Nikolay Chumerin

Within the Ambient Assisted Living (AAL) community, Brain-Computer Interfaces (BCIs) have raised great hopes as they provide alternative communication means for persons with disabilities bypassing the need for speech and other motor activities. Although significant advancements have been realized in the last decade, applications of language models (e.g., word prediction, completion) have only recently started to appear in BCI systems. The main goal of this article is to review the language model applications that supplement non-invasive BCI-based communication systems by discussing their potential and limitations, and to discern future trends. First, a brief overview of the most prominent BCI spelling systems is given, followed by an in-depth discussion of the language models applied to them. These language models are classified according to their functionality in the context of BCI-based spelling: the static/dynamic nature of the user interface, the use of error correction and predictive spelling, and the potential to improve their classification performance by using language models. To conclude, the review offers an overview of the advantages and challenges when implementing language models in BCI-based communication systems when implemented in conjunction with other AAL technologies.

The performance and usability of brain-computer interfaces (BCIs) can be improved by new paradigms, stimulation methods, decoding strategies, sensor technology etc. In this study we introduce new stimulation and decoding methods for electroencephalogram (EEG)-based BCIs that have targets flickering at the same frequency but with different phases. The phase information is estimated from the EEG data, and used for target command decoding. All visual stimulation is done on a conventional (60-Hz) LCD screen. Instead of the 'on/off' visual stimulation, commonly used in phase-coded BCI, we propose one based on a sampled sinusoidal intensity profile. In order to fully exploit the circular nature of the evoked phase response, we introduce a filter feature selection procedure based on circular statistics and propose a fuzzy logic classifier designed to cope with circular information from multiple channels jointly. We show that the proposed visual stimulation enables us not only to encode more commands under the same conditions, but also to obtain EEG responses with a more stable phase. We also demonstrate that the proposed decoding approach outperforms existing ones, especially for the short time windows used. The work presented here shows how to overcome some of the limitations of screen-based visual stimulation. The superiority of the proposed decoding approach demonstrates the importance of preserving the circularity of the data during the decoding stage.

We propose a complex-valued multilayer feedforward neural network classifier for decoding of phase-coded information from steady-state visual evoked potentials. To optimize the performance of the classifier we supply it with two filter-based feature selection strategies. The proposed approaches could be used for a phase-coded brain–computer interface, enabling to encode several targets using only one stimulation frequency. The proposed classifier is a multichannel one, which distinguishes our approach from the existing single-channel ones. We show that the proposed approach outperforms others in terms of accuracy and length of the data segments used for decoding. We show that the decoding based on one optimally selected channel yields an inferior performance compared to the one based on several features, which supports our argument for a multichannel approach.

This paper describes our first attempt to port a brain-computer interface (BCI), created in a research lab and running on expensive equipment, to consumer grade equipment, allowing one to reach a much broader audience and raise public awareness of this new technology. With the BCI, the user can perform a complicated task through mind control only: playing a tactical video-game. Reliable control is accomplished by adapting a Steady-State Visual Evoked Potential (SSVEP) classifier to be robust enough to cope with the signal quality of the consumer grade electroencephalography (EEG) device used, i.e. the Emotiv EPOC. The difference in performance of the game running on research grade EEG equipment versus the Emotiv EPOC is examined. The game was tested by a broad audience during a public event and was well received.

We present an overview of our Brain-computer interface (BCI) research, invasive as well as non-invasive, during the past four years. The invasive BCIs are based on local field-and action potentials recorded with microelectrode arrays implanted in the visual cortex of the macaque monkey. The non-invasive BCIs are based on electroencephalogram (EEG) recorded from a human subject's scalp. Several EEG paradigms were used to enable the subject to type text or to select icons on a computer screen, without having to rely on one's fingers, gestures, or any other form of motor activity: the P300 event-related potential, the steady-state visual evoked potential, and the error related potential. We report on the status of our EEG BCI tests on healthy subjects as well as patients with severe communication disabilities, and our demonstrations to a broad audience to raise the public awareness of BCI.

We report on the development of a four command Brain-Computer Interface (BCI) based on steady-state visual evoked potential (SSVEP) responses detected from human electroencephalograms (EEGs). The proposed system combines spatial filtering, feature extraction and selection, and a classifier. Two types of classifiers were compared: one based on equal treatment of all harmonics in all EEG channels and the second based on preliminary training resulting in a weighted treatment of the harmonics. Results from six healthy subjects are evaluated.