Josef Faller

Bio: Josef Faller is an academic researcher from Columbia University. The author has contributed to research in topics: Brain–computer interface & Electroencephalography. The author has an hindex of 21, co-authored 62 publications receiving 1266 citations. Previous affiliations of Josef Faller include Graz University of Technology & United States Army Research Laboratory.

Combining BCI with Virtual Reality: Towards New Applications and Improved BCI

Abstract: Brain–Computer Interfaces (BCI) are communication systems which can convey messages through brain activity alone. Recently BCIs were gaining interest among the virtual reality (VR) community since they have appeared as promising interaction devices for virtual environments (VEs). Especially these implicit interaction techniques are of great interest for the VR community, e.g., you are imaging the movement of your hand and the virtual hand is moving, or you can navigate through houses or museums by your thoughts alone or just by looking at some highlighted objects. Furthermore, VE can provide an excellent testing ground for procedures that could be adapted to real world scenarios, especially patients with disabilities can learn to control their movements or perform specific tasks in a VE. Several studies will highlight these interactions.

Autocalibration and Recurrent Adaptation: Towards a Plug and Play Online ERD-BCI

Abstract: System calibration and user training are essential for operating motor imagery based brain-computer interface (BCI) systems. These steps are often unintuitive and tedious for the user, and do not necessarily lead to a satisfactory level of control. We present an Adaptive BCI framework that provides feedback after only minutes of autocalibration in a two-class BCI setup. During operation, the system recurrently reselects only one out of six predefined logarithmic bandpower features (10-13 and 16-24 Hz from Laplacian derivations over C3, Cz, and C4), specifically, the feature that exhibits maximum discriminability. The system then retrains a linear discriminant analysis classifier on all available data and updates the online paradigm with the new model. Every retraining step is preceded by an online outlier rejection. Operating the system requires no engineering knowledge other than connecting the user and starting the system. In a supporting study, ten out of twelve novice users reached a criterion level of above 70% accuracy in one to three sessions (10-80 min online time) of training, with a median accuracy of 80.2 11.3% in the last session. We consider the presented system a positive first step towards fully autocalibrating motor imagery BCIs.

Random forests in non-invasive sensorimotor rhythm brain-computer interfaces: a practical and convenient non-linear classifier.

Abstract: There is general agreement in the brain-computer interface (BCI) community that although non-linear classifiers can provide better results in some cases, linear classifiers are preferable. Particularly, as non-linear classifiers often involve a number of parameters that must be carefully chosen. However, new non-linear classifiers were developed over the last decade. One of them is the random forest (RF) classifier. Although popular in other fields of science, RFs are not common in BCI research. In this work, we address three open questions regarding RFs in sensorimotor rhythm (SMR) BCIs: parametrization, online applicability, and performance compared to regularized linear discriminant analysis (LDA). We found that the performance of RF is constant over a large range of parameter values. We demonstrate - for the first time - that RFs are applicable online in SMR-BCIs. Further, we show in an offline BCI simulation that RFs statistically significantly outperform regularized LDA by about 3%. These results confirm that RFs are practical and convenient non-linear classifiers for SMR-BCIs. Taking into account further properties of RFs, such as independence from feature distributions, maximum margin behavior, multiclass and advanced data mining capabilities, we argue that RFs should be taken into consideration for future BCIs.

Compact Convolutional Neural Networks for Classification of Asynchronous Steady-state Visual Evoked Potentials

Abstract: Steady-State Visual Evoked Potentials (SSVEPs) are neural oscillations from the parietal and occipital regions of the brain that are evoked from flickering visual stimuli. SSVEPs are robust signals measurable in the electroencephalogram (EEG) and are commonly used in brain-computer interfaces (BCIs). However, methods for high-accuracy decoding of SSVEPs usually require hand-crafted approaches that leverage domain-specific knowledge of the stimulus signals, such as specific temporal frequencies in the visual stimuli and their relative spatial arrangement. When this knowledge is unavailable, such as when SSVEP signals are acquired asynchronously, such approaches tend to fail. In this paper, we show how a compact convolutional neural network (Compact-CNN), which only requires raw EEG signals for automatic feature extraction, can be used to decode signals from a 12-class SSVEP dataset without the need for any domain-specific knowledge or calibration data. We report across subject mean accuracy of approximately 80% (chance being 8.3%) and show this is substantially better than current state-of-the-art hand-crafted approaches using canonical correlation analysis (CCA) and Combined-CCA. Furthermore, we analyze our Compact-CNN to examine the underlying feature representation, discovering that the deep learner extracts additional phase and amplitude related features associated with the structure of the dataset. We discuss how our Compact-CNN shows promise for BCI applications that allow users to freely gaze/attend to any stimulus at any time (e.g., asynchronous BCI) as well as provides a method for analyzing SSVEP signals in a way that might augment our understanding about the basic processing in the visual cortex.

Regulation of arousal via online neurofeedback improves human performance in a demanding sensory-motor task.

Abstract: Our state of arousal can significantly affect our ability to make optimal decisions, judgments, and actions in real-world dynamic environments. The Yerkes-Dodson law, which posits an inverse-U relationship between arousal and task performance, suggests that there is a state of arousal that is optimal for behavioral performance in a given task. Here we show that we can use online neurofeedback to shift an individual's arousal from the right side of the Yerkes-Dodson curve to the left toward a state of improved performance. Specifically, we use a brain-computer interface (BCI) that uses information in the EEG to generate a neurofeedback signal that dynamically adjusts an individual's arousal state when they are engaged in a boundary-avoidance task (BAT). The BAT is a demanding sensory-motor task paradigm that we implement as an aerial navigation task in virtual reality and which creates cognitive conditions that escalate arousal and quickly results in task failure (e.g., missing or crashing into the boundary). We demonstrate that task performance, measured as time and distance over which the subject can navigate before failure, is significantly increased when veridical neurofeedback is provided. Simultaneous measurements of pupil dilation and heart-rate variability show that the neurofeedback indeed reduces arousal. Our work demonstrates a BCI system that uses online neurofeedback to shift arousal state and increase task performance in accordance with the Yerkes-Dodson law.

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

A Review of Classification Algorithms for EEG-based Brain-Computer Interfaces: A 10-year Update

Abstract: Objective: Most current Electroencephalography (EEG)-based Brain-Computer Interfaces (BCIs) are based on machine learning algorithms. There is a large diversity of classifier types that are used in this field, as described in our 2007 review paper. Now, approximately 10 years after this review publication, many new algorithms have been developed and tested to classify EEG signals in BCIs. The time is therefore ripe for an updated review of EEG classification algorithms for BCIs. Approach: We surveyed the BCI and machine learning literature from 2007 to 2017 to identify the new classification approaches that have been investigated to design BCIs. We synthesize these studies in order to present such algorithms, to report how they were used for BCIs, what were the outcomes, and to identify their pros and cons. Main results: We found that the recently designed classification algorithms for EEG-based BCIs can be divided into four main categories: adaptive classifiers, matrix and tensor classifiers, transfer learning and deep learning, plus a few other miscellaneous classifiers. Among these, adaptive classifiers were demonstrated to be generally superior to static ones, even with unsupervised adaptation. Transfer learning can also prove useful although the benefits of transfer learning remain unpredictable. Riemannian geometry-based methods have reached state-of-the-art performances on multiple BCI problems and deserve to be explored more thoroughly, along with tensor-based methods. Shrinkage linear discriminant analysis and random forests also appear particularly useful for small training samples settings. On the other hand, deep learning methods have not yet shown convincing improvement over state-of-the-art BCI methods. Significance: This paper provides a comprehensive overview of the modern classification algorithms used in EEG-based BCIs, presents the principles of these Review of Classification Algorithms for EEG-based BCI 2 methods and guidelines on when and how to use them. It also identifies a number of challenges to further advance EEG classification in BCI.

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.

Deep learning for electroencephalogram (EEG) classification tasks: a review.

Abstract: Objective Electroencephalography (EEG) analysis has been an important tool in neuroscience with applications in neuroscience, neural engineering (e.g. Brain-computer interfaces, BCI's), and even commercial applications. Many of the analytical tools used in EEG studies have used machine learning to uncover relevant information for neural classification and neuroimaging. Recently, the availability of large EEG data sets and advances in machine learning have both led to the deployment of deep learning architectures, especially in the analysis of EEG signals and in understanding the information it may contain for brain functionality. The robust automatic classification of these signals is an important step towards making the use of EEG more practical in many applications and less reliant on trained professionals. Towards this goal, a systematic review of the literature on deep learning applications to EEG classification was performed to address the following critical questions: (1) Which EEG classification tasks have been explored with deep learning? (2) What input formulations have been used for training the deep networks? (3) Are there specific deep learning network structures suitable for specific types of tasks? Approach A systematic literature review of EEG classification using deep learning was performed on Web of Science and PubMed databases, resulting in 90 identified studies. Those studies were analyzed based on type of task, EEG preprocessing methods, input type, and deep learning architecture. Main results For EEG classification tasks, convolutional neural networks, recurrent neural networks, deep belief networks outperform stacked auto-encoders and multi-layer perceptron neural networks in classification accuracy. The tasks that used deep learning fell into five general groups: emotion recognition, motor imagery, mental workload, seizure detection, event related potential detection, and sleep scoring. For each type of task, we describe the specific input formulation, major characteristics, and end classifier recommendations found through this review. Significance This review summarizes the current practices and performance outcomes in the use of deep learning for EEG classification. Practical suggestions on the selection of many hyperparameters are provided in the hope that they will promote or guide the deployment of deep learning to EEG datasets in future research.