Awards

IEEE Systems, Man, and Cybernetics Society Conference 2018 Franklin V. Taylor Memorial Award - the best oral presentation and paper - "A Dictionary Driven Mental Typewriter Based on Code-Modulated Visual Evoked Potentials (cVEP)".

The Brain Products MoBI Award 2017 - excellence in the field of Mobile Brain/Body Imaging research - 3rd Place with "SSVEP-Based BCI in a Smart Home Scenario" submission.

The MDPI Brain Sciences 2019 Best Paper Award This paper was nominated by the Editor-in-Chief and the editorial office, was the most cited in 2019: "Brain–computer interface spellers: A review".

Year 2023

Tiago H. Falk, Christoph Guger, and Ivan Volosyak. "Brain–Computer Interfaces: Recent Advances, Challenges, and Future Directions" Handbook of Human-Machine Systems

DOI: 10.1002/9781119863663.ch2

Book chapter on Recent Advances, Challenges, and Future Directions of Brain–Computer Interfaces.
Ivan Volosyak, Foluke Adepoju, Piotr Stawicki, Paul Rulffs, Atilla Cantürk, and Lisa Henke. "Gender Influence on cVEP-based BCI Performance" Rojas I., Joya G., Catala A. (eds) Advances in Computational Intelligence. IWANN 2023. Lecture Notes in Computer Science 2023

DOI: 10.1007/978-3-031-43078-7_48

A Brain-Computer Interface (BCI) is a technical system that creates a direct communication pathway between the human brain and an external device, such as a computer, without generally necessitating any physical movement. BCIs use various methods to detect and interpret brain activity, the most common being electroencephalography (EEG). BCIs can be beneficial for people with disabilities since they provide an alternative communication and control method that can extend and replace traditional means, such as speech or muscular movements. This paper investigates performance differences in code-modulated visual evoked potentials (cVEP) based BCI system between subjects of different gender identities. In this regard, the cVEP-based spelling interface with four targets was tested between two gender groups - 18 females and 18 males each, with ages ranging from 20 to 39 years. Three different spelling tasks were performed - writing of two command-balanced words and a pangram sentence, and cVEP stimuli were rendered on a monitor with a vertical refresh rate of 240 Hz. Both groups (female and male) successfully completed all spelling tasks, achieving for the pangram task, a mean information transfer rate (ITR) of 29.38 bits per minute (bpm) and 28.09 bpm, respectively. Although the difference was not statistically significant for the pangram task, some recognizable differences were observed for the command-balanced tasks. Consequently, a trend (rather than a substantial difference) was realized between the male and female groups’ performance in the pangram task. Regarding the level of annoyance, subjects from both groups rated similar results on the visual stimulation setup.
Lisa Henke, Paul Rulffs, Foluke Adepoju, Piotr Stawicki, Atilla Cantürk, and Ivan Volosyak. "Investigating the Influence of Background Music on the Performance of a cVEP-based BCI." In 2023 IEEE International Conference on Systems, Man and Cybernetics (SMC), pp. 1104-1109, IEEE, 2023.

DOI: 10.1109/SMC53992.2023.10394503

Brain-computer interfaces (BCIs) like e.g. different types of EEG-based BCI spellers (up to date the most common BCI applications) allow new methods of control and interaction with computers and machines. The impact of background music and noise on user’s performance (information transfer rate - ITR and accuracy) has already been investigated for different types of spellers, and usually led to a distractive, decreasing effect on the BCI performance, though there is always room for improving the subjective user experience. In this study, 11 participants used a cVEP-based BCI to perform two spelling tasks “BCI AND MUSIC” and “CONTRARY”, while listening via headphones to a standard instrumental song, a self-chosen instrumental song (“own music”), or to noise conditions: “no music” and “white noise”. Objective factors such as the blood pressure and heart rate were measured after each spelling task, and questionnaires were answered. The BCI accuracy was close to 100% in most cases, while the lowest accuracy was reached while listening to the individually selected, self-chosen music (“own music”). Similarly, the ITR was the highest in case of “no music” and lowest in case of “own music” (which, on the other hand, resulted in a better mood and higher excitement of the participants). Thus, while the general condition of “no music” could be recommended for further BCI experiments, additional research regarding individual factors like musicality or listening habits of BCI participants should be considered.

Year 2022

Piotr Stawicki, Ivan Volosyak. "cVEP Training Data Validation—Towards Optimal Training Set Composition from Multi-Day Data" Brain Sciences 12.2 (2022): 234

DOI: 10.3390/brainsci12020234

This paper investigates the effects of the repetitive block-wise training process on the classification accuracy for a code-modulated visual evoked potentials (cVEP)-based brain–computer interface (BCI). The cVEP-based BCIs are popular thanks to their autocorrelation feature. The cVEP-based stimuli are generated by a specific code pattern, usually the m-sequence, which is phase-shifted between the individual targets. Typically, the cVEP classification requires a subject-specific template (individually created from the user’s own pre-recorded EEG responses to the same stimulus target), which is compared to the incoming electroencephalography (EEG) data, using the correlation algorithms. The amount of the collected user training data determines the accuracy of the system. In this offline study, previously recorded EEG data collected during an online experiment with 10 participants from multiple sessions were used. A template matching target identification, with similar models as the task-related component analysis (TRCA), was used for target classification. The spatial filter was generated by the canonical correlation analysis (CCA). When comparing the training models from one session with the same session’s data (intra-session) and the model from one session with the data from the other session (inter-session), the accuracies were (94.84%, 94.53%) and (76.67%, 77.34%) for intra-sessions and inter-sessions, respectively. In order to investigate the most reliable configuration for accurate classification, the training data blocks from different sessions (days) were compared interchangeably. In the best training set composition, the participants achieved an average accuracy of 82.66% for models based only on two training blocks from two different sessions. Similarly, at least five blocks were necessary for the average accuracy to exceed 90%. The presented method can further improve cVEP-based BCI performance by reusing previously recorded training data.
Jesus Minguillon, Ivan Volosyak, Christoph Guger, Michael Tangermann and Miguel Angel Lopez. "Editorial: Brain-Computer Interfaces: Novel Applications and Interactive Technologies" Frontiers in neuroscience 16 (2022)

DOI: 10.3389/fncom.2022.939202

Editorial on the Research Topic "Brain-Computer Interfaces: Novel Applications and Interactive Technologies".

Year 2021

Piotr Stawicki, Aya Rezeika, Ivan Volosyak. "Effects of Training on BCI Accuracy in SSMVEP-based BCI" Rojas I., Joya G., Catala A. (eds) Advances in Computational Intelligence. IWANN 2021. Lecture Notes in Computer Science, vol 12862. Springer, Cham, 2021

DOI: 10.1007/978-3-030-85099-9_6

This paper investigates the effects of the training process on the classification accuracy for a steady-state motion visual evoked potentials (SSMVEP)-based brain-computer interface (BCI) paradigm. An SSMVEP-based BCI works similar to SSVEP with the main difference that the stimulus is smoothly changing its appearance, with a continuous motion, leading to less user fatigue. Typical SSMVEP classification utilises correlation algorithms to compare the incoming Electroencephalography (EEG) data with a sine-cosine template. To increase the classification performance of BCI algorithms, collecting user training data has been a common practice recently, usually for template-matching detection algorithms. The incoming EEG data are compared with an individually created template from the user’s own pre-recorded EEG response to the stimulus. In this offline study, previously recorded data (3 s of training EEG data), which were collected during an online experiment with 86 participants, were used. Task-related component analysis (TRCA), a state of the art classification method, was modified with the spatial filter W generated by the canonical-correlation analysis (CCA). The TRCA and the sine+cosine templates were compared. The cross paradigm utilisation of the training data was also investigated, e.g. the TRCA model built from SSVEP training data was used to classify the SSMVEP data and vice versa. Results show a significant difference in favour of the usage of the training data over the sine-cosine template for the SSMVEP paradigm classification. A cross-paradigm validation shows promising results (accuracy >70%) for a time window of 1.5 s, similar to the sine+cosine templates. The trained TRCA models achieved an accuracy of 94% and 97% for the SSMVEP and SSVEP paradigms, respectively, in the mentioned time window. Overall, we conclude that training can significantly improve the SSMVEP target classification.

Year 2020

Felix Gembler, Piotr Stawicki, Aya Rezeika, Mihaly Benda, and Ivan Volosyak. "Exploring Session-to-Session Transfer forBrain-Computer Interfaces based onCode-Modulated Visual Evoked Potentials" In 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp.1505-1510. IEEE, 2020

DOI: 10.1109/SMC42975.2020.9282826

Brain-computer interfaces (BCIs) based on code-modulated visual evoked potentials (c-VEPs) hold promise to serve as a fast and reliable hands-free communication tool for people with severe disabilities. A c-VEP BCI application presents flickering target objects (e.g. letters of a keyboard) coded with different time-lags of a code pattern. Template matching methods are used to identify the target of interest. Unfortunately, this approach requires a training session, in which several trials of EEG data are recorded and analysed. Long training sessions are necessary to ensure good signal-to-noise ratios. For the user,these training sessions may be tedious. Especially for patients,who may use the system on a daily basis e. g. for communication,alternative approaches are desirable. This paper investigates the feasibility of session-to-session transfer of EEG templates for c-VEP BCIs, where templates recorded in a previous session are used, so the application could be used instantly. Ten healthy participants went through training and copy-spelling tasks in two experimental sessions (they were scheduled two weeks apart). In the second session, the templates recorded in the first session were used. Eight participants yielded good results with the session-to-session transfer approach with accuracies of 97.1%and information transfer rates of 85.7 bit/min on average. For these participants, the results were not significantly different from the values achieved using the standard approach (training in the same session). For two participants, however, the system was not controllable with the priorly recorded templates. The results demonstrate that for most users daily recalibration is not required.
Felix W. Gembler, Mihaly Benda, Aya Rezeika, Piotr R. Stawicki, and Ivan Volosyak. "Asynchronous c-VEP communication tools—efficiency comparison of low-target, multi-target and dictionary-assisted BCI spellers" Scientific Reports

DOI: 10.1038/s41598-020-74143-4

Keyboards and smartphones allow users to express their thoughts freely via manual control. Hands-free communication can be realized with brain-computer interfaces (BCIs) based on code-modulated visual evoked potentials (c-VEPs). Various variations of such spellers have been developed: Low-target systems, multi-target systems and systems with dictionary support. In general, it is not clear which kinds of systems are optimal in terms of reliability, speed, cognitive load, and visual load. The presented study investigates the feasibility of different speller variations. 58 users tested a 4-target speller and a 32-target speller with and without dictionary functionality. For classification, multiple individualized spatial filters were generated via canonical correlation analysis (CCA). We used an asynchronous implementation allowing non-control state, thus aiming for high accuracy rather than speed. All users were able to control the tested spellers. Interestingly, no significant differences in accuracy were found: 94.4%, 95.5% and 94.0% for 4-target spelling, 32-target spelling, and dictionary-assisted 32-target spelling. The mean ITRs were highest for the 32-target interface: 45.2, 96.9 and 88.9 bit/min. The output speed in characters per minute, was highest in dictionary-assisted spelling: 8.2, 19.5 and 31.6 characters/min. According to questionnaire results, 86% of the participants preferred the 32-target speller over the 4-target speller.
Piotr Stawicki and Ivan Volosyak. "Comparison of Modern Highly Interactive Flicker-Free Steady State Motion Visual Evoked Potentials for Practical Brain–Computer Interfaces" Brain Sciences 10, no. 10 (2020): 686.

DOI: 10.3390/brainsci10100686

Motion-based visual evoked potentials (mVEP) is a new emerging trend in the field of steady-state visual evoked potentials (SSVEP)-based brain–computer interfaces (BCI). In this paper, we introduce different movement-based stimulus patterns (steady-state motion visual evoked potentials—SSMVEP), without employing the typical flickering. The tested movement patterns for the visual stimuli included a pendulum-like movement, a flipping illusion, a checkerboard pulsation, checkerboard inverse arc pulsations, and reverse arc rotations, all with a spelling task consisting of 18 trials. In an online experiment with nine participants, the movement-based BCI systems were evaluated with an online four-target BCI-speller, in which each letter may be selected in three steps (three trials). For classification, the minimum energy combination and a filter bank approach were used. The following frequencies were utilized: 7.06 Hz, 7.50 Hz, 8.00 Hz, and 8.57 Hz, reaching an average accuracy between 97.22% and 100% and an average information transfer rate (ITR) between 15.42 bits/min and 33.92 bits/min. All participants successfully used the SSMVEP-based speller with all types of stimulation pattern. The most successful SSMVEP stimulus was the SSMVEP1 (pendulum-like movement), with the average results reaching 100% accuracy and 33.92 bits/min for the ITR.
Ivan Volosyak, Aya Rezeika, Mihaly Benda, Felix Gembler, and Piotr Stawicki. "Towards solving of the Illiteracy phenomenon for VEP-based brain-computer interfaces" Biomedical Physics & Engineering Express, 6 (2020) 035034.

DOI: 10.1088/2057-1976/ab87e6

Brain-Computer Interface (BCI) systems use brain activity as an input signal and enable communication without requiring bodily movement. This novel technology may help impaired patients and users with disabilities to communicate with their environment. Over the years, researchers investigated the performance of subjects in different BCI paradigms, stating that 15%–30% of BCI users are unable to reach proficiency in using a BCI system and therefore were labelled as BCI illiterates. Recent progress in the BCIs based on the visually evoked potentials (VEPs) necessitates re-considering of this term, as very often all subjects are able to use VEP-based BCI systems. This study examines correlations among BCI performance, personal preferences, and further demographic factors for three different modern visually evoked BCI paradigms: (1) the conventional Steady-State Visual Evoked Potentials (SSVEPs) based on visual stimuli flickering at specific constant frequencies (fVEP), (2) Steady-State motion Visual Evoked Potentials (SSmVEP), and (3) code-modulated Visual Evoked Potentials (cVEP). Demographic parameters, as well as handedness, vision correction, BCI experience, etc., have no significant effect on the performance of VEP-based BCI. Most subjects did not consider the flickering stimuli annoying, only 20 out of a total of 86 participants indicated a change in fatigue during the experiment. 83 subjects were able to successfully finish all spelling tasks with the fVEP speller, with a mean (SD) information transfer rate of 31.87 bit/min (9.83) and an accuracy of 95.28% (5.18), respectively. Compared to that, 80 subjects were able to successfully finish all spelling tasks using SSmVEP, with a mean information transfer rate of 26.44 bit/min (8.04) and an accuracy of 91.10% (6.01), respectively. Finally, all 86 subjects were able to successfully finish all spelling tasks with the cVEP speller, with a mean information transfer rate of 40.23 bit/min (7.63) and an accuracy of 97.83% (3.37).
Chris Brennan, Paul McCullagh, Gaye Lightbody, Leo Galway, Sally McClean, Piotr Stawicki, Felix Gembler, Ivan Volosyak, Elaine Armstrong, and Eileen Thompson. "Performance of a Steady-State Visual Evoked Potential and Eye Gaze Hybrid Brain-Computer Interface on Participants With and Without a Brain Injury." IEEE Transactions on Human-Machine Systems PP(99):1-10, April 2020

DOI: 10.1109/THMS.2020.2983661

The brain–computer interface (BCI) and the tracking of eye gaze provide modalities for human–machine communication and control. In this article, we provide the evaluation of a collaborative BCI and eye gaze approach, known as a hybrid BCI. The combined inputs interact with a virtual environment to provide actuation according to a four-way menu system. The following two approaches are evaluated: first, steady-state visual evoked potential (SSVEP) BCI with on-screen stimulation; second, hybrid BCI, which combined eye gaze and SSVEP for navigation and selection. A study comprises participants without known brain injury (non-BI, N = 30) and participants with known brain injury (BI, N = 14). A total of 29 out of 30 non-BI participants can successfully control the hybrid BCI, while nine out of the 14 BI participants are able to achieve control, as evidenced by task completion. The hybrid BCI provides a mean accuracy of 99.84% in the cohort of non-BI participants and 99.14% in the cohort of BI participants. Information transfer rates are 24.41 bpm in non-BI participants and 15.87 bpm in BI participants. The research goal is to quantify usage of SSVEP and ET approaches in cohorts of non-BI and BI participants. The hybrid is the preferred interaction modality for most participants for both cohorts. When compared to non-BI participants, it is encouraging that nine out of 14 participants with known BI can use the hBCI technology with equivalent accuracy and efficiency, albeit with slower transfer rates.
Mihaly Benda, and Ivan Volosyak. "Comparison of Different Visual Feedback Methods for SSVEP-Based BCIs." Brain Sciences 10, no. 4 (2020): 240.

DOI: 10.3390/brainsci10040240

In this paper we compared different visual feedback methods, informing users about classification progress in a steady-state visual evoked potential (SSVEP)-based brain–computer interface (BCI) speller application. According to results from our previous studies, changes in stimulus size and contrast as online feedback of classification progress have great impact on BCI performance in SSVEP-based spellers. In this experiment we further investigated these effects, and tested a 4-target SSVEP speller interface with a much higher number of subjects. Five different scenarios were used with variations in stimulus size and contrast, “no feedback”, “size increasing”, “size decreasing”, “contrast increasing”, and “contrast decreasing”. With each of the five scenarios, 24 participants had to spell six letter words (at least 18 selections with this three-steps speller). The fastest feedback modalities were different for the users, there was no visual feedback which was generally better than the others. With the used interface, six users achieved significantly better Information Transfer Rates (ITRs) compared to the “no feedback” condition. Their average improvement by using the individually fastest feedback method was 46.52%. This finding is very important for BCI experiments, as by determining the optimal feedback for the user, the speed of the BCI can be improved without impairing the accuracy.
Felix Gembler, Aya Rezeika, Mihaly Benda, and Ivan Volosyak. "Five Shades of Grey: Exploring Quintary m-Sequences for More User-Friendly c-VEP-Based BCIs." Computational intelligence and neuroscience, 2020 (2020).

DOI: 10.1155/2020/7985010

Responsive EEG-based communication systems have been implemented with brain-computer interfaces (BCIs) based on code-modulated visual evoked potentials (c-VEPs). The BCI targets are typically encoded with binary m-sequences because of their autocorrelation property; the digits one and zero correspond to different target colours (usually black and white), which are updated every frame according to the code. While binary flickering patterns enable high communication speeds, they are perceived as annoying by many users. Quintary (base 5) m-sequences, where the five digits correspond to different shades of grey, may yield a more subtle visual stimulation. This study explores two approaches to reduce the flickering sensation: (1) adjusting the flickering speed via refresh rates and (2) applying quintary codes. In this respect, six flickering modalities are tested using an eight-target spelling application: binary patterns and quintary patterns generated with 60, 120, and 240 Hz refresh rates. This study was conducted with 18 nondisabled participants. For all six flickering modalities, a copy-spelling task was conducted. According to questionnaire results, most users favoured the proposed quintary over the binary pattern while achieving similar performance to it (no statistical differences between the patterns were found). Mean accuracies across participants were above 95%, and information transfer rates were above 55 bits/min for all patterns and flickering speeds.

Year 2019

Piotr Stawicki, Aya Rezeika, Abdul Saboor, and Ivan Volosyak. "Investigating Flicker-Free Steady-State Motion Stimuli for VEP-Based BCIs." 2019 E-Health and Bioengineering Conference (EHB), Iasi, Romania, 2019, pp. 1-4.

DOI: 10.1109/EHB47216.2019.8969970

A modern emerging trend in electroencephalography (EEG) - based brain-computer interface (BCI) systems is the implementation of moving objects as visual stimuli to elicit steady- state visual evoked potential (SSVEP) responses. Motion based stimulation has been proven to be less annoying, while at the same time it elicits a comparably strong response as the commonly used SSVEP. In this paper, we present a BCI system that utilizes an oscillation-like (pendulum) behavior for generating steady- state motion visual evoked potentials (SSMVEP), and evaluate its practical use in a four target BCI spelling application. The SSMVEP was investigated with three different frequency sets (Low 3.00 - 4.29 Hz, Mid 6.00 - 8.57 Hz, and High 9.23 - 12.00 Hz) and compared to the standard SSVEP stimulation. In the online experiment seven participants reached average accuracies of 99.0%, 100%, and 98.65% and average information transfer rates of 25.4, 32.5, and 31.05 bits/min for the Low, Mid and High frequency sets, respectively, with the SSMVEP paradigm. The results showed that the presented SSMVEP approach is suitable for BCI application without the typical discomfort for the user. Interestingly, the Low frequency set evoked a relatively strong harmonic response in this study, with performance comparable to the higher frequency sets.
Ivan Volosyak, and Marco Schmidt. "Asynchronous Control of a Spherical Robot by Means of SSVEP-based Brain-Computer Interface." 2019 E-Health and Bioengineering Conference (EHB), Iasi, Romania, 2019, pp. 1-4.

DOI: 10.1109/EHB47216.2019.8969955

Controlling a mobile robot in its environment can be very challenging. There is a large number of different interfaces available to navigate a robot, but they require in many cases expert knowledge in the field of robotics. This work addresses a new approach to control a robotic system with a Brain-Computer Interface (BCI). The key idea is to use the steady state visual evoked potentials (SSVEPs) BCI technology as a robust and performant interface for the control of external devices. In this preliminary study, the BCI is connected to an asynchronous control concept to move the robot in the same room as the operator. It will be shown within this work, how participants control a spherical robot in the laboratory settings. The performance of five healthy participants was evaluated in an online experiment. All participants were able to successfully navigate the Sphero robot out of the laboratory room with a mean information transfer rate (ITR) of 23.67 bpm.
Mihaly Benda, and Ivan Volosyak. "Peak Detection with Online Electroencephalography (EEG) Artifact Removal for Brain–Computer Interface (BCI) Purposes." Brain Sciences 9, no. 12 (2019): 347.

DOI: 10.3390/brainsci9120347

Brain–computer interfaces (BCIs) measure brain activity and translate it to control computer programs or external devices. However, the activity generated by the BCI makes measurements for objective fatigue evaluation very difficult, and the situation is further complicated due to different movement artefacts. The BCI performance could be increased if an online method existed to measure the fatigue objectively and accurately. While BCI-users are moving, a novel automatic online artefact removal technique is used to filter out these movement artefacts. The effects of this filter on BCI performance and mainly on peak frequency detection during BCI use were investigated in this paper. A successful peak alpha frequency measurement can lead to more accurately determining objective user fatigue. Fifteen subjects performed various imaginary and actual movements in separate tasks, while fourteen electroencephalography (EEG) electrodes were used. Afterwards, a steady-state visual evoked potential (SSVEP)-based BCI speller was used, and the users were instructed to perform various movements. An offline curve fitting method was used for alpha peak detection to assess the effect of the artefact filtering. Peak detection was improved by the filter, by finding 10.91% and 9.68% more alpha peaks during simple EEG recordings and BCI use, respectively. As expected, BCI performance deteriorated from movements, and also from artefact removal. Average information transfer rates (ITRs) were 20.27 bit/min, 16.96 bit/min, and 14.14 bit/min for the (1) movement-free, (2) the moving and unfiltered, and (3) the moving and filtered scenarios, respectively.
Aya Rezeika, Felix Gembler, Mihaly Benda, and Ivan Volosyak. "An Offline Study for a Single-Trial ERP Card-Guessing Game." In 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), pp. 228-234. IEEE, 2019.

DOI: 10.1109/SMC.2019.8914087

Event-Related Potential (ERP) is one of the brain signal features which are used in Electroencephalography (EEG) based research and application development, such as Brain-Computer Interface (BCI) applications. Recently, single-trial ERP has been one of the main interests of researchers in the field of BCI and neuroscience. In this paper, an offline study which evaluated the feasibility of developing an online BCI guessing game, based on single-trial ERP, was presented. The objective was to determine the optimal methods and parameters needed to achieve high online classification accuracy and performance. Eight subjects participated in our experiments to collect the data for the offline study. Each subject had to choose one out of six cards displayed on a computer monitor. Three different algorithms of Linear Discriminant Analysis (LDA) were used for classifying the cards into targets and non-targets. Canonical Correlation Analysis (CCA) was applied as a spatial filter for the 16-channel data. Additionally, the data were analysed and classified per channel to deduce which channel reached the higher performance. The results proved the feasibility of the online application. The best performance was achieved with the personalised data and by taking the majority vote of the three LDA algorithms.
Felix Gembler, Mihaly Benda, Abdul Saboor, and Ivan Volosyak. "A multi-target c-VEP-based BCI speller utilizing n-gram word prediction and filter bank classification." In 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), pp.2719-2724. IEEE, 2019.

DOI: 10.1109/SMC.2019.8914235

Brain-Computer Interfaces (BCIs) based on code-modulated visual evoked potentials can be used as hand-free communication tool for severely disabled people. In this paper we propose a filter bank design for c-VEP BCIs based on alpha, beta and gamma sub-bands. The approach was tested using a dictionary driven spelling application utilizing flexible time-windows. The graphical user interface offers word suggestions that are updated after each selection. The system was tested with 18 healthy participants. Performance of a word and a sentence spelling task was analyzed. Remarkably, in the word spelling task, all participants reached 100 % accuracy. In the sentence spelling task the mean accuracy was still extremely high (97 %). Furthermore, to assess the speed of the system, information transfer rate (ITR) and output characters per minute (OCM) were calculated. Mean ITRs of 149.3 bpm and 93.1 bpm were reached in word and sentence spelling; the mean OCM was 29.9 chars/min and 32.1 chars/min.
Elena Marx, Mihaly Benda, and Ivan Volosyak. "Optimal Electrode Positions for an SSVEP-based BCI." In 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), pp. 2731-2736. IEEE, 2019.

DOI: 10.1109/SMC.2019.8914280

In this paper, the performance of a steady-state visually evoked potential (SSVEP)-based brain-computer interface (BCI) was evaluated after reducing the number of electroencephalography (EEG) electrodes used for recording. Our aim was the comparison of the performance using a different number of electrodes, as well as determining the best electrode locations. The main benefit of determining the most efficient electrode sites can be the shortening of the preparation time needed for the setup of the BCI system. The performance of the BCI was measured with a different number of EEG electrodes reduced from initially sixteen to six electrodes as the intermediate step, and finally to four electrodes. Seventeen subjects participated in this study, seven were male and ten female. The mean ITRs were 27.50 bit/min, 24.09 bit/min, and 23.23 bit/min for sixteen, six and four EEG electrodes, respectively. However, not all users managed to use the system with less electrodes, as one user did not manage to control the system with six electrodes, and four of the seventeen users were not able to finish the spelling tasks with four electrodes. With a reduced number of electrodes, a high accuracy can be achieved while retaining a fair spelling speed.
Michael Adams, Mihaly Benda, Abdul Saboor, André Frank Krause, Aya Rezeika, Felix Gembler, Piotr Stawicki, Marc Hesse, Kai Essig, Sadok Ben-Salem, Zahidul Islam, Arne Vogelsang, Thorsten Jungeblut, Ulrich Ruckert, and Ivan Volosyak. "Towards an SSVEP-BCI Controlled Smart Home." In 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), pp. 2737-2742. IEEE, 2019.

DOI: 10.1109/SMC.2019.8914668

Brain-Computer Interfaces (BCIs) based on Steady-State Visually Evoked Potentials (SSVEPs) can be used as hand-free control device. To utilize this control method in a real life scenario, we created a system in which a smart home is controlled by BCI. Six devices in the smart home environment could be controlled with the BCI system: The entrance door, the wardrobe, the kitchens’ worktop and drawers, the light system of all the rooms and a guide light. In the presented paper, the visual stimuli for the BCI were placed at multiple screens in the smart home (placed at different locations such as the kitchen and the living room). The processing was done on one computer, located in the living room. The placement of the visual stimuli corresponded to the actuators that were controlled, e.g. the kitchen drawers were linked to the stimuli displayed in the kitchen. An online experiment was conducted where participants went through a scenario consisting of thirteen SSVEP-BCI selections in total. Eight healthy participants took part in the experiments. For BCI signal acquisition, a mobile EEG amplifier was used. Participants walked freely around the rooms during the experiment. An average accuracy of 81 % was achieved, which suggests that the SSVEP-system is suitable to control the external devices in the smart home, and that the system can be expanded to involve more actuators.
Liza Psotta, Aya Rezeika, Ivan Volosyak. "Investigating the Influence of Background Music on the Performance of an SSVEP-based BCI." In 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), pp. 4187-4193. IEEE, 2019.

DOI: 10.1109/SMC.2019.8913855

Brain-computer interfaces (BCIs) measure brain activity and can be used by impaired patients to close the gap to the real world. In BCI applications based on steady-state visual evoked potentials (SSVEPs), the user focuses on stimuli with different frequencies. During the last decades, the effect of background music on the cognitive performance has been discussed controversially in several studies. This study investigated the influence of background music on the performance of an SSVEP-based BCI speller based on objective (ITR, accuracy, and vital parameters) and subjective measures (familiarity, excitement, mood, valence, and support). The experiments were performed with 18 healthy participants (age 25.17± 4.4 years, eleven females) and comprised a control condition without music, one with white noise, and four conditions with “exciting” and “relaxing” pre-selected and self-chosen music. While the ITR decreased for the noise and music conditions compared to the one without music, an accuracy increase was shown in the white noise and “exciting” self-chosen music condition. The physiological parameters and subjective opinions did not necessarily match the achieved performances. Excitement, mood, and other factors including familiarity of the music and the underlying musical structure were identified as having an influence on the performance values. In sum, this study shows and discusses both positive and negative effects of background music on the BCI performance and prepares further investigations concerning the possible application of BCI systems in noisy environments.
Felix Gembler, Piotr Stawicki, Abdul Saboor, and Ivan Volosyak. "Dynamic time window mechanism for time synchronous VEP-based BCIs—Performance evaluation with a dictionary-supported BCI speller employing SSVEP and c-VEP." PloS one 14, no. 6 (2019): e0218177.

DOI: 10.1371/journal.pone.0218177

Brain-Computer Interfaces (BCIs) based on visual evoked potentials (VEPs) allow high communication speeds and accuracies. The fastest speeds can be achieved if targets are identified in a synchronous way (i.e., after a pre-set time period the system will produce a command output). The duration a target needs to be fixated on until the system classifies an output command affects the overall system performance. Hence, extracting a data window dedicated for the classification is of critical importance for VEP-based BCIs. Secondly, unintentional fixation on a target could easily lead to its selection. For the practical usability of BCI applications it is desirable to distinguish between intentional and unintentional fixations. This can be achieved by using threshold-based target identification methods. The study explores personalized dynamic classification time windows for threshold-based time synchronous VEP BCIs. The proposed techniques were tested employing the SSVEP and the c-VEP paradigm. Spelling performance was evaluated using an 8-target dictionary-supported BCI utilizing an n-gram word prediction model. The performance of twelve healthy participants was assessed with the information transfer rate (ITR) and accuracy. All participants completed sentence spelling tasks, reaching average accuracies of 94% and 96.3% for the c-VEP and the SSVEP paradigm, respectively. Average ITRs around 57 bpm were achieved for both paradigms.
Felix Gembler, and Ivan Volosyak. "A Novel Dictionary-Driven Mental Spelling Application Based on Code-Modulated Visual Evoked Potentials." Computers, 8, no. 2 (2019): 33.

DOI: 10.3390/computers8020033

Brain-computer interfaces (BCIs) based on code-modulated visual evoked potentials (c-VEPs) typically utilize a synchronous approach to identify targets (i.e., after preset time periods the system produces command outputs). Hence, users have only a limited amount of time to fixate a desired target. This hinders the usage of more complex interfaces, as these require the BCI to distinguish between intentional and unintentional fixations. In this article, we investigate a dynamic sliding window mechanism as well as the implementation of software-based stimulus synchronization to enable the threshold-based target identification for the c-VEP paradigm. To further improve the usability of the system, an ensemble-based classification strategy was investigated. In addition, a software-based approach for stimulus on-set determination is proposed, which allows for an easier setup of the system, as it reduces additional hardware dependencies. The methods were tested with an eight-target spelling application utilizing an n-gram word prediction model. The performance of eighteen participants without disabilities was tested; all participants completed word- and sentence spelling tasks using the c-VEP BCI with a mean information transfer rate (ITR) of 75.7 and 57.8 bpm, respectively.
Piotr Stawicki, Felix Gembler, Roland Grichnik, and Ivan Volosyak. "Remote Steering of a Mobile Robotic Car by Means of VR-Based SSVEP BCI." Rojas I. et al (eds) Advances in Computational Intelligence. IWANN 2019. Lecture Notes in Computer Science, vol 11506. Springer, Cham, 2019.

DOI: 10.1007/978-3-030-20521-8_34

Brain-computer interface (BCI) technology, including applications based on the steady-state visual evoked potentials (SSVEPs) have proven to provide reliable and accurate control. In this paper, we present and evaluate remote steering of a previously developed and successfully tested mobile robotic car (MRC) utilizing the SSVEP-based BCI system.The visual stimulations were presented inside the head-mounted virtual reality (VR) glasses, here, the Oculus Go. The live video feedback from the MRCs point of view was displayed inside the custom made app of the VR environment. The three visual stimuli were located on both sides and above the video stream of the MRC camera.The task of this study was to steer the MRC through a 8 meter long path (in the real world) with 6 turns. Seven participants took part in the experiment reaching on average an accuracy of 98.1 (standard deviation: 5.04) %, an information transfer rate (ITR) of 10.71 (2.78) bits/min with an average command classification time of 3.95 (2.3) seconds. For classification, the minimum energy combination method (MEC) with 16 EEG electrodes as well as a filter bank decomposing method were utilized. All participants successfully completed the task, almost all subjects stated that the presented VR-based SSVEP-BCI was a highly immersive experience.
Felix Gembler, Piotr Stawicki, Aya Rezeika, and Ivan Volosyak. "A Comparison of cVEP-Based BCI-Performance Between Different Age Groups" Rojas I. et al (eds) Advances in Computational Intelligence. IWANN 2019. Lecture Notes in Computer Science, vol 11506. Springer, Cham, 2019.

DOI: 10.1007/978-3-030-20521-8_33

Persons who need assistive technologies to communicate with the relatives, for example amyotrophic lateral sclerosis (ALS) patients, could benefit from Brain-Computer Interface (BCI) technology if it is used alternatively or in addition to established communication tools. BCIs based on visual evoked potentials (VEPs) have shown high system speeds in many studies. However, some major issues need to be addressed: On the one hand, the strength of VEP responses varies across subjects. Especially age-related performance differences have been covered in several studies and need to be investigated further. On the other hand, the stimuli used to evoke the VEP response, are considered as annoying by many people.
The paper investigates the subjective level of annoyance in different age groups for different flickering rates as well as age-related performance differences in cVEP based BCIs. In this regard, the cVEP-based eight target spelling interface was tested with two age groups (13 subjects each, ranging from 20 to 28 years and 62 to 83 years). Typically, 60 Hz monitor refresh rate is used to generate the cVEP stimuli. Here, three different flickering speeds were tested (m-sequences generated using refresh rates of 30, 60 and 120 Hz for stimuli presentation).
The mean ITR of the elderly age group was 42.03, 45.32 and 45.75 bits per minute(bpm) while the young group achieved an ITR of 53.09, 64.01 and 72.92 bpm for the 30, 60 and 120 Hz setups. The difference was significant for the faster flickering setups (60 and 120 Hz). Hence, our results show that elderly people have slightly worse BCI performance in terms of information transfer rate (ITR). Regarding the level of annoyance, subjects from both age groups preferred the 120 Hz setup which offered a more subtle visual stimulation.
Mihaly Benda, Felix Gembler, Piotr Stawicki, Sadok Ben-Salem, Zahidul Islam, Arne Vogelsang, and Ivan Volosyak. "Custom-Made Monitor For Easy High-Frequency SSVEP Stimulation." Rojas I. et al (eds) Advances in Computational Intelligence. IWANN 2019. Lecture Notes in Computer Science, vol 11506. Springer, Cham, 2019.

DOI: 10.1007/978-3-030-20521-8_32

In this paper, we present and evaluate a special Custom-Made Computer Display (CMCD) with additional background light, which is separately controlled in order to create visual stimuli for Brain-Computer Interfaces (BCIs). While the monitor itself is working with a 60 Hz refresh rate, twelve strips of LED lights that are placed in between the backlight allow for a higher frequency flickering than any flickering object on a conventional screen. The goal of this study is to evaluate the effectiveness of this CMCD, which is mostly based on a change in intensity rather than in contrast. Therefore, we compared the responses to both types of flickering at different frequency ranges, while also measuring the speed and accuracy of the BCI with short spelling tasks. The CMCD LED illumination yielded slightly superior performance in terms of offline ITR in comparison to the standard flickering.
Abdul Saboor, Mihaly Benda, Felix Gembler, and Ivan Volosyak. "Word prediction support model for SSVEP-based BCI web speller." Rojas I. et al (eds) Advances in Computational Intelligence. IWANN 2019. Lecture Notes in Computer Science, vol 11506. Springer, Cham, 2019.

DOI: 10.1007/978-3-030-20521-8_36

Steady state visual evoked potential (SSVEP) based BCI-systems are dependent on the brain signals which are elicited in response to a visual stimuli presented to the user. The spelling systems are very popular applications for the SSVEP-based BCI. In this paper, we are presenting a web-based speller supported with word prediction. The emphasis of the study was on two main points: (1) provide a dictionary based web speller which could also be accessed through a widely available web browsers; (2) increase the accuracy and speed of the SSVEP-based BCI speller. Using the concept of three step speller, a web interface was developed which provided additional support of word predictions based on characters typed and the cooccurrence of the previously typed word. The architectural pattern for the word prediction support model was based on MVC (model-view-controller). The AJAX call was placed form the web speller interface to access the database using Java Servlet and Java Beans. The relational database for the word prediction was derived from the Leipzig corpora collection. The developed system was tested with eleven healthy subjects. An average accuracy of 92.5 % and ITR of 18.8 bits/min were achieved. The results showed that word suggestions can increase the typing speed and accuracy of the web speller.
Roland Grichnik, Mihaly Benda, and Ivan Volosyak. "An SSVEP-Based Virtual Reality Hybrid BCI with Gesture Input." Rojas I. et al (eds) Advances in Computational Intelligence. IWANN 2019. Lecture Notes in Computer Science, vol 11506. Springer, Cham, 2019.

DOI: 10.1007/978-3-030-20521-8_35

Brain-Computer Interfaces (BCIs) using Steady-State Visual Evoked Potentials have been proven to work with many different display technologies for visual stimulation. The recent advent of consumer grade Virtual Reality (VR) Head-Mounted Devices (VR-HMDs) has made research in the area of VR-based BCIs more accessible than ever - yet the possibilities of such systems still have to be tested. In this paper, we present a BCI using a well-studied 3-step spelling interface converted into a Virtual Environment (VE). The Oculus Rift CV1 VR-HMD used in this study also provides motion tracking capability, which was used to implement a novel hybrid BCI utilizing gesture input. The interface consisted of three flickering boxes on a virtual screen in the VE for typing letters. Head shake gestures were used to intuitively trigger “Delete/Back” commands. A g.tec g.USBamp amplifier was used to record and filter the signal of eight electrodes mounted in an electroencephalography cap. The Minimum Energy Combination (MEC) method was used to classify commands in real time. Eighteen participants successfully performed seven spelling tasks each, reaching an accuracy of 91.11±10.26% (mean±Standard Deviation, SD) and an Information Transfer Rate of 23.56±7.54 bit/minute (mean±SD). Questionnaires filled out before and after the experiment show that most participants enjoyed the VR BCI experience and found the gesture input very natural. Future studies could expand the input mechanism by adding more head gestures, e.g. pecking, nodding or circling to control intuitively related software tasks.

Year 2018

Abdul Saboor, Mihaly Benda, Aya Rezeika, Roland Grichnik, Felix Gembler, Piotr Stawicki, and Ivan Volosyak. "Mesh of SSVEP-based BCI and Eye-tracker for use of higher frequency stimuli and lower number of EEG channels." In 2018 International Conference on Frontiers of Information Technology (FIT) (pp. 99-104). IEEE, 2018.

DOI: 10.1109/FIT.2018.00025

Steady-State Visually Evoked Potential (SSVEP) is widely used in Brain-Computer Interface (BCI) systems. However, the use of flickering stimuli at low frequencies causes visual fatigue for users. The visual fatigue increases when multiple stimuli are used, flickering at different frequencies. To overcome this problem, this paper present a solution by using single high frequency (30 Hz) stimulus interface with 30 targets. In the proposed system, the initial recognition of the target was achieved through the eye gaze position using an eye-tracker, and the selection/classification of command was provided by EEG. As only a single stimulating frequency was used (i.e. 30 Hz), thus, only two EEG electrodes (at positions Pz and Oz) were used along with g.USBamp amplifier. This reduced the setup-time for the preparation of the users. A new calibration technique for the eye tracker was designed and developed, which resulted in better eye gaze tracking. The results showed that higher classification accuracy can be achieved by using the mesh of SSVEP-based BCI system and eye-tracker as compared to the SSVEP-based BCI system.
Piotr Stawicki, Felix Gembler and Ivan Volosyak. "Design and Customization of SSVEP-Based BCI Applications Aimed for Elderly People." Brain–Computer Interfaces Handbook: Technological and Theoretical Advances, p.133. 2018.

In this chapter, we discuss the parameter setup for steady-state visually evoked potential (SSVEP)-based brain-computer interface (BCI) systems aimed for elderly people. In this respect, the reader is guided through the key features of SSVEP-based BCI applications. In detail, we discuss the appropriate choice of stimulation frequencies, classification time windows, and the number of selectable commands. Additionally, we list design choices for the graphical user interfaces geared to the needs of users of advanced age. The chapter summarizes results of our previous research, where age-related differences in BCI performance were investigated.
Read more...
Aya Rezeika, Mihaly Benda, Piotr Stawicki, Felix Gembler, Abdul Saboor, and Ivan Volosyak. "Brain–computer interface spellers: A review." Brain sciences, 8, no. 4 (2018): 57.

DOI: 10.3390/brainsci8040057

A Brain–Computer Interface (BCI) provides a novel non-muscular communication method via brain signals. A BCI-speller can be considered as one of the first published BCI applications and has opened the gate for many advances in the field. Although many BCI-spellers have been developed during the last few decades, to our knowledge, no reviews have described the different spellers proposed and studied in this vital field. The presented speller systems are categorized according to major BCI paradigms: P300, steady-state visual evoked potential (SSVEP), and motor imagery (MI). Different BCI paradigms require specific electroencephalogram (EEG) signal features and lead to the development of appropriate Graphical User Interfaces (GUIs). The purpose of this review is to consolidate the most successful BCI-spellers published since 2010, while mentioning some other older systems which were built explicitly for spelling purposes. We aim to assist researchers and concerned individuals in the field by illustrating the highlights of different spellers and presenting them in one review. It is almost impossible to carry out an objective comparison between different spellers, as each has its variables, parameters, and conditions. However, the gathered information and the provided taxonomy about different BCI-spellers can be helpful, as it could identify suitable systems for first-hand users, as well as opportunities of development and learning from previous studies for BCI researchers.
Felix Gembler, Piotr Stawicki, Abdul Saboor, Mihaly Benda, Roland Grichnik, Aya Rezeika, and Ivan Volosyak. "A Dictionary Driven Mental Typewriter Based on Code-Modulated Visual Evoked Potentials (cVEP)." In 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC) (pp. 619-624). IEEE, 2018.

DOI: 10.1109/SMC.2018.00114

Brain-computer interfaces (BCIs) based on code-modulated potentials (cVEPs) identify a target usually in the synchronous way (i.e. after a preset time period the system will produce a command output). Hence, users have only a limited amount of time to fixate a desired target. For the practical usability of BCI spellers it is important to distinguish between intentional and unintentional fixations. In this paper we propose the use of threshold-based target identification methods for the cVEP paradigm. These methods were tested with a dictionary driven spelling application utilizing eight flashing targets. In this respect, an n-gram word prediction model was implemented. The performance of ten healthy participants was evaluated in an online experiment. All participants completed different German sentences using the cVEP BCI with a mean information transfer rate (ITR) of 31.08 bpm.
Piotr Stawicki, Felix Gembler, Cheuk Yin Chan, Mihaly Benda, Aya Rezeika, Abdul Saboor, Roland Grichnik, and Ivan Volosyak. "Investigating Spatial Awareness within an SSVEP-based BCI in Virtual Reality." In 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 615-618. IEEE, 2018.

DOI: 10.1109/SMC.2018.00113

Brain-Computer Interfaces (BCIs) allow users to communicate and to control their environment without the use of peripheral muscles. One of the commonly used BCI paradigms is called steady state visual evoked potentials (SSVEPs). It is controlled by brain signals induced through gazing at a constantly flickering light source. In this article, a VR-based SSVEP-controlled simulation is presented and evaluated, in comparison to the standard desktop based version. Three control classes were used to control the application. The experimental task was to navigate (in first person view) through a virtual maze and reach the desired destination (the optimal path required at least 26 commands). Participants performed the task twice, using either a head mounted display (HMD), or the laptop screen, to compare the paths and investigate the spatial awareness with the HMD. During the first run, the participants needed to explore the maze (different corridors and doors on 3 levels) in order to reach the destination (a teleporter room). There were three commands available for the user: "Turn left", "Forward", and "Turn right". All participants were able to complete both versions (HMD and laptop screen). On average, the number of commands needed to complete the task in the online experiment was 51 and 62 for the HMD and laptop screen, respectively. The average time of the task for the HMD scenario was 287.16 seconds and for the laptop 435.79 seconds, almost 51.75% higher. We found, that the participants achieved a better spatial awareness with the HMD setup.
Piotr Stawicki, Felix Gembler, Cheuk Yin Chan, Mihaly Benda, Aya Rezeika, Abdul Saboor, Roland Grichnik, and Ivan Volosyak. "SSVEP-based BCI in Virtual Reality - Control of a Vacuum Cleaner Robot." In 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 534-537. IEEE, 2018.

DOI: 10.1109/SMC.2018.00749

Brain-Computer Interfaces (BCIs) allow communication and control of the environment without the use of peripheral muscles. One of the standard BCI paradigms is based on steady state visual evoked potentials (SSVEPs), brain signals induced by gazing at a constantly flickering target. In this article, a VR SSVEP-based steering simulation is presented and evaluated in comparison to a standard desktop version. Three control classes were used to control the application. The experimental task was to steer a virtual vacuum robot and collect 10 dust piles (for this, at least 31 command classifications were required). Participants were instructed to complete the task twice, using a head mounted display (HMD) and the laptop screen for visual stimulation. All participants were able to complete the task in both scenarios. Mean accuracies of 98.91% and 97.48% and mean ITRs of 23.96 and 20.71 bits/min were achieved for the HMD and desktop control, respectively. On average, the number of commands needed to complete the task in the online experiment was 32.00 and 32.75, for the HMD and desktop scenario, respectively.
Mihaly Benda, Piotr Stawicki, Felix Gembler, Aya Rezeika, Abdul Saboor, and Ivan Volosyak. "SSVEP-Based BCI Performance and Objective Fatigue Under Different Background Conditions." In 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 1116-1121. IEEE, 2018.

DOI: 10.1109/SMC.2018.00197

In this paper the influence of different backgrounds was investigated on SSVEP-based BCI performance, with a focus on measuring objective user fatigue. We tested three different backgrounds: a black screen, white noise, and a video, with a BCI spelling application (in which four distinct frequencies were used). We measured information transfer rate (ITR), accuracy, and several parameters which could indicate user fatigue levels. The data were recorded with EEG. The level of comfort before and after the experiment, as well as the subjective level of fatigue were assessed using questionnaires, while the objective evaluation was done using the measured indexes. Eight healthy participants were tested. With the used objective fatigue evaluation method, no significant differences were found between the different background scenarios. Evaluating the study as a whole showed significantly decreased alpha-band activity (p = 0.03) at the end and a significantly increased subjective user fatigue. This experiment was conducted to investigate the level of fatigue caused by SSVEP-based BCIs in noisy environments.
Abdul Saboor, Felix Gembler, Mihaly Benda, Piotr Stawicki, Aya Rezeika, Roland Grichnik, and Ivan Volosyak. "A Browser-Driven SSVEP-Based BCI Web Speller." In 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 625-630. IEEE, 2018.

DOI: 10.1109/SMC.2018.00115

Brain-Computer Interface (BCI) provides a non-muscular communication by using the brain signals. During last decades, the BCI-systems provided various graphical user interfaces, especially the speller interfaces. Efforts had been made to increase the speller speed and user friendliness of the system. In this paper, we are introducing a browser-driven SSVEP-based BCI web speller (accessible at: http://bci-lab.hochschule-rhein-waal.de/en/speller/). This web speller can be used with the help of major existing web browsers. Thus, all the international researchers working in the field of BCI can access this web speller online free of charge, and they can run this speller using their own classifier applications. In the presented three-step web speller, the user can select a desired character by going through three different steps of the web interface. The browser-driven BCI speller was tested in this study by ten subjects, who were asked to spell the words "BCI_LAB" and "KLEVE". All of the subjects were able to perform the spelling tasks, with the mean accuracy of 94.5% and an average information transfer rate (ITR) of 12.7 bits/min.
Aya Rezeika, Mihaly Benda, Piotr Stawicki, Felix Gembler, Abdul Saboor, and Ivan Volosyak. "Surface Electromyographic Control of a Three-Steps Speller Interface." In 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 147-152. IEEE, 2018.

DOI: 10.1109/SMC.2018.00036

Many individuals require Aided Augmentative and Alternative Communication (AAAC) to communicate, especially when traditional AAC, like sign language, is not an option due to some movement impairments. This paper presents a high tech AAAC using Surface Electromyography (sEMG) signals as an input modality for the direct control of a speller presented on a Graphical User Interface (GUI). The GUI displays alphabetical letters, special characters, and a delete option. The aim of this study is to introduce and examine the performance of a three-steps sEMG-based speller which does not depend on the movement of a system cursor. Seven subjects participated in the experiment to test the spelling system. Each participant had to undergo a familiarization task first, after which the main spelling task took place. Experimental data were recorded and the resulted mean accuracy and information transfer rate (ITR) for the main spelling task were 89.10% and 55.10 bits/min, respectively, at an average spelling speed of 10.29 char/min. Results and user's feedback also indicated that the spelling performance could be further enhanced through training and the regular use of the speller.
Aya Rezeika, Mihaly Benda, Piotr Stawicki, Felix Gembler, Abdul Saboor, and Ivan Volosyak. "30-Targets Hybrid BNCI Speller Based on SSVEP and EMG." In 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 153-158. IEEE, 2018.

DOI: 10.1109/SMC.2018.00037

Brain-Computer Interface (BCI) interprets brain signals, which are measured by an electroencephalogram (EEG), allowing people to communicate without the need for any muscular movement. One of the most commonly discussed applications in literature is BCI speller as a communication modality for people with disabilities. In Brain-Neural Computer Interface (BNCI) other bio signals are merged with the brain signals to combine the advantages of both. Consequently, the here-studied hybrid BCI system discusses the parallel usage of a Steady-State Visual Evoked Potential (SSVEP) BCI and surface-electromyographic (sEMG) activity to accomplish a faster performance for a more accurate spelling application. sEMG signal was used for the activation of target selection for an SSVEP-based speller. Eight participants carried out three copy-spelling tasks for each system (six in total) to compare between both paradigms: SSVEP alone and the hybrid speller. Results showed that the hybrid speller can achieve faster performances without affecting the accuracy (mean accuracy 92.37%, 93.75%, and 100%, mean ITR 37.37, 33.41, and 31.05 bits/min), verifying our hypothesis. In addition, participants who experienced difficulties controlling the SSVEP speller were able to control the hybrid system.
Mihaly Benda, Piotr Stawicki, Felix Gembler, Roland Grichnik, Aya Rezeika, Abdul Saboor, and Ivan Volosyak. "Different Feedback Methods For An SSVEP-Based BCI." In 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 1939-1943. IEEE, 2018.

DOI: 10.1109/EMBC.2018.8512622

In this paper we examined different ways to inform the user of the classification progress in our online SSVEP-based BCI speller. Different user feedback was given based on the distance from the classification threshold, separately calculated for each stimulus. We focused on the comparison of the accuracies and spelling times associated with each different feedback type. We tested eight different methods, one without feedback for comparison, and the two paradigms each (an increase and a decrease), for three varying parameters, during an online spelling task. The eighth method was a combination of the best performing feedback modalities. A 28 target speller was used for spelling the same word with different feedback methods. The level of comfort was assessed by the seven healthy participants, using a questionnaire. We found substantial decreases in spelling times; they were reduced to 12-77% of the no-feedback condition spelling times, for each of our subjects, with at least one of the parameters. However, this parameter, as expected, was different for each user. According to the personal fastest feedback methods, a combination of them was also used for spelling. These combined feedback methods usually resulted in a slower spelling than the individual best feedback, but still faster than without any feedback. Overall, the average spelling times with the different feedback methods were: no feedback, 95.09 s, increasing size, 62.94 s, decreasing size, 87.73 s, increasing contrast, 77.80 s, decreasing contrast, 124.37 s, increasing duty-cycle, 134.70 s, and decreasing duty-cycle, 103.77 s.

Year 2017

Felix Gembler, Piotr Stawicki, and Ivan Volosyak. "Suitable Number of Visual Stimuli for SSVEP-Based BCI Spelling Applications." In International Work-Conference on Artificial Neural Networks, pp. 441-452. Springer, Cham, 2017.

DOI: 10.1007/978-3-319-59147-6_38

Steady state visual evoked potentials (SSVEPs)-based Brain-Computer interfaces (BCIs) provide a pathway for re-establishing communication to people with severe disabilities. In the presented study, we compared accuracy and speed of three SSVEP-based BCI spelling applications in order to investigate the influence of the number of visual stimuli on the BCI performance. Three systems with four, six and 28 stimulating frequencies were tested. Ten subjects (one female) participated in this study. The highest ITR achieved in the experiment was 51.77 bpm. It is interesting, that it was achieved with the system based on six flickering targets. Our results confirm that the number of stimuli has high impact on classification accuracy and BCI literacy of SSVEP-based BCIs.
Abdul Saboor, Aya Rezeika, Piotr Stawicki, Felix Gembler, Mihaly Benda, Thomas Grunenberg, and Ivan Volosyak. "SSVEP-based BCI in a smart home scenario." In International Work-Conference on Artificial Neural Networks, pp. 474-485. Springer, Cham, 2017.

DOI: 10.1007/978-3-319-59147-6_41

Steady state visual evoked potentials (SSVEPs)-based Brain-Computer Interfaces (BCIs) can provide hand-free human interaction with the environment. In the presented study, visual stimuli were displayed on Epson Moverio BT-200 augmented reality glasses, which can be easily used in smart homes. QR codes were used to identify the devices to be controlled with the BCI. In order to simulate a real life scenario, participants were instructed to go out of the lab to get a coffee. During this task light switches, elevator and a coffee machine were controlled by focusing on SSVEP stimuli displayed on the smart glasses. An average accuracy of 85.70% was achieved, which suggests that augmented reality may be used together with SSVEP to control external devices.
Piotr Stawicki, Felix Gembler, Aya Rezeika, and Ivan Volosyak. "A novel hybrid mental spelling application based on eye tracking and SSVEP-based BCI." In Brain sciences 7, no. 4 (2017): 35.

DOI: 10.3390/brainsci7040035

Steady state visual evoked potentials (SSVEPs)-based Brain-Computer interfaces (BCIs), as well as eyetracking devices, provide a pathway for re-establishing communication for people with severe disabilities. We fused these control techniques into a novel eyetracking/SSVEP hybrid system, which utilizes eye tracking for initial rough selection and the SSVEP technology for fine target activation. Based on our previous studies, only four stimuli were used for the SSVEP aspect, granting sufficient control for most BCI users. As Eye tracking data is not used for activation of letters, false positives due to inappropriate dwell times are avoided. This novel approach combines the high speed of eye tracking systems and the high classification accuracies of low target SSVEP-based BCIs, leading to an optimal combination of both methods. We evaluated accuracy and speed of the proposed hybrid system with a 30-target spelling application implementing all three control approaches (pure eye tracking, SSVEP and the hybrid system) with 32 participants. Although the highest information transfer rates (ITRs) were achieved with pure eye tracking, a considerable amount of subjects was not able to gain sufficient control over the stand-alone eye-tracking device or the pure SSVEP system (78.13% and 75% of the participants reached reliable control, respectively). In this respect, the proposed hybrid was most universal (over 90% of users achieved reliable control), and outperformed the pure SSVEP system in terms of speed and user friendliness. The presented hybrid system might offer communication to a wider range of users in comparison to the standard techniques.
Ivan Volosyak, Felix Gembler, and Piotr Stawicki. "Age-related differences in SSVEP-based BCI performance." In Neurocomputing 250 (2017): 57-64.

DOI: 10.1016/j.neucom.2016.08.121

Brain–Computer Interface (BCI) systems analyze brain signals to generate control commands for computer applications or external devices. Utilized as alternative communication channel, BCIs have the potential to assist people with severe motor disabilities to interact with their environment and to participate in daily life activities. Handicapped people from all age groups could benefit from such BCI technologies. Although some papers have previously reported slightly worse BCI performance by older subjects, in many studies BCI systems were tested with young subjects only.
In the presented paper age-associated differences in BCI performance were investigated. We compared accuracy and speed of a steady-state visual evoked potential (SSVEP)-based BCI spelling application controlled by participants of two different equally sized age groups. Twenty subjects (eleven female and nine male) participated in this study; each age group consisted of ten subjects, ranging from 19 to 27 years and from 64 to 76 years. Our results confirm that elderly people may have a deteriorated information transfer rate (ITR). The mean (SD) ITR of the young age group was 27.36 (6.50) bit/min while the elderly people achieved a significantly lower ITR of 16.10 (5.90) bit/min. The average time window length associated with the signal classification was usually larger for the participants of advanced age. These findings show that the subject age must be taken into account during the development of SSVEP-based applications.
Piotr Stawicki, Felix Gembler, Abdul Saboor, and Ivan Volosyak. "Comparison of speed, accuracy, and user friendliness between SSVEP-based BCI and eye tracker." In Proceedings of the 7th Graz Brain-Computer Interface Conference 2017: From Vision to Reality, 2017

DOI: 10.3217/978-3-85125-533-1-85

This article intends to compare two rivaling technology tools that could reestablish communication for people with severe disabilities. One of the tested technologies, steady state visual evoked potentials (SSVEPs) based Brain-Computer Interface (BCI), detects patterns in brain activity. Eye-tracking devices, on the other hand, measure the eye position, blinks, saccades, fixation paths, and other eye-specific parameters. Both methods can be used to interpret the user's intent allowing control of spelling applications. Accuracy and speed of these two control methods are compared. A graphical user interface (GUI) with 30 targets (letters of the alphabet and special characters) was developed implementing each of the two technologies. Nine participants (two female) completed the phrase "RHINE WAAL UNIVERSITY" with both technologies. As expected, the achieved ITR with the eye-tracking device was significantly higher (91.8 bpm compared to 38.2 bpm for the SSVEP-based BCI). However, the eye tracking did not work for all of the participants, in this case the SSVEP-based interface can offer an alternative. The optimal interface needs to be customized individually.
Felix Gembler, Piotr Stawicki, and Ivan Volosyak. "How many electrodes are needed for multi-target SSVEP-based BCI control: Exploring the minimum number of signal electrodes for CCA and MEC." In Proceedings of the 7th Graz Brain-Computer Interface Conference 2017: From Vision to Reality, 2017

DOI: 10.3217/978-3-85125-533-1-29

As the SSVEP paradigm (based on steady state visual evoked potentials) requires EEG-measurement, high number of EEG electrodes might be impractical in daily life scenarios because of the time consuming electrode montage. Reducing the number of signal electrodes can shorten preparation time but might compromise signal quality. This paper explores the number of signal electrodes required to achieve sufficient control over multi target SSVEP-based BCI systems. In this respect, two of the most commonly used multi-channel classification methods, the minimum energy combination method (MEC) and the canonical correlation analysis (CCA), are investigated. Data from six healthy subjects recorded during a copy spelling experiment using eight signal electrodes were analyzed off-line. A spelling interface with 30 flickering targets was used. Results for all possible channel combinations were evaluated, revealing that already three electrode channels are sufficient for reliable BCI control.

Year 2016

Felix Gembler, Piotr Stawicki, and Ivan Volosyak. "Exploring the possibilities and limitations of multitarget SSVEP-based BCI applications." In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 1488-1491. IEEE, 2016.

DOI: 10.1109/EMBC.2016.7590991

Steady state visual evoked potentials (SSVEPs) are the brain signals induced by gazing at a constantly flickering target. Frame-based frequency approximation methods can be implemented in order to realize a high number of visual stimuli for SSVEP-based Brain-Computer Interfaces (BCIs) on ordinary computer screens. In this paper, we investigate the possibilities and limitations regarding the number of targets in SSVEP-based BCIs. The BCI-performance of seven healthy subjects was evaluated in an online experiment with six differently sized target matrices. Our results confirm previous observations, according to which BCI accuracy and speed are dependent on the number of simultaneously displayed targets. The peak ITR achieved in the experiment was 130.15 bpm. Interestingly, it was achieved with the 15 target matrix. Generally speaking, the BCI performance dropped with an increasing number of simultaneously displayed targets. Surprisingly, however, one subject even gained control over a system with 84 flickering targets, achieving an accuracy of 91.30%, which verifies that stimulation frequencies separated by less than 0.1 Hz can still be distinguished from each other.
Piotr Stawicki, Felix Gembler, and Ivan Volosyak. "Driving a semiautonomous mobile robotic car controlled by an SSVEP-based BCI." In Computational intelligence and neuroscience, 2016 (2016): 5.

DOI: 10.1155/2016/4909685

Brain-computer interfaces represent a range of acknowledged technologies that translate brain activity into computer commands. The aim of our research is to develop and evaluate a BCI control application for certain assistive technologies that can be used for remote telepresence or remote driving. The communication channel to the target device is based on the steady-state visual evoked potentials. In order to test the control application, a mobile robotic car (MRC) was introduced and a four-class BCI graphical user interface (with live video feedback and stimulation boxes on the same screen) for piloting the MRC was designed. For the purpose of evaluating a potential real-life scenario for such assistive technology, we present a study where 61 subjects steered the MRC through a predetermined route. All 61 subjects were able to control the MRC and finish the experiment (mean time 207.08 s, SD 50.25) with a mean (SD) accuracy and ITR of 93.03% (5.73) and 14.07 bits/min (4.44), respectively. The results show that our proposed SSVEP-based BCI control application is suitable for mobile robots with a shared-control approach. We also did not observe any negative influence of the simultaneous live video feedback and SSVEP stimulation on the performance of the BCI system.
Piotr Stawicki, Felix Gembler, and Ivan Volosyak. "A step towards the solution of the illiteracy phenomena in SSVEP-based bcis." In Вісник Харківського національного технічного університету сільського господарства імені Петра Василенка, 175 (2016): 55-57.

In this paper, we present an adaptive approach for classification of SSVEP-based BCI signals. In a series of studies, we have shown that this method has the potential to solve the problem of so-called BCI illiteracy, when users are not able to successfully operate the system. The maximum duration of a single classification can be up to 16 seconds, but absolutely all of the subjects were able to successfully manage this interface.
Read more...
Piotr Stawicki, Felix Gembler, and Ivan Volosyak. "A User-Friendly Dictionary-Supported SSVEP-based BCI Application." In International Workshop on Symbiotic Interaction, pp. 168-180. Springer, Cham, 2016.

DOI: 10.1007/978-3-319-57753-1_15

A brain-computer interface (BCI) measures and interprets brain signals enabling people to communicate without the use of peripheral muscles. One of the common BCI paradigms are steady state visual evoked potentials (SSVEPs), brain signals induced by gazing at a constantly flickering target. The choice of stimulation frequencies and the number of simultaneously used stimuli highly influence the performance of such SSVEP-based BCI. In this article, a dictionary-driven four class SSVEP-based spelling application is presented, tested, and evaluated. To enhance classification accuracy, frequencies were determined individually with a calibration software for SSVEP-BCIs, enabling non-experts to set up the system. Forty-one healthy participants used the BCI system to spell English sentences (lengths between 23 and 37 characters). All participants completed the spelling task successfully. A mean accuracy of 97.92% and a mean ITR of 23.84 bits/min were achieved, 18 participants even reached 100% accuracy. On average the number of commands needed to spell the example sentences with four classes, without dictionary support is higher by a factor of 1.92. Thanks to the implemented dictionary the time needed to spell typical everyday sentences can be drastically reduced.

Year 2015

Felix Gembler, Piotr Stawicki, and Ivan Volosyak. "Autonomous parameter adjustment for SSVEP-based BCIs with a novel BCI wizard." In Frontiers in neuroscience 9 (2015): 474.

DOI: 10.3389/fnins.2015.00474

Brain-Computer Interfaces (BCIs) transfer human brain activities into computer commands and enable a communication channel without requiring movement. Among other BCI approaches, steady-state visual evoked potential (SSVEP)-based BCIs have the potential to become accurate, assistive technologies for persons with severe disabilities. Those systems require customization of different kinds of parameters (e.g., stimulation frequencies). Calibration usually requires selecting predefined parameters by experienced/trained personnel, though in real-life scenarios an interface allowing people with no experience in programming to set up the BCI would be desirable. Another occurring problem regarding BCI performance is BCI illiteracy (also called BCI deficiency). Many articles reported that BCI control could not be achieved by a non-negligible number of users. In order to bypass those problems we developed a SSVEP-BCI wizard, a system that automatically determines user-dependent key-parameters to customize SSVEP-based BCI systems. This wizard was tested and evaluated with 61 healthy subjects. All subjects were asked to spell the phrase "RHINE WAAL UNIVERSITY" with a spelling application after key parameters were determined by the wizard. Results show that all subjects were able to control the spelling application. A mean (SD) accuracy of 97.14 (3.73)% was reached (all subjects reached an accuracy above 85% and 25 subjects even reached 100% accuracy).
Felix Gembler, Piotr Stawicki, and Ivan Volosyak. "A comparison of SSVEP-based BCI-performance between different age groups." In International Work-Conference on Artificial Neural Networks, pp. 71-77. Springer, Cham, 2015.

DOI: 10.1007/978-3-319-19258-1_6

In this paper we compare the performance of a SSVEP-based BCI spelling application of two different equally sized age groups (five subjects each, ranging from 19 to 27 years and 66 to 70 years). Our results confirm that elderly people may have a slightly deteriorated information transfer rate (ITR). The mean (SD) ITR of the young age group was 27.18 (8.82) bit/min while the elderly people achieved an ITR of 14.42 (6.29) bit/min. The results show that the subject age must be taken into account during the development of a SSVEP-based application.
Piotr Stawicki, Felix Gembler, and Ivan Volosyak. "Evaluation of suitable frequency differences in SSVEP-based BCIs." In International Work-Conference on Artificial Neural Networks, pp. 159-165. Springer, Cham, 2015.

DOI: 10.1007/978-3-319-24917-9_17

Frame-based frequency approximation methods are a popular approach to realize visual stimuli that can be used to elicit steady-state visual evoked potentials (SSVEPs) at various frequencies on computer screens and allows the development of multi-target Brain-Computer Interface (BCI)-Systems. In this paper we investigate appropriate selection of visual stimuli for multi-target BCIs using a frequency approximation method. Twelve sets of frequencies from different bands and with different resolutions have been compared among each other during an on-line BCI-task with six healthy subjects. Our results confirm that equidistant frequency sets are not optimal, as the results from the sets with lower frequency ranges ( < 12 Hz) surpass those of the mid-range sets, even if a higher resolution is used. Interestingly, the study shows, that SSVEPs elicted by stimuli from lower bands with a very high frequency resolution of 0.05 Hz could still be classified with adequate accuracy (around 90%). The results confirm that careful stimuli choice has high impact on SSVEP based BCI performance.

Books

Ivan Volosyak "Microchip AVR Programming using ATmega Microcontrollers: with Answers" Publication Series of BCI Lab Kleve, Rhine-Waal University of Applied Sciences, ISBN: 978-3-8440-8015-5, Shaker Verlag, Germany, June 2021

DOI: 10.2370/9783844080155

The book Ivan Volosyak - Microchip AVR Programming using ATmega Microcontrollers: with Answers can be ordered from Shaker Verlag GmbH, Germany.
Ivan Volosyak (Editor). "Recent advances in VEP-based BCI systems" Publication Series of BCI Lab Kleve, Rhine-Waal University of Applied Sciences, ISBN: 978-3-8440-7404-8, Shaker Verlag, Germany, June 2020

DOI: 10.2370/9783844074048

The book series Publication Series of BCI Lab Kleve, Rhine-Waal University of Applied Sciences can be ordered from Shaker Verlag GmbH, Germany.
Felix Gembler. "Parameter Optimization for Brain-Computer Interfaces based on Visual Evoked Potentials." Bielefeld: Universität Bielefeld, 2020. Dissertation.

DOI: 10.4119/unibi/2948847

For people who are physically unable to communicate with their fellow human beings due to severe disabilities, technical communication aids can be a life enrichment. Communication tools can be realized with so-called brain-computer interfaces (BCIs), which provide a connection between the brain and the computer and can be controlled without the activation of the peripheral nervous system. The electrical brain activity is recorded, usually noninvasively, by means of an electroencephalogram (EEG). BCIs analyze the collected EEG data in real-time and convert them into output signals allowing hands-free control of various kinds of applications such as mental typewriters. One of the control paradigms used to realize BCIs is based on visual evoked potentials (VEPs), which appear in the visual cortex of the brain when visual stimuli are perceived. An example of such stimuli is flickering target objects on a computer screen, each flashing with a specific frequency. By detecting the VEPs, the BCI can determine the target on which the user is focusing. In spelling applications, these targets represent letters; the user can spell a word or sentence just by looking at the corresponding stimulus. In several studies, a high variation in BCI accuracy across users has been observed; not all users did achieve reliable control over the system. A significant problem in BCI research is that EEG data cannot be interpreted reliably for all users. In spelling applications, the system might output wrong letters too frequently, which makes effective communication difficult. For other applications, such as wheelchair control, faulty classifications should be avoided entirely. An essential goal in the field of research is, therefore, to improve the accuracy of the classification. One way to achieve this goal is to customize critical parameters to the user. In this work, factors that impact the performance of VEP-based BCIs were investigated. These factors include parameters and settings of the user interface and the classification, such as the number of targets and the duration that a stimulus needs to be fixated until the corresponding command is executed. Furthermore, demographic differences such as age and gender and their relation to BCI performance were analyzed. To this end, several studies - each dedicated to one or several of these factors - were conducted. The results of these studies indicated that user age and the number of targets of the graphical user interface have a high impact on classification accuracy. Based on these findings, a robust BCI application was developed, a spelling application that determines personalized key parameters. This application enables a more accurate BCI control, as the BCI is tailored to the respective user. Moreover, the software allows non-specialists to set up the system. The latter is an essential point in terms of usability in daily life; it enables nursing staff or family members to adjust the necessary system settings with little effort.

Legal Notices | Privacy Policy