A fast algorithm for automated independent process separation from single channel biomedical signal recordings: Fast IPA


James, C.J. and Davies, M.E. (2008) A fast algorithm for automated independent process separation from single channel biomedical signal recordings: Fast IPA. In, 4th IET International Conference on Advances in Medical, Signal and Information Processing, 2008. MEDSIP 2008. Proceedings of MEDSIP 2008 4th IET International Conference on Advances in Medical Signal and Information Processing, Sta Margherita Ligure, Italy, 14-16 July Stevenage, UK, Institute of Engineering and Technology, IET, 1-4.

Download

Full text not available from this repository.

Description/Abstract

Independent component analysis (ICA) has found many uses in source separation in biomedical signals. We highlight a methodology and put forward an algorithm which allows single channel ICA to be performed on single channel biomedical signal recordings. The algorithm uses a fast, deflationary approach to efficiently extract independent processes underlying the single channel recordings. We show that for processes which are reasonably spectrally disjoint the algorithm can separate out individual sources. We show examples of this using brain signal recordings and abdominal foetal recordings.

Item Type: Book Section
Additional Information: 1 CD-ROM : col. ; 4 3/4 in.
ISBNs: 9780863419348 (hardback)
Related URLs:
Keywords: blind source separation, independent component analysis (ICA), single channel ICA, automated source extraction, independent process analysis
Subjects: Q Science > Q Science (General)
T Technology > TA Engineering (General). Civil engineering (General)
Divisions: University Structure - Pre August 2011 > Institute of Sound and Vibration Research > Signal Processing and Control
ePrint ID: 65184
Date Deposited: 04 Mar 2009
Last Modified: 27 Mar 2014 18:46
URI: http://eprints.soton.ac.uk/id/eprint/65184

Actions (login required)

View Item View Item