Axel Gräser

Multiple Channel Detection of Steady-State Visual Evoked Potentials for Brain-Computer Interfaces

In this paper, novel methods for detecting steady-state visual evoked potentials using multiple electroencephalogram (EEG) signals are presented. The methods are tailored for brain-computer interfacing, where fast and accurate detection is of vital importance for achieving high information transfer rates. High detection accuracy using short time segments is obtained by finding combinations of electrode signals that cancel strong interference signals in the EEG data. Data from a test group consisting of 10 subjects are used to evaluate the new methods and to compare them to standard techniques. Using 1-s signal segments, six different visual stimulation frequencies could be discriminated with an average classification accuracy of 84%. An additional advantage of the presented methodology is that it is fully online, i.e., no calibration data for noise estimation, feature extraction, or electrode selection is needed

BCI Demographics: How Many (and What Kinds of) People Can Use an SSVEP BCI?

Brain-computer interface (BCI) systems enable communication without movement. It is unclear why some BCI approaches or parameters are less effective with some users. This study elucidates BCI demographics by exploring correlations among BCI performance, personal preferences, and different subject factors such as age or gender. Results showed that most people, despite having no prior BCI experience, could use the Bremen SSVEP BCI system in a very noisy field setting. Performance tended to be better in both young and female subjects. Most subjects stated that they did not consider the flickering stimuli annoying and would use or recommend this BCI system. These and other demographic analyses may help identify the best BCI for each user.

Convolutional Neural Networks for P300 Detection with Application to Brain-Computer Interfaces

A Brain-Computer Interface (BCI) is a specific type of human-computer interface that enables the direct communication between human and computers by analyzing brain measurements. Oddball paradigms are used in BCI to generate event-related potentials (ERPs), like the P300 wave, on targets selected by the user. A P300 speller is based on this principle, where the detection of P300 waves allows the user to write characters. The P300 speller is composed of two classification problems. The first classification is to detect the presence of a P300 in the electroencephalogram (EEG). The second one corresponds to the combination of different P300 responses for determining the right character to spell. A new method for the detection of P300 waves is presented. This model is based on a convolutional neural network (CNN). The topology of the network is adapted to the detection of P300 waves in the time domain. Seven classifiers based on the CNN are proposed: four single classifiers with different features set and three multiclassifiers. These models are tested and compared on the Data set II of the third BCI competition. The best result is obtained with a multiclassifier solution with a recognition rate of 95.5 percent, without channel selection before the classification. The proposed approach provides also a new way for analyzing brain activities due to the receptive field of the CNN models.

BCI Demographics II: How Many (and What Kinds of) People Can Use a High-Frequency SSVEP BCI?

Brain-computer interface (BCI) systems use brain activity as an input signal and enable communication without movement. This study is a successor of our previous study (BCI demographics I) and examines correlations among BCI performance, personal preferences, and different subject factors such as age or gender for two sets of steady-state visual evoked potential (SSVEP) stimuli: one in the medium frequency range (13, 14, 15 and 16 Hz) and another in the high-frequency range (34, 36,38, 40 Hz). High-frequency SSVEPs (above 30 Hz) diminish user fatigue and risk of photosensitive epileptic seizures. Results showed that most people, despite having no prior BCI experience, could use the SSVEP-based Bremen-BCI system in a very noisy field setting at a fair. Results showed that demographic parameters as well as handedness, tiredness, alcohol and caffeine consumption, etc., have no significant effect on the performance of SSVEP-based BCI. Most subjects did not consider the flickering stimuli annoying, only five out of total 86 participants indicated change in fatigue during the experiment. 84 subjects performed with a mean information transfer rate of 17.24 ± 6.99 bit/min and an accuracy of 92.26 ± 7.82% with the medium frequency set, whereas only 56 subjects performed with a mean information transfer rate of 12.10 ± 7.31 bit/min and accuracy of 89.16 ± 9.29% with the high-frequency set. These and other demographic analyses may help identify the best BCI for each user.

Navigating a smart wheelchair with a brain-computer interface interpreting steady-state visual evoked potentials

In order to allow severely disabled people who cannot move their arms and legs to steer an automated wheelchair, this work proposes the combination of a non-invasive EEG-based human-robot interface and an autonomous navigation system that safely executes the issued commands. The robust classification of steady-state visual evoked potentials in brain activity allows for the seamless projection of qualitative directional navigation commands onto a frequently updated route graph representation of the environment. The deduced metrical target locations are navigated to by the application of an extended version of the well-established nearness diagram navigation method. The applicability of the system proposed is demonstrated by a real-world pilot study in which eight out of nine untrained subjects successfully navigated an automated wheelchair, requiring only some ten minutes of preparation.

Brain-Computer Interface for high-level control of rehabilitation robotic systems

In this work, a brain-computer interface (BCI) based on steady-state visual evoked potentials (SSVEP) is presented as an input device for the human machine interface (HMI) of the semi-autonomous robot FRIEND II. The role of the BCI is to translate high-level requests from the user into control commands for the FRIEND II system. In the current application, the BCI is used to navigate a menu system and to select commands such as pouring a beverage into a glass. The low-level control of the test platform, the rehabilitation robot FRIEND II, is executed by the control architecture MASSiVE, which in turn is served by a planning instance, an environment model and a set of sensors (e.g., machine vision) and actors. The BCI is introduced as a step towards the goal of providing disabled users with at least 1.5 hours independence from care givers.

Evaluation of the Bremen SSVEP based BCI in real world conditions

A brain-computer interface (BCI) provides the possibility to translate brain neural activity patterns into control commands without users movement. The brain activity is most commonly measured non-invasively via standard electroencephalography (EEG), i.e., with electrodes placed on the surface of the scalp. In this article, we evaluate a BCI system based on steady-state visual evoked potentials (SSVEPs) in real world conditions. Although the performance of this type of BCI has already been proved by several research groups with healthy users in laboratory settings assisted by scientific researchers, there are still many difficulties in changing from demonstration systems to practical BCIs. The Bremen-BCI was evaluated in this case study with 37 naive subjects (without any SSVEP-BCI experience), including 8 handicapped users, at the international rehabilitation fair RehaCare2008. In spite of unsuitable environment conditions on the fair, the spelling tasks were successfully completed by 32 participants with a mean accuracy of over 92% and an average information transfer rate (ITR) of 22.6[bits/min]. No significant dependency of the physical disability of participants on the ITR could be observed.

A step forward in manual welding: demonstration of augmented reality helmet

A new welding helmet for the manual welding process has been developed. The welders working conditions are improved by augmenting the visual information before and during welding. The image is improved by providing a better view of the working area. An online quality assistant is available during welding, suggesting the correction of the guns position or pointing out welding errors, by analyzing the electrical welding parameters. An assembly advisor will suggest the assembly sequence, by displaying the type and the position of the following piece into the actual ensemble. In addition, an available online documentation of the welding process gives an opportunity to reduce the effort of post process quality assurance which often uses expensive X-ray investigations.

Brain-computer interface using water-based electrodes.

Current brain-computer interfaces (BCIs) that make use of EEG acquisition techniques require unpleasant electrode gel causing skin abrasion during the standard preparation procedure. Electrodes that require tap water instead of electrolytic electrode gel would make both daily setup and clean up much faster, easier and comfortable. This paper presents the results from ten subjects that controlled an SSVEP-based BCI speller system using two EEG sensor modalities: water-based and gel-based surface electrodes. Subjects performed in copy spelling mode using conventional gel-based electrodes and water-based electrodes with a mean information transfer rate (ITR) of 29.68 ± 14.088 bit min(-1) and of 26.56 ± 9.224 bit min(-1), respectively. A paired t-test failed to reveal significant differences in the information transfer rates and accuracies of using gel- or water-based electrodes for EEG acquisition. This promising result confirms the operational readiness of water-based electrodes for BCI applications.

Impact of Frequency Selection on LCD Screens for SSVEP Based Brain-Computer Interfaces

In this work, the high impact of appropriate selection of visual stimuli on liquid crystal displays (LCDs) used for the brain-computer interfaces (BCIs) based on the Steady-State Visual Evoked Potentials (SSVEPs) has been confirmed. The number of suitable frequencies on the standard LCD monitor is limited due to the vertical refresh rate of 60Hz and the number of simultaneously used stimuli. Two sets of frequencies have been compared among each other during the on-line spelling task with the Bremen-BCI system in the study with 10 healthy subjects. This work is meaningful for the practical design of LCD based BCIs. In this study, appropriate selection of visual stimuli results in a 40% change in the BCI literacy under otherwise equal conditions.