DocumentCode :
141403
Title :
Basis selection for maximally independent EEG sources
Author :
Balkan, Ozgur ; Bigdely-Shamlo, Nima ; Kreutz-Delgado, Kenneth ; Makeig, Scott
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of California, San Diego, La Jolla, CA, USA
fYear :
2014
fDate :
26-30 Aug. 2014
Firstpage :
6639
Lastpage :
6642
Abstract :
We suggest a solution to the following problem: “Given multichannel linear source mixture data Y, and an overcomplete dictionary, A, of source projections, ai, how can we construct a complete basis, A0, by selecting columns from A such that the sources X = A-01Y are as statistically independent as possible from each other?”. While conventional independent component analysis (ICA) methods learn the mixing matrix A0 from scratch given Y, we restrict ourselves to selecting basis vectors from a known overcomplete dictionary. We develop two methods based on modifications of the maximum likelihood equivalent of the Infomax approach and the reconstruction-ICA (RICA) algorithm. We show that on realistic synthetic electroencephalographic (EEG) data our algorithms can find the true sources in the case of a highly coherent dictionary while requiring relatively fewer data points compared to other algorithms. On real EEG data, our algorithms obtain higher mutual information reduction.
Keywords :
bioelectric potentials; electroencephalography; independent component analysis; maximum likelihood estimation; medical signal processing; neurophysiology; Infomax approach; given multichannel linear source mixture data; independent component analysis methods; maximally independent EEG sources; maximum likelihood equivalent modifications; realistic synthetic electroencephalographic data; reconstruction-ICA algorithm; Algorithm design and analysis; Brain modeling; Dictionaries; Electroencephalography; Mutual information; Signal processing algorithms; Vectors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual International Conference of the IEEE
Conference_Location :
Chicago, IL
ISSN :
1557-170X
Type :
conf
DOI :
10.1109/EMBC.2014.6945150
Filename :
6945150
Link To Document :
بازگشت