This article is part of the supplement: Third Annual MCBIOS Conference. Bioinformatics: A Calculated Discovery
Independent Component Analysis-motivated Approach to Classificatory Decomposition of Cortical Evoked Potentials
1 Department of Biology, Emory University, Atlanta, Georgia, USA
2 Department of Biology, Arkansas State University, Jonesboro, Arkansas, USA
3 Kidney Disease Program, University of Louisville, Louisville, Kentucky, USA
4 Computer Science Department, University of Arkansas at Little Rock, Little Rock, Arkansas, USA
BMC Bioinformatics 2006, 7(Suppl 2):S8 doi:10.1186/1471-2105-7-S2-S8Published: 26 September 2006
Independent Component Analysis (ICA) proves to be useful in the analysis of neural activity, as it allows for identification of distinct sources of activity. Applied to measurements registered in a controlled setting and under exposure to an external stimulus, it can facilitate analysis of the impact of the stimulus on those sources. The link between the stimulus and a given source can be verified by a classifier that is able to "predict" the condition a given signal was registered under, solely based on the components. However, the ICA's assumption about statistical independence of sources is often unrealistic and turns out to be insufficient to build an accurate classifier. Therefore, we propose to utilize a novel method, based on hybridization of ICA, multi-objective evolutionary algorithms (MOEA), and rough sets (RS), that attempts to improve the effectiveness of signal decomposition techniques by providing them with "classification-awareness."
The preliminary results described here are very promising and further investigation of other MOEAs and/or RS-based classification accuracy measures should be pursued. Even a quick visual analysis of those results can provide an interesting insight into the problem of neural activity analysis.
We present a methodology of classificatory decomposition of signals. One of the main advantages of our approach is the fact that rather than solely relying on often unrealistic assumptions about statistical independence of sources, components are generated in the light of a underlying classification problem itself.