Spatial projections of neural arrays: A short guide to classic and new signal analysis techniques

Electroencephalography and other neural recording techniques collect simultaneous data with a multitude of channels. A variety of methods have been proposed to analyze such high-dimensional data and go by various 3-letter acronyms such as PCA, ICA, LDA, SVM, CSP, DSS, CCA, CSD. What all of these methods have in common is that they integrate information by averaging across space, and the different techniques only differ in the contribution of each channel to the average. This has the potential to substantially improve signal quality. The goal of this presentation is to give an overview of existing techniques focusing on those techniques that have an easy to understand objective criterion. It should thus provide a guide on how to pick the technique that best suits a given experimental goal. The review will start with the simplest and most straightforward idea, and finish with a few more recent and novel techniques that are not yet widely known.