A Theory for Multiresolution Signal Decomposition: The Wavelet Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern Recognition and Machine Learning (Information Science and Statistics)
Pattern Recognition and Machine Learning (Information Science and Statistics)
Comparing time series using wavelet-based semblance analysis
Computers & Geosciences
ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
Soft transition from probabilistic to possibilistic fuzzy clustering
IEEE Transactions on Fuzzy Systems
| Hi-index | 0.00 |
We make a major step towards answering the question posed in the title, using as model the mouse foetus in its 17-19 embryonic days. We use (a) 2-photon microscopy to image the brainstem cell activity ([Ca2+]) in the pre-Boetzinger complex, and (b) electrical recordings from the phrenic nerve, which indicate the diaphragm contraction during inspiration. We classify the brainstem regions (individual cells or groups of cells) into 'active' and 'inactive', based on whether they contribute or not to the individual electrical signal peaks. As features, we use the Continuous Wavelet Transform-based Semblance responses, for comparing non-periodic and/or periodic-like signals. We use our novel Generative Mixture Model (GMM) possibilistic clustering to obtain the desired classes robustly. This way, we model the inspiration control as a physiological process, which is a crucial step towards understanding how the living brain controls breathing.