Experimental Study on the Effects of Watermarking Techniques on EEG-Based Application System Performance

Watermarking has been suggested as a means to improve security of e-Health systems or to add additional functionalities to such system. All watermarking methods alter the host signal to some extent, though the acceptability of this modification varies with the watermarking scheme and depends on a particular application. However, the effect of watermarking methods on Electroencephalogram (EEG)-based applications has not been investigated. In this paper, we propose a robust EEG watermarking scheme and experimentally investigate the impact of applying the proposed method on the recognition performance of some EEG-based application systems such as emotion recognition and user authentication. We have found that the proposed EEG watermarking scheme results in a small degradation of performance.