Blind source separation methods applied to synthesized polysomnographic recordings: a comparative study
- 1 August 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
- Vol. 2007 (1094687X) , 3868-3871
- https://doi.org/10.1109/IEMBS.2007.4353177
Abstract
Blind Source Separation (BSS) problems, under the assumption of static mixture, were extensively explored from the theoretical point of view. Powerful algorithms are now at hand to deal with many concrete BSS applications. Nevertheless, the performances of BSS methods, for a given biomedical application, are rarely investigated. The aim of this paper is to perform quantitative comparisons between various well-known BSS techniques. To do so, synthetic data, reproducing real polysomnographic recordings, are considered.Keywords
This publication has 12 references indexed in Scilit:
- Blind Source Separation for Ambulatory Sleep RecordingIEEE Transactions on Information Technology in Biomedicine, 2006
- Two Contributions to Blind Source Separation Using Time–Frequency DistributionsIEEE Signal Processing Letters, 2004
- Robust whitening procedure in blind source separationcontextElectronics Letters, 2000
- Optimal separation of independent narrow-band sources: Concept and performanceSignal Processing, 1999
- A blind source separation technique using second-order statisticsIEEE Transactions on Signal Processing, 1997
- Electroencephalogram and visual evoked potential generation in a mathematical model of coupled cortical columnsBiological Cybernetics, 1995
- Electroencephalogram and visual evoked potential generation in a mathematical model of coupled cortical columnsBiological Cybernetics, 1995
- A fast method to compute surface potentials generated by dipoles within multilayer anisotropic spheresPhysics in Medicine & Biology, 1995
- Independent component analysis, A new concept?Signal Processing, 1994
- Blind beamforming for non-gaussian signalsIEE Proceedings F Radar and Signal Processing, 1993