Using conditional FCM to mine event-related brain dynamics

We introduce a framework for mining event related dynamics based on conditional FCM (CFCM). For a given set of responses, the variation in the data is summarized by means of a small set of meaningful prototypes accompanied with a low-dimensional graph capturing their relative relationships. CFCM enables prototyping in a principled manner. User-defined constraints, which are imposed by the nature of experimental data and/or dictated by the neuroscientist's intuition, direct the process of knowledge extraction and can robustify single-trial analysis. The method is introduced using simulated data and demonstrated using actual encephalographic data.

[1]  Stefanos Zafeiriou,et al.  Beyond FCM: Graph-theoretic post-processing algorithms for learning and representing the data structure , 2008, Pattern Recognit..

[2]  T. Sejnowski,et al.  Analysis and visualization of single‐trial event‐related potentials , 2001, Human brain mapping.

[3]  Thomas Martinetz,et al.  Topology representing networks , 1994, Neural Networks.

[4]  P. Tass.  Phase Resetting in Medicine and Biology , 1999 .

[5]  N. Thakor,et al.  Multiresolution wavelet analysis of evoked potentials , 1993, IEEE Transactions on Biomedical Engineering.

[6]  G. Gerstein,et al.  Trial-to-Trial Variability and State-Dependent Modulation of Auditory-Evoked Responses in Cortex , 1999, The Journal of Neuroscience.

[7]  S. Fotopoulos,et al.  Mining information from event-related recordings , 2004, IEEE Signal Processing Magazine.

[8]  R. Homma,et al.  Understanding and characterizing Olfactory responses [A manifold learning approach based on optical recordings] , 2008, IEEE Engineering in Medicine and Biology Magazine.

[9]  Piotr J. Durka,et al.  Single evoked potential reconstruction by means of wavelet transform , 2004, Biological Cybernetics.

[10]  R. Prim.  Shortest connection networks and some generalizations , 1957 .

[11]  Walter S. Pritchard,et al.  PCAVR: A portable laboratory program for performing varimax-rotated principal components analysis of event-related potentials , 1984, Brain Research Bulletin.

[12]  A. A. Ioannides,et al.  Single-trial variability in early visual neuromagnetic responses: an explorative study based on the regional activation contributing to the N70m peak , 2003, NeuroImage.

[13]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[14]  Witold Pedrycz,et al.  Knowledge-based clustering - from data to information granules , 2007 .

[15]  R. Yuste,et al.  Attractor dynamics of network UP states in the neocortex , 2003, Nature.

[16]  J. Friedman,et al.  Graphics for the Multivariate Two-Sample Problem , 1981 .

[17]  Dejan Vucinic,et al.  A Manifold Learning Approachcto Understanding and Characterizing Olfactory Responses from Optical-recordings , 2008 .

[18]  S. Makeig,et al.  Mining event-related brain dynamics , 2004, Trends in Cognitive Sciences.

[19]  G Zouridakis,et al.  Estimation of individual evoked potential components using iterative independent component analysis , 2007, Physics in medicine and biology.

[20]  B. Jansen,et al.  Phase synchronization of the ongoing EEG and auditory EP generation , 2003, Clinical Neurophysiology.

[21]  B.H. Jansen,et al.  A fuzzy clustering approach to EP estimation , 1997, IEEE Transactions on Biomedical Engineering.

[22]  A Bezerianos,et al.  Robust moving averages, with Hopfield neural network implementation, for monitoring evoked potential signals. , 1997, Electroencephalography and clinical neurophysiology.

[23]  David A. Leopold,et al.  Single-trial evoked potential estimation using wavelets , 2007, Comput. Biol. Medicine.

[24]  N. Laskaris,et al.  Semantic geodesic maps: a unifying geometrical approach for studying the structure and dynamics of single trial evoked responses , 2002, Clinical Neurophysiology.

[25]  R Quian Quiroga,et al.  Wavelet Transform in the analysis of the frequency composition of evoked potentials. , 2001, Brain research. Brain research protocols.

[26]  D. H. Lange,et al.  Modeling and estimation of single evoked brain potential components , 1997, IEEE Transactions on Biomedical Engineering.

[27]  G. Zouridakis,et al.  Single-trial evoked potential estimation: Comparison between independent component analysis and wavelet denoising , 2007, Clinical Neurophysiology.

[28]  Andreas A. Ioannides,et al.  Clustering of Early Cortical Responses to Median Nerve Stimulation from Average and Single Trial MEG and EEG Signals , 2005, Brain Topography.

[29]  D. Liberati,et al.  A parametric method of identification of single-trial event-related potentials in the brain , 1988, IEEE Transactions on Biomedical Engineering.

[30]  K. J. Blinowska,et al.  Wavelets—new method of evoked potential analysis , 2006, Medical and Biological Engineering and Computing.

[31]  Vahe Poghosyan,et al.  Timing and connectivity in the human somatosensory cortex from single trial mass electrical activity , 2002, Human brain mapping.

[32]  Xiaofei He,et al.  Locality Preserving Projections , 2003, NIPS.

[33]  A. Grinvald,et al.  Dynamics of Ongoing Activity: Explanation of the Large Variability in Evoked Cortical Responses , 1996, Science.