DocumentCode :
2961886
Title :
Blind sensor characteristics estimation in a multi-sensor network applied to fMRI analysis
Author :
Theis, Fabian J.
Author_Institution :
Inst. fur Biophys., Regensburg Univ., Germany
fYear :
2004
fDate :
14-17 Dec. 2004
Firstpage :
223
Lastpage :
228
Abstract :
We propose an algorithm, based on blind source separation methods, for blindly estimating the sensor characteristics of a multi-sensor network, whose structure is also unknown. From the observed sensor outputs, the non-linearities are recovered using a well-known Gaussianization procedure. The underlying sources are then reconstructed using spatial decorrelation. Application of this robust algorithm to data sets acquired through functional magnetic resonance imaging (fMRI) lead to detecting a distinctive ´bump´ of the BOLD (blood oxygenation level dependent) effect at larger activations.
Keywords :
Gaussian processes; biomedical MRI; blind source separation; decorrelation; medical image processing; parameter estimation; Gaussianization procedure; blind sensor characteristics estimation; blind source separation; blood oxygenation level dependent effect; fMRI analysis; functional magnetic resonance imaging; multi-sensor network; sensor nonlinearities; spatial decorrelation; Algorithm design and analysis; Biosensors; Data analysis; Decorrelation; Independent component analysis; Intelligent networks; Magnetic sensors; Robustness; Sensor phenomena and characterization; Source separation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Sensors, Sensor Networks and Information Processing Conference, 2004. Proceedings of the 2004
Print_ISBN :
0-7803-8894-1
Type :
conf
DOI :
10.1109/ISSNIP.2004.1417466
Filename :
1417466
Link To Document :
بازگشت