Non-negative Independent Component Analysis Algorithm Based on 2D Givens Rotations and a Newton Optimization

Abstract. In this paper, we consider the Independent Component Analysis problem when the hidden sources are non-negative (Non-negative ICA). This problem is formulated as a non-linear cost function optimization over the special orthogonal matrix group SO(n). Using Givens rotations and Newton optimization, we developed an effective axis pair rotation method for Non-negative ICA. The performance of the proposed method is compared to those designed by Plumbley and simulations on synthetic data show the efficiency of the proposed algorithm. Key words: Non-negative ICA, Givens rotations, Newton optimization, Complexity calculation

• Type: Journal
• Year: 2010
• Where: ICA
• Authors: Wendyam Serge Boris Ouedraogo, Antoine Souloumiac, Christian Jutten
• Keywords: Component Analysis Problem, Cost Function Optimization, ICA 2010, Non-negative ICA, Signal Processing