A CNN based system to blind sources separation of MEG signals

In this paper a cellular neural network (CNN) based system to perform a real-time, parallel processing of magetoencephalographic data is proposed. In particular, a nonlinear approach to blind sources separation, instead of the linear procedure performed by independent component analysis, is introduced. Moreover, the characteristic spatial distribution of the cells in the CNN system has been exploited to reproduce the topology of the acquisition channels over the scalp.

[1]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[2]  Tzyy-Ping Jung,et al.  Imaging brain dynamics using independent component analysis , 2001, Proc. IEEE.

[3]  D. Shannahoff-Khalsa,et al.  Randomized Controlled Trial of Yogic Meditation Techniques for Patients With Obsessive-Compulsive Disorder , 1999, CNS Spectrums.

[4]  P. Arena,et al.  Cellular neural networks : chaos, complexity and VLSI processing , 1999 .

[5]  C. Koch,et al.  Category-specific visual responses of single neurons in the human medial temporal lobe , 2000, Nature Neuroscience.

[6]  L. Fortuna,et al.  Independent component analysis of magnetoencephalography data , 2001, 2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[7]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[8]  Richard M. Leahy,et al.  Electromagnetic brain mapping , 2001, IEEE Signal Process. Mag..