An Efficient Pairwise Kurtosis Optimization Algorithm for Independent Component Analysis
- Cite this paper as:
- Ge F., Ma J. (2010) An Efficient Pairwise Kurtosis Optimization Algorithm for Independent Component Analysis. In: Huang DS., McGinnity M., Heutte L., Zhang XP. (eds) Advanced Intelligent Computing Theories and Applications. ICIC 2010. Communications in Computer and Information Science, vol 93. Springer, Berlin, Heidelberg
In the framework of Independent Component Analysis (ICA), kurtosis has been used widely in designing source separation algorithms. In fact, the sum of absolute kurtosis values of all the output components is an effective objective function for separating arbitrary sources. In this paper, we propose an efficient ICA algorithm via a modified Jacobi optimization procedure on the kurtosis-sum objective function. The optimal rotation angle for any pair of the output components can be solved directly. It is demonstrated by numerical simulation experiments that our proposed algorithm can be even more computationally efficient than the FastICA algorithm under the same separation performance.
KeywordsIndependent Component Analysis kurtosis pairwise optimization Jacobi algorithm
Unable to display preview. Download preview PDF.