Classification-Based Causality Detection in Time Series

Abstract

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.

Classification-Based Prediction of Effective Connectivity Between Timeseries With a Realistic Cortical Network Model

“…The remaining part of the dataset was used to estimate the quality of predictions, both for the proposed method and for the Granger Causality Analysis (GCA, see Barnett and Seth, 2014 ) method (see section 3), for comparison. In the second part of this section, we briefly present the proposed classification-based method for predicting causality, following Benozzo et al ( 2016 , 2017 ). Before the second part, we define the multivariate autoregressive (MAR) model, that we use for generating a second dataset to further characterize the proposed method, and a traditional causality measure: the Geweke index, on which GCA is based.…”

“…The method presented in this work builds on our previous work (see Benozzo et al, 2016 , 2017 ), where we developed a conceptually similar paradigm applied to a simple MAR model, rather than to a complex biophysical model of neural interactions. There, we proposed a novel feature space to encode the multivariate timeseries and showed that effective connectivity could be predicted at even better rates than those of state-of-the-art solutions.…”

“…In order to set up a classification problem, here we adopt the feature space that we designed in Benozzo et al ( 2016 , 2017 ), which is based on the Granger principles of temporal precedence and predictability. With such feature space, we obtain a more convenient representation of the multivariate timeseries generated by the neural network model.…”

“…In the remaining part of the article, we first describe the proposed neural network model derived from Mazzoni et al ( 2008 ), that we extended by adding connections between microcircuits rather than studying single isolated microcircuits as in the original model (see section 2). Then, we briefly describe the proposed method for detecting the pattern of effective connectivity from observed timeseries, following Benozzo et al ( 2016 , 2017 ). In section 3, we report the experiments conducted in this work to support our claims.…”

Supervised Estimation of Granger-Based Causality between Time Series

“…In addition, we report the details of the solution computed with the supervised method that we submitted to the Biomag2014 Causality Challenge (Causal2014)b 1 , which reached the second place of the ranking (Benozzo et al, 2016 ). Such competition adopted an autoregressive model as generative process to simulate brain signals.…”