This work discusses the implications of selecting particular statistical metrics and thresholds as criteria to diagnose awareness through Brain-Computer Interface (BCI) technology in patients with Disorders of Consciousness (DOC). We report a first analysis of a novel dataset collected to investigate whether a motor attempt electroencephalography (EEG) paradigm coupled with Functional Electrical Stimulation (FES) can detect command following and, therefore, signs of conscious awareness in DOC. We assessed 22 DOC patients admitted to the acute rehabilitation unit after a brain lesion over one or more sessions. We extracted EEG sensorimotor rhythms and performed a standard open-loop BCI pipeline evaluation, classifying motor attempt against resting-state trials. We validate this approach by correlating classification accuracy with the established clinical scale Coma Recovery Scale Revised. We employ a machine learning (ML)-inspired diagnostic criterion based on confidence intervals over chance-level classification accuracy and show that it yields more conservative and, arguably, reliable inference of Cognitive Motor Dissociation (CMD) by means of command-following, neuroimaging-based tools, compared to diagnoses based on clinical assessments or criteria examining the statistical significance of brain features across different mental states.

There is a critical demand for BCI systems that can swiftly adapt to a new user and at the same time function with any user. We propose a fine-tuning approach for neural networks that serves a dual purpose; first, to minimize calibration times through requiring considerably less data - up to one-sixth - from the target subject than training from scratch, and second, to alleviate cases of user illiteracy by providing a substantial performance boost of over 11% in absolute accuracy from the features learned from other subjects. Ultimately, our adaptation method surpasses standard within-subject performance by a large margin in all subjects. We present ablation studies across three datasets, in which we demonstrate that fine-tuning outperforms other adaptation methods for BCI systems and that what matters most is the quantity of pre-training subjects, rather than their BCI-ability, achieving over 8% absolute increase in classification accuracy when scaling up the order of magnitude. Finally, we compare our approach to the state-of-the-art in EEG-based motor imagery and find it comparable, if not superior, to methods employing far more complex neural networks, obtaining 82.60% and 85.64% within-subject accuracy in the four-class BCIC IV-2a and binary MMI datasets respectively.

The susceptibility of electroencephalography (EEG) signal to artifacts is considered a major obstacle preventing the deployment of relevant non-invasive neurotechnology. In spite of a large body of literature dedicated to the identification, rejection and removal of artifactual components in EEG, the study of the impact that different artifacts may have on the EEG signal properties has been mostly qualitative and focused on the source (e.g. muscle activity, electromagnetic interference) rather than the function generating them. This work takes advantage of a unique dataset where EEG of 12 participants elicited during the execution of 9 common human activities (e.g., speaking, blinking, etc.) is co-registered with electromyography (EMG), electrooculography (EOG), accelerometer and gyroscope sensors, and baselined to “resting” (artifact-free) intervals to allow an exact, quantified assessment of the impact of artifacts. We examine several metrics capturing different facets of the influence of artifacts on EEG and measure the extent to which a state-of-the-art artifact removal method is able to eliminate them. In addition to an in-depth, quantified profiling of functional EEG artifacts, our work provides valuable information for precisely tuning the hyper-parameters of artifact rejection and removal algorithms and for designing realistic brain-computer interface (BCI) applications.

This work studies the class of algorithms for learning with side-information that emerges by extending generative models with embedded context-related variables. Using finite mixture models (FMMs) as the prototypical Bayesian network, we show that maximum-likelihood estimation (MLE) of parameters through expectation-maximization (EM) improves over the regular unsupervised case and can approach the performances of supervised learning, despite the absence of any explicit ground-truth data labeling. By direct application of the missing information principle (MIP), the algorithms' performances are proven to range between the conventional supervised and unsupervised MLE extremities proportionally to the information content of the contextual assistance provided. The acquired benefits regard higher estimation precision, smaller standard errors, faster convergence rates, and improved classification accuracy or regression fitness shown in various scenarios while also highlighting important properties and differences among the outlined situations. Applicability is showcased with three real-world unsupervised classification scenarios employing Gaussian mixture models. Importantly, we exemplify the natural extension of this methodology to any type of generative model by deriving an equivalent context-aware algorithm for variational autoencoders (VAs), thus broadening the spectrum of applicability to unsupervised deep learning with artificial neural networks. The latter is contrasted with a neural-symbolic algorithm exploiting side information.

We describe an approach to improving the design and development of Brain-Computer Interface (BCI) applications by simulating the error-prone characteristics and subjective feel of electroencephalogram (EEG), motor-imagery based BCIs. BCIs have the potential to enhance the quality of life of people who are severely disabled, but it is often time-consuming to test and develop the systems. Simulation of BCI characteristics allows developers to rapidly test design options, and gain both subjective and quantitative insight into expected behaviour without using an EEG cap. A further motivation for the use of simulation is that 'impairing' a person without motor disabilities in a game with a disabled BCI user can create a level playing field and help carers empathise with BCI users. We demonstrate a use of the simulator in controlling a game of Brain Pong.

This paper discusses and evaluates the role of shared control approach in a BCI-based telepresence framework. Driving a mobile device by using human brain signals might improve the quality of life of people suffering from severely physical disabilities. By means of a bidirectional audio/video connection to a robot, the BCI user is able to interact actively with relatives and friends located in different rooms. However, the control of robots through an uncertain channel as a BCI may be complicated and exhaustive. Shared control can facilitate the operation of brain-controlled telepresence robots, as demonstrated by the experimental results reported here. In fact, it allows all subjects to complete a rather complex task, driving the robot in a natural environment along a path with several targets and obstacles, in shorter times and with less number of mental commands.