A new constrained independent component analysis method

Abstract—Constrained independent component analysis (cICA) is a gen-eral framework to incorporate a priori information from problem into the negentropy contrast function as constrained terms to form an augmented Lagrangian function. In this letter, a new improved algorithm for cICA is presented through the investigation of the inequality constraints, in which different closeness measurements are compared. The utility of our pro-posed algorithm is demonstrated by the experiments with synthetic data and electroencephalogram (EEG) data. Index Terms—Constrained optimization, electroencephalogram (EEG), ICA with reference (ICA-R), independent component analysis (ICA). I