Independent Component Analysis Applied on Multi–channel Auditory Steady–state Response Measurements

The application of auditory steady–state responses (ASSRs) is an objective and frequency specific technique to assess reliable hearing thresholds at audiometric frequencies. Unfortunately, the duration of ASSR measurement can be long, which is unpractical for wide scale clinical application. Therefore, we propose independent component analysis (ICA) as a tool to improve the ASSR detection in recorded multi–channel electroencephalogram (EEG) data obtained at high intensities. We conclude that ICA is able to reduce measurement duration significantly. For a multi–channel implementation, near–optimal performance is obtained with five–channel recordings. A proposal for a generative model is suggested. This model may provide the ability to explain some observed characteristics of the ICA–ASSR problem.