Classification-Based Causality Detection in Time Series

Brain effective connectivity aims to detect causal interactions between distinct brain units and it can be studied through the analysis of magneto/electroencephalography (M/EEG) signals. Methods to evaluate effective connectivity belong to the large body of literature related to detecting causal interactions between multivariate autoregressive (MAR) data, a field of signal processing. Here, we reformulate the problem of causality detection as a supervised learning task and we propose a classification-based approach for it. Our solution takes advantage of the MAR model by generating a labeled data set that contains trials of multivariate signals for each possible configuration of causal interactions. Through the definition of a proper feature space, a classifier is trained to identify the causality structure within each trial. As evidence of the efficacy of the proposed method, we report both the cross-validated results and the details of our submission to the causality detection competition of Biomag2014, where the method reached the 2nd place.

[1]  Karl J. Friston.  Functional and Effective Connectivity: A Review , 2011, Brain Connect..

[2]  S. Butler,et al.  Asymmetries in the electroencephalogram associated with cerebral dominance. , 1974, Electroencephalography and clinical neurophysiology.

[3]  Timoteo Carletti,et al.  The Stochastic Evolution of a Protocell: The Gillespie Algorithm in a Dynamically Varying Volume , 2011, Comput. Math. Methods Medicine.

[4]  Vangelis Sakkalis,et al.  Review of advanced techniques for the estimation of brain connectivity measured with EEG/MEG , 2011, Comput. Biol. Medicine.

[5]  Karin Schwab,et al.  Comparison of linear signal processing techniques to infer directed interactions in multivariate neural systems , 2005, Signal Process..

[6]  Luiz A. Baccalá,et al.  Partial directed coherence: a new concept in neural structure determination , 2001, Biological Cybernetics.

[7]  Rodrigo Quian Quiroga,et al.  Nonlinear multivariate analysis of neurophysiological signals , 2005, Progress in Neurobiology.

[8]  Mark W. Woolrich,et al.  Measuring functional connectivity in MEG: A multivariate approach insensitive to linear source leakage , 2012, NeuroImage.

[9]  Barry Horwitz,et al.  The elusive concept of brain connectivity , 2003, NeuroImage.

[10]  Luiz A. Baccalá,et al.  Studying the Interaction Between Brain Structures via Directed Coherence and Granger Causality , 1998 .

[11]  K. Hlavácková-Schindler,et al.  Causality detection based on information-theoretic approaches in time series analysis , 2007 .

[12]  C. Granger.  Investigating causal relations by econometric models and cross-spectral methods , 1969 .

[13]  Mingzhou Ding,et al.  Evaluating causal relations in neural systems: Granger causality, directed transfer function and statistical assessment of significance , 2001, Biological Cybernetics.

[14]  Katarzyna J. Blinowska,et al.  A new method of the description of the information flow in the brain structures , 1991, Biological Cybernetics.

[15]  Luca Faes,et al.  Measuring Connectivity in Linear Multivariate Processes: Definitions, Interpretation, and Practical Analysis , 2012, Comput. Math. Methods Medicine.

[16]  P. G. Larsson,et al.  Reducing the bias of causality measures. , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

[17]  W. Singer,et al.  Testing non-linearity and directedness of interactions between neural groups in the macaque inferotemporal cortex , 1999, Journal of Neuroscience Methods.