feasibility and robustness of semiSRC-AVE. The results of the simulated and real fMRI experiments showed that semiSRC-AVE significantly outperformed supervised learning SRC with an average coefficient (SRC-AVE) method and showed better performance than the other three semisupervised learning methods.

Joint Sparse Representation of Brain Activity Patterns in Multi-Task fMRI Data

2015 ◽  
Vol 34 (1) ◽  
pp. 2-12 ◽  
Author(s):  
M. Ramezani ◽  
K. Marble ◽  
H. Trang ◽  
I. S. Johnsrude ◽  
P. Abolmaesumi
Keyword(s):  
Sparse Representation ◽  
Brain Activity ◽  
Activity Patterns ◽  
Fmri Data ◽  
Joint Sparse Representation

scholarly journals Signal sampling for efficient sparse representation of resting state FMRI data

2015 ◽  
Vol 10 (4) ◽  
pp. 1206-1222 ◽  
Author(s):  
Bao Ge ◽  
Milad Makkie ◽  
Jin Wang ◽  
Shijie Zhao ◽  
Xi Jiang ◽  
...  
Keyword(s):  
Sparse Representation ◽  
Resting State ◽  
Resting State Fmri ◽  
Fmri Data ◽  
Signal Sampling

scholarly journals Assessing the effects of cocaine dependence and pathological gambling using group-wise sparse representation of natural stimulus FMRI data

2016 ◽  
Vol 11 (4) ◽  
pp. 1179-1191 ◽  
Author(s):  
Yudan Ren ◽  
Jun Fang ◽  
Jinglei Lv ◽  
Xintao Hu ◽  
Cong Christine Guo ◽  
...  
Keyword(s):  
Pathological Gambling ◽  
Sparse Representation ◽  
Cocaine Dependence ◽  
Fmri Data ◽  
Natural Stimulus
Sign in / Sign up

Export Citation Format

Share Document