To search, Click below search items.


All Published Papers Search Service


Comparative Evaluation of Various Independent Components (ICA) Tech for the removal of artifacts of EEG Signals


B.Paulchamy, Ilavennila, J.Jaya, R.Saravanakumar


Vol. 10  No. 3  pp. 226-234


In this paper, Independent Component Analysis (ICA) is applied to EEG signals collected from different mental tasks in order to remove the artifacts from the EEG signals. ICA is a statistical and computational technique for revealing hidden factors that underlie sets of random signals. In the ICA model the data samples are assumed to be linear mixture of some unknown latent variables, and the mixing system is also unknown. The latent variables are assumed to have a nongaussian distribution. These variables are the independent components of the observed data which can be found, up to some degree of accuracy, using different algorithms based on ICA techniques. There are several algorithms based on different approaches for ICA widely in use for all sort of applications. These algorithms include, but not limited to, the popular Fast-ICA, Joint Approximate Diagonalization of Eigen values (JADE), Infomax, and Extended Infomax etc. Fast-ICA is based on the optimization of negentropy of the datasets. Infomax and Extended Infomax are based on the minimization of mutual information between the data variables. JADE is based on the fourth-order cumulate matrices of the input data. A framework for accommodating four ICA algorithms is developed to estimate the convergence speed of the algorithms and hence selects the best algorithm for the specific type of data.


Artifacts, EEG Signal, Fast ICA, JADE, BCI, Infomax, Entropy