Abstract | ||
---|---|---|
In this paper the problem of BOLD detection is addressed. The focus here is on non-negative matrix factorization (NMF), which is a data driven method and able to provide part-based representation of data. A new constrained optimization problem is proposed for the purpose of BOLD detection. The proposed constraint imposes some prior spatial information of active area inside the brain, on the decomposition process. The constraint is built up based on the type of stimulus and available physiological knowledge of the brain performance. The simulation results on both synthetic and real fMRI data show that applying the proposed constraint improves the BOLD detection performance. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/IEMBS.2011.6091251 | 2011 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC) |
Keywords | Field | DocType |
machine learning,signal processing,data handling,magnetic resonance imaging,signal to noise ratio,matrix decomposition,non negative matrix factorization,spatial information,correlation,magnetic resonance image | Spatial analysis,Computer vision,Data-driven,Pattern recognition,Computer science,Signal-to-noise ratio,Matrix decomposition,Artificial intelligence,Non-negative matrix factorization,Constrained optimization problem,Group method of data handling,Signal processing algorithms | Conference |
Volume | ISSN | Citations |
2011 | 1557-170X | 2 |
PageRank | References | Authors |
0.35 | 3 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Saideh Ferdowsi | 1 | 147 | 10.85 |
Vahid Abolghasemi | 2 | 274 | 22.58 |
Bahador Makkiabadi | 3 | 53 | 8.92 |
Saeid Sanei | 4 | 530 | 72.63 |