Using Dynamic Bayesian Networks for modeling EEG topographic sequences

In this work we present a methodology for modeling the trajectory of EEG topography over time, using Dynamic Bayesian Networks (DBNs). Based on the microstate model we are using DBNs to model the evolution of the EEG topography. Analysis of the microstate model is being usually limited in the wide band signal or an isolated band. We are using Coupled Hidden Markov Models (CHMM) and a two level influence model in order to model the temporal evolution and the coupling of the topography states in three bands, delta, theta and alpha. We are applying this methodology for the classification of target and non-target single trial from a visual detection task. The results indicate that taking under consideration the interaction among the different bands improves the classification of single trials.

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

[2]  Denis Brunet,et al.  Topographic ERP Analyses: A Step-by-Step Tutorial Review , 2008, Brain Topography.

[3]  W. Klimesch,et al.  Simultaneous desynchronization and synchronization of different alpha responses in the human electroencephalograph: a neglected paradox? , 2000, Neuroscience Letters.

[4]  M Congedo,et al.  A review of classification algorithms for EEG-based brain–computer interfaces , 2007, Journal of neural engineering.

[5]  Panteleimon Giannakopoulos,et al.  Distinction between Perceptual and Attentional Processing in Working Memory Tasks: A Study of Phase-locked and Induced Oscillatory Brain Dynamics , 2007, Journal of Cognitive Neuroscience.

[6]  Gilles Pourtois,et al.  Decoding Sequence Learning from Single-Trial Intracranial EEG in Humans , 2011, PloS one.

[7]  Serge Beucher,et al.  Watershed, Hierarchical Segmentation and Waterfall Algorithm , 1994, ISMM.

[8]  Christoph M. Michel,et al.  Towards the utilization of EEG as a brain imaging tool , 2012, NeuroImage.

[9]  Maria Stein,et al.  A Tutorial on Data-Driven Methods for Statistically Assessing ERP Topographies , 2013, Brain Topography.

[10]  Dimitris N. Metaxas,et al.  Parallel hidden Markov models for American sign language recognition , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[11]  M. Zervakis,et al.  Intertrial coherence and causal interaction among independent EEG components , 2011, Journal of Neuroscience Methods.

[12]  Raveendran Paramesran,et al.  VEP optimal channel selection using genetic algorithm for neural network classification of alcoholics , 2002, IEEE Trans. Neural Networks.

[13]  Nikolaos G. Bourbakis,et al.  Emulating human visual perception for measuring difference in images using an SPN graph approach , 2002, IEEE Trans. Syst. Man Cybern. Part B.

[14]  Samy Bengio,et al.  Learning Influence among Interacting Markov Chains , 2005, NIPS.

[15]  Stuart J. Russell,et al.  Dynamic bayesian networks: representation, inference and learning , 2002 .

[16]  William Equitz,et al.  A new vector quantization clustering algorithm , 1989, IEEE Trans. Acoust. Speech Signal Process..

[17]  Nikolaos G. Bourbakis,et al.  Microstate analysis of the EEG using local global graphs , 2013, 13th IEEE International Conference on BioInformatics and BioEngineering.

[18]  D Lehmann,et al.  EEG alpha map series: brain micro-states by space-oriented adaptive segmentation. , 1987, Electroencephalography and clinical neurophysiology.