Self-organizing maps
Empirical mode decomposition of field potentials from macaque V4 in visual spatial attention
Biological Cybernetics
Decoding Population Neuronal Responses by Topological Clustering
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
| Hi-index | 0.00 |
This paper describes the use of empirical mode decomposition and Hilbert transform for the analysis of non-stationary signal. The effectiveness of the method is shown on examples of both artificial signals and neurobiological recordings. The method can decompose a signal into data-driven intrinsic mode functions, which can be regarded as underlying oscillations contained in the signal. Then the Hilbert transform is used to extract instantaneous frequencies. Better time-frequency resolution can be obtained compared to the Fourier or wavelet transforms. Initial attempt has also been made on clustering decomposed and extracted signal components. The study suggests that using the instantaneous frequency as the matching criteria can reveal hidden features that may not be observable using features from other transformation methods.