Christoforos Christoforou

Bio: Christoforos Christoforou is an academic researcher from St. John's University. The author has contributed to research in topics: Psychology & Bilinear interpolation. The author has an hindex of 8, co-authored 20 publications receiving 448 citations. Previous affiliations of Christoforos Christoforou include City College of New York & City University of New York.

In a Blink of an Eye and a Switch of a Transistor: Cortically Coupled Computer Vision

Abstract: Our society's information technology advancements have resulted in the increasingly problematic issue of information overload-i.e., we have more access to information than we can possibly process. This is nowhere more apparent than in the volume of imagery and video that we can access on a daily basis-for the general public, availability of YouTube video and Google Images, or for the image analysis professional tasked with searching security video or satellite reconnaissance. Which images to look at and how to ensure we see the images that are of most interest to us, begs the question of whether there are smart ways to triage this volume of imagery. Over the past decade, computer vision research has focused on the issue of ranking and indexing imagery. However, computer vision is limited in its ability to identify interesting imagery, particularly as ?interesting? might be defined by an individual. In this paper we describe our efforts in developing brain-computer interfaces (BCIs) which synergistically integrate computer vision and human vision so as to construct a system for image triage. Our approach exploits machine learning for real-time decoding of brain signals which are recorded noninvasively via electroencephalography (EEG). The signals we decode are specific for events related to imagery attracting a user's attention. We describe two architectures we have developed for this type of cortically coupled computer vision and discuss potential applications and challenges for the future.

Spatiotemporal Linear Decoding of Brain State

Abstract: This review summarizes linear spatiotemporal signal analysis methods that derive their power from careful consideration of spatial and temporal features of skull surface potentials. BCIs offer tremendous potential for improving the quality of life for those with severe neurological disabilities. At the same time, it is now possible to use noninvasive systems to improve performance for time-demanding tasks. Signal processing and machine learning are playing a fundamental role in enabling applications of BCI and in many respects, advances in signal processing and computation have helped to lead the way to real utility of noninvasive BCI.

Bilinear Discriminant Component Analysis

Abstract: Factor analysis and discriminant analysis are often used as complementary approaches to identify linear components in two dimensional data arrays. For three dimensional arrays, which may organize data in dimensions such as space, time, and trials, the opportunity arises to combine these two approaches. A new method, Bilinear Discriminant Component Analysis (BDCA), is derived and demonstrated in the context of functional brain imaging data for which it seems ideally suited. The work suggests to identify a subspace projection which optimally separates classes while ensuring that each dimension in this space captures an independent contribution to the discrimination.

Your Brain on the Movies: A Computational Approach for Predicting Box-office Performance from Viewer's Brain Responses to Movie Trailers.

Abstract: The ability to anticipate the population-wide response of a target audience to a new movie or TV series, before its release, is critical to the film industry. Equally important is the ability to understand the underlying factors that drive or characterize viewer's decision to watch a movie. Traditional approaches (which involve pilot test-screenings, questionnaires, and focus groups) have reached a plateau in their ability to predict the population-wide responses to new movies. In this study, we develop a novel computational approach for extracting neurophysiological electroencephalography (EEG) and eye-gaze based metrics to predict the population-wide behavior of movie goers. We further, explore the connection of the derived metrics to the underlying cognitive processes that might drive moviegoers' decision to watch a movie. Towards that, we recorded neural activity-through the use of EEG-and eye-gaze activity from a group of naive individuals while watching movie trailers of pre-selected movies for which the population-wide preference is captured by the movie's market performance (i.e., box-office ticket sales in the US). Our findings show that the neural based metrics, derived using the proposed methodology, carry predictive information about the broader audience decisions to watch a movie, above and beyond traditional methods. In particular, neural metrics are shown to predict up to 72% of the variance of the films' performance at their premiere and up to 67% of the variance at following weekends; which corresponds to a 23-fold increase in prediction accuracy compared to current neurophysiological or traditional methods. We discuss our findings in the context of existing literature and hypothesize on the possible connection of the derived neurophysiological metrics to cognitive states of focused attention, the encoding of long-term memory, and the synchronization of different components of the brain's rewards network. Beyond the practical implication in predicting and understanding the behavior of moviegoers, the proposed approach can facilitate the use of video stimuli in neuroscience research; such as the study of individual differences in attention-deficit disorders, and the study of desensitization to media violence.

Second-Order Bilinear Discriminant Analysis

Abstract: Traditional analysis methods for single-trial classification of electro-encephalography (EEG) focus on two types of paradigms: phase-locked methods, in which the amplitude of the signal is used as the feature for classification, that is, event related potentials; and second-order methods, in which the feature of interest is the power of the signal, that is, event related (de)synchronization. The process of deciding which paradigm to use is ad hoc and is driven by assumptions regarding the underlying neural generators. Here we propose a method that provides an unified framework for the analysis of EEG, combining first and second-order spatial and temporal features based on a bilinear model. Evaluation of the proposed method on simulated data shows that the technique outperforms state-of-the art techniques for single-trial classification for a broad range of signal-to-noise ratios. Evaluations on human EEG--including one benchmark data set from the Brain Computer Interface (BCI) competition--show statistically significant gains in classification accuracy, with a reduction in overall classification error from 26%-28% to 19%.

EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces

Abstract: Objective Brain-computer interfaces (BCI) enable direct communication with a computer, using neural activity as the control signal. This neural signal is generally chosen from a variety of well-studied electroencephalogram (EEG) signals. For a given BCI paradigm, feature extractors and classifiers are tailored to the distinct characteristics of its expected EEG control signal, limiting its application to that specific signal. Convolutional neural networks (CNNs), which have been used in computer vision and speech recognition to perform automatic feature extraction and classification, have successfully been applied to EEG-based BCIs; however, they have mainly been applied to single BCI paradigms and thus it remains unclear how these architectures generalize to other paradigms. Here, we ask if we can design a single CNN architecture to accurately classify EEG signals from different BCI paradigms, while simultaneously being as compact as possible. Approach In this work we introduce EEGNet, a compact convolutional neural network for EEG-based BCIs. We introduce the use of depthwise and separable convolutions to construct an EEG-specific model which encapsulates well-known EEG feature extraction concepts for BCI. We compare EEGNet, both for within-subject and cross-subject classification, to current state-of-the-art approaches across four BCI paradigms: P300 visual-evoked potentials, error-related negativity responses (ERN), movement-related cortical potentials (MRCP), and sensory motor rhythms (SMR). Main results We show that EEGNet generalizes across paradigms better than, and achieves comparably high performance to, the reference algorithms when only limited training data is available across all tested paradigms. In addition, we demonstrate three different approaches to visualize the contents of a trained EEGNet model to enable interpretation of the learned features. Significance Our results suggest that EEGNet is robust enough to learn a wide variety of interpretable features over a range of BCI tasks. Our models can be found at: https://github.com/vlawhern/arl-eegmodels.

EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces

Abstract: Brain computer interfaces (BCI) enable direct communication with a computer, using neural activity as the control signal. This neural signal is generally chosen from a variety of well-studied electroencephalogram (EEG) signals. For a given BCI paradigm, feature extractors and classifiers are tailored to the distinct characteristics of its expected EEG control signal, limiting its application to that specific signal. Convolutional Neural Networks (CNNs), which have been used in computer vision and speech recognition, have successfully been applied to EEG-based BCIs; however, they have mainly been applied to single BCI paradigms and thus it remains unclear how these architectures generalize to other paradigms. Here, we ask if we can design a single CNN architecture to accurately classify EEG signals from different BCI paradigms, while simultaneously being as compact as possible. In this work we introduce EEGNet, a compact convolutional network for EEG-based BCIs. We introduce the use of depthwise and separable convolutions to construct an EEG-specific model which encapsulates well-known EEG feature extraction concepts for BCI. We compare EEGNet to current state-of-the-art approaches across four BCI paradigms: P300 visual-evoked potentials, error-related negativity responses (ERN), movement-related cortical potentials (MRCP), and sensory motor rhythms (SMR). We show that EEGNet generalizes across paradigms better than the reference algorithms when only limited training data is available. We demonstrate three different approaches to visualize the contents of a trained EEGNet model to enable interpretation of the learned features. Our results suggest that EEGNet is robust enough to learn a wide variety of interpretable features over a range of BCI tasks, suggesting that the observed performances were not due to artifact or noise sources in the data.