Document Type




Publication Details

A dissertation submitted in partial fulfilment of the requirements of Dublin Institute of Technology for the degree of M.Sc. in Computer Science (Data Science) March 2022.


The presence of artefacts in Electroencephalograph (EEG) signals can have a considerable impact on the information they portray. In this comparative study, the automated removal of eye blink artefacts using the constrained latent representation of a stacked dense autoencoders (SDAE) and comparing its ability to that of the manual independent component analysis (ICA) approach was evaluated. A comparative evaluation of 5 stacked dense autoencoder architectures lead to a chosen architecture for which the ability to automatically detect and remove eye blink artefacts were both statistically and humanistically evaluated. The ability of the stacked dense autoencoder was statistically evaluated with the manual approach of ICA using the correlation coefficient, a comparative affect on the SNR using both approaches and a humanistic evaluation using visual inspections of the components of the stacked dense autoencoder reconstruction to that of the post ICA reconstruction where an inverse RMSE allowed for a further statistical evaluation of this comparison. It was found that the stacked dense autoencoder was unable to reconstruct random signal segments in any meaningful capacity when compared to that of ICA.

Creative Commons License

Creative Commons Attribution-Share Alike 4.0 International License
This work is licensed under a Creative Commons Attribution-Share Alike 4.0 International License.