On the use of Independent Component Analysis for brain signal processing 1=Healthcare technologies 2=Digital Signal Processing

Lead Research Organisation: University of Warwick
Department Name: Sch of Engineering

Abstract

Independent Component Analysis (ICA) is a signal processing technique that has gained in popularity over the years used as a means of extracting meaningful information from a number of biomedical signal measurements made across the body. In Neural Engineering in particular, ICA has provided a very useful means of extracting information about neural sources from recordings of the electroencephalogram and magnetoencephalogram - (EEG and MEG respectively). ICA is about the separation of statistically independent sources from a set of mixed measurements - for example in extracting eye-blinks from EEG, etc. The strong assumption of statistical independence of the underlying sources is usually well met in neural engineering cases. Standard methods of ICA usually work with multiple channels that extract a similar number of independent sources. In previous work it has been shown that 'single-channel' ICA is possible and is in itself a very powerful technique for the extraction of multiple sources underlying a single channel measurement. Whereas 'standard' ICA can be termed as 'spatial' ICA, single channel ICA can be termed as 'temporal' ICA - as there is no spatial information informing the ICA process due to the single channel arrangement. The logical progression for ICA is to perform spatio-temporal ICA, whereby the ICA process is informed by means of both spatial and temporal/spectral information derived from a set of neural signal recordings. It can be shown that space-time ICA results in a powerful algorithm that can extract meaningful information in brain signal recordings across a number of conditions. The technique is not without its issues, suffering from the same problems standard ICA suffers from; including issues around the assumptions of linear, noiseless, statistically independent mixing of sources as well as the dilemma of choosing relevant sources after ICA is complete. With space-time ICA the problem is compounded due to the curse of dimensionality. This project will build on previous work, enhancing the ICA process and applying the techniques to various EEG signal databases. A further part of the project will involve the setting up and running of various EEG data gathering exercises applying the ICA techniques to brain-computer interfacing paradigms.

Publications

10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/R513374/1 01/10/2018 30/09/2023
2083690 Studentship EP/R513374/1 01/10/2018 31/03/2022 Hok Yin CHIU