Information Theoretic Feature Transformation Learning for Brain Interfaces

Abstract

Objective: A variety of pattern analysis techniques for model training in brain interfaces exploit neural feature dimensionality reduction based on feature ranking and selection heuristics. In the light of broad evidence demonstrating the potential sub-optimality of ranking based feature selection by any criterion, we propose to extend this focus with an information theoretic learning driven feature transformation concept. Methods:We present a maximum mutual information linear transformation (MMI-LinT), and a nonlinear transformation (MMI-NonLinT) framework derived by a general definition of the feature transformation learning problem. Empirical assessments are performed based on electroencephalographic (EEG) data recorded during a four class motor imagery brain-computer interface (BCI) task. Exploiting state-of-the-art methods for initial feature vector construction, we compare the proposed approaches with conventional feature selection based dimensionality reduction techniques which are widely used in brain interfaces. Furthermore, for the multi-class problem, we present and exploit a hierarchical graphical model based BCI decoding system.Results: Both binary and multi-class decoding analyses demonstrate significantly better performances with the proposed methods. Conclusion:Information theoretic feature transformations are capable of tackling potential confounders of conventional approaches in various settings.Significance: We argue that this concept provides significant insights to extend the focus on feature selection heuristics to a broader definition of feature transformation learning in brain interfaces.

Stochastic Mutual Information Gradient Estimation for Dimensionality Reduction Networks

“…In combination with the theoretical advancements on gradient-based methods of neural network interpretability (e.g., layer-wise relevance propagation [1,29]), obtained synergies across features as highlighted by high-dimensional feature relevances can yield significant insights based on the application domain. Such feature-synergy based ideas were particularly found interesting for feature learning in brain interfacing as we studied earlier [32,33], as well as gene expression data analysis [23] in consistency with their biological interpretations.…”

“…We motivate our study in the light of these work, where we aim to use standard gradient descent based artificial neural network training and inference pipelines to perform nonlinear maximum mutual information based feature transformations. We previously explored this idea for neurophysiological feature transformations in brain-computer interfaces [32], which we re-address here in the context of neural networks. Recently a different line of work focused on estimating mutual information of high dimensional continuous variables over neural networks, initially proposed as mutual information neural estimation (MINE) [3].…”

“…Specifically, these bounds suggest that the lowest possible Bayes error of any given classifier can be achieved when the mutual information between the random variables Y and C is maximized (cf. [32,43]).…”

A Comprehensive Review on Critical Issues and Possible Solutions of Motor Imagery Based Electroencephalography Brain-Computer Interface

“…In doing so, they constructed a nearest neighbour graph to model the IMFs intrinsic structure. Özdenizci and Erdoğmuş [ 114 ] proposed the information theory based linear and non-linear feature transformation approach to select optimal feature for multi-class MI-EEG BCI system. Pei et al [ 71 ] used stacked auto-encoders on spectral features to reduce the dimension and achieve high accuracy in a multi class asynchronous MI-BCI system.…”

Exploiting Multiple EEG Data Domains with Adversarial Learning

“…Electroencephalogram (EEG) based brain-computer interface (BCI) systems aim to identify users' intentions from brain recordings with potential uses in neurorehabilitation systems [1]. However, moderate decoding accuracies have limited the practical use of BCIs [2], [3]. Due to the high data collection efforts and costs, EEG datasets highly diverge in their recording environment (e.g., stimulus), the equipment and devices, and the ground truths derived.…”