scholarly journals A Link between the Increase in Electroencephalographic Coherence and Performance Improvement in Operating a Brain-Computer Interface

2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Irma Nayeli Angulo-Sherman ◽  
David Gutiérrez
Keyword(s):  
Performance Improvement ◽  
Motor Imagery ◽  
Brain Computer Interface ◽  
Training Session ◽  
Brain Regions ◽  
Computer Interface ◽  
Imagery Task ◽  
And Performance ◽  
The Relationship ◽  
Event Related Coherence

We study the relationship between electroencephalographic (EEG) coherence and accuracy in operating a brain-computer interface (BCI). In our case, the BCI is controlled through motor imagery. Hence, a number of volunteers were trained using different training paradigms: classical visual feedback, auditory stimulation, and functional electrical stimulation (FES). After each training session, the volunteers’ accuracy in operating the BCI was assessed, and the event-related coherence (ErCoh) was calculated for all possible combinations of pairs of EEG sensors. After at least four training sessions, we searched for significant differences in accuracy and ErCoh using one-way analysis of variance (ANOVA) and multiple comparison tests. Our results show that there exists a high correlation between an increase in ErCoh and performance improvement, and this effect is mainly localized in the centrofrontal and centroparietal brain regions for the case of our motor imagery task. This result has a direct implication with the development of new techniques to evaluate BCI performance and the process of selecting a feedback modality that better enhances the volunteer’s capacity to operate a BCI system.

scholarly journals Multiclass Informative Instance Transfer Learning Framework for Motor Imagery-Based Brain-Computer Interface

2018 ◽  
Vol 2018 ◽  
pp. 1-12 ◽  
Author(s):  
Ibrahim Hossain ◽  
Abbas Khosravi ◽  
Imali Hettiarachchi ◽  
Saeid Nahavandi
Keyword(s):  
Transfer Learning ◽  
Motor Imagery ◽  
Brain Computer Interface ◽  
Training Session ◽  
Training Data ◽  
Superior Performance ◽  
Computer Interface ◽  
Imagery Task ◽  
Learning Framework ◽  
Optimal Ensemble

A widely discussed paradigm for brain-computer interface (BCI) is the motor imagery task using noninvasive electroencephalography (EEG) modality. It often requires long training session for collecting a large amount of EEG data which makes user exhausted. One of the approaches to shorten this session is utilizing the instances from past users to train the learner for the novel user. In this work, direct transferring from past users is investigated and applied to multiclass motor imagery BCI. Then, active learning (AL) driven informative instance transfer learning has been attempted for multiclass BCI. Informative instance transfer shows better performance than direct instance transfer which reaches the benchmark using a reduced amount of training data (49% less) in cases of 6 out of 9 subjects. However, none of these methods has superior performance for all subjects in general. To get a generic transfer learning framework for BCI, an optimal ensemble of informative and direct transfer methods is designed and applied. The optimized ensemble outperforms both direct and informative transfer method for all subjects except one in BCI competition IV multiclass motor imagery dataset. It achieves the benchmark performance for 8 out of 9 subjects using average 75% less training data. Thus, the requirement of large training data for the new user is reduced to a significant amount.

Competing at the Cybathlon Championship for Athletes With Disabilities: Long-Term Motor Imagery Brain-Computer Interface Training of a Tetraplegic Cybathlete

2021 ◽  
Author(s):  
Attila Korik ◽  
Karl McCreadie ◽  
Niall McShane ◽  
Naomi Du Bois ◽  
Massoud Khodadadzadeh ◽  
...  
Keyword(s):  
Motor Imagery ◽  
Brain Computer Interface ◽  
Computer Interface ◽  
Cognitive State ◽  
Contributing Factors ◽  
Performance Pressure ◽  
Cord Injury ◽  
Athletes With Disabilities ◽  
Run Up ◽  
And Performance

Abstract Background: The brain-computer interface (BCI) race at the Cybathlon championship for athletes with disabilities challenges teams (BCI researchers, developers and pilots with spinal cord injury) to control an avatar on a virtual racetrack without movement. Here we describe the training regime and results of the Ulster University BCI Team pilot who is tetraplegic and has trained to use an electroencephalography (EEG)-based BCI intermittently over 10 years, to compete in three Cybathlon events. Methods: A multi-class, multiple binary classifier framework was used to decode three kinesthetically imagined movements (motor imagery) (left (L) and right (R) arm and feet (F)) as well as relax state (X). Three games paradigms were used for training i.e., NeuroSensi, Triad, and Cybathlon: BrainDriver. An evaluation of the pilot’s performance is presented for two Cybathlon competition training periods – spanning 20 sessions over 5 weeks prior to the 2019 competition, and 25 sessions over 5 weeks in the run up to the 2020 competition.Results: Having participated in BCI training in 2009 and competed in Cybathlon 2016, the experienced pilot achieved high two-class accuracy on all class pairs when training began in 2019 (decoding accuracy >90%, resulting in efficient NeuroSensi and Triad game control). The BrainDriver performance (i.e., Cybathlon race completion time) improved significantly during the training period, leading up to the competition day, ranging from 274s - 156s (255±24s to 191±14s mean±std), over 17 days (10 sessions) in 2019, and from 230s - 168s (214±14s to 181±4s), over 18 days (13 sessions) in 2020. However, on both competition occasions, towards the race date, the performance deteriorated significantly.Conclusions: The training regime and framework applied were highly effective in achieving competitive race completion times. The BCI framework did not cope with significant deviation in electroencephalography (EEG) observed in the sessions occurring shortly before and during the race day. Stress, arousal level and fatigue, associated with the competition challenge and performance pressure resulting in cognitive state changes, were likely contributing factors to the nonstationary effects that resulted in the BCI and pilot achieving suboptimal performance on race day. Trial registration: not registered

scholarly journals Tangent Space Features-Based Transfer Learning Classification Model for Two-Class Motor Imagery Brain–Computer Interface

2019 ◽  
Vol 29 (10) ◽  
pp. 1950025 ◽  
Author(s):  
Pramod Gaur ◽  
Karl McCreadie ◽  
Ram Bilas Pachori ◽  
Hui Wang ◽  
Girijesh Prasad
Keyword(s):  
Transfer Learning ◽  
Motor Imagery ◽  
Tangent Space ◽  
Brain Computer Interface ◽  
Training Session ◽  
Training Data ◽  
Classification Model ◽  
Computer Interface ◽  
Multivariate Empirical Mode Decomposition ◽  
Subject Specific

The performance of a brain–computer interface (BCI) will generally improve by increasing the volume of training data on which it is trained. However, a classifier’s generalization ability is often negatively affected when highly non-stationary data are collected across both sessions and subjects. The aim of this work is to reduce the long calibration time in BCI systems by proposing a transfer learning model which can be used for evaluating unseen single trials for a subject without the need for training session data. A method is proposed which combines a generalization of the previously proposed subject-specific “multivariate empirical-mode decomposition” preprocessing technique by taking a fixed band of 8–30[Formula: see text]Hz for all four motor imagery tasks and a novel classification model which exploits the structure of tangent space features drawn from the Riemannian geometry framework, that is shared among the training data of multiple sessions and subjects. Results demonstrate comparable performance improvement across multiple subjects without subject-specific calibration, when compared with other state-of-the-art techniques.

Discriminative Learning of Propagation and Spatial Pattern for Motor Imagery EEG Analysis

2013 ◽  
Vol 25 (10) ◽  
pp. 2709-2733 ◽  
Author(s):  
Xinyang Li ◽  
Haihong Zhang ◽  
Cuntai Guan ◽  
Sim Heng Ong ◽  
Kai Keng Ang ◽  
...  
Keyword(s):  
Spatial Pattern ◽  
Motor Imagery ◽  
Brain Activity ◽  
Brain Computer Interface ◽  
Statistical Significance ◽  
Activity Patterns ◽  
Signal Propagation ◽  
Brain Regions ◽  
Computer Interface ◽  
Scalp Eeg

Effective learning and recovery of relevant source brain activity patterns is a major challenge to brain-computer interface using scalp EEG. Various spatial filtering solutions have been developed. Most current methods estimate an instantaneous demixing with the assumption of uncorrelatedness of the source signals. However, recent evidence in neuroscience suggests that multiple brain regions cooperate, especially during motor imagery, a major modality of brain activity for brain-computer interface. In this sense, methods that assume uncorrelatedness of the sources become inaccurate. Therefore, we are promoting a new methodology that considers both volume conduction effect and signal propagation between multiple brain regions. Specifically, we propose a novel discriminative algorithm for joint learning of propagation and spatial pattern with an iterative optimization solution. To validate the new methodology, we conduct experiments involving 16 healthy subjects and perform numerical analysis of the proposed algorithm for EEG classification in motor imagery brain-computer interface. Results from extensive analysis validate the effectiveness of the new methodology with high statistical significance.

Free Virtual Navigation Using Motor Imagery Through an Asynchronous Brain–Computer Interface

2010 ◽  
Vol 19 (1) ◽  
pp. 71-81 ◽  
Author(s):  
Francisco Velasco-Álvarez ◽  
Ricardo Ron-Angevin ◽  
Maria José Blanca-Mena
Keyword(s):  
Virtual Environments ◽  
Motor Imagery ◽  
Brain Computer Interface ◽  
Computer Interface ◽  
Imagery Task ◽  
Virtual Navigation ◽  
Intentional Control ◽  
Feedback Training ◽  
Control Interface ◽  
Fixed Path

In this paper, an asynchronous brain–computer interface is presented that enables the control of a wheelchair in virtual environments using only one motor imagery task. The control is achieved through a graphical intentional control interface with three navigation commands (move forward, turn right, and turn left) which are displayed surrounding a circle. A bar is rotating in the center of the circle, so it points successively to the three possible commands. The user can, by motor imagery, extend this bar length to select the command at which the bar is pointing. Once a command is selected, the virtual wheelchair moves in a continuous way, so the user controls the length of the advance or the amplitude of the turns. Users can voluntarily switch from this interface to a noncontrol interface (and vice versa) when they do not want to generate any command. After performing a cue-based feedback training, three subjects carried out an experiment in which they had to navigate through the same fixed path to reach an objective. The results obtained support the viability of the system.

scholarly journals Brain-computer interface algorithm based on wavelet-phase stability analysis in motor imagery experiment

2020 ◽  
Vol 16 (2) ◽  
pp. 236-242
Author(s):  
Muhamad Firdaus Mohd Rafi ◽  
Arief Ruhullah A Harris ◽  
Tan Tian Swee ◽  
Kah Meng Leong ◽  
Jia Hou Tan ◽  
...  
Keyword(s):  
Motor Imagery ◽  
Phase Stability ◽  
Phase Synchronization ◽  
Brain Computer Interface ◽  
Computer Interface ◽  
Imagery Task ◽  
Body Parts ◽  
Time Data ◽  
Input Signals ◽  
Human Augmentation

Severe movement or motor disability diseases such as amyotrophic lateral sclerosis (ALS), cerebral palsy (CB), and muscular dystrophy (MD) are types of diseases which lead to the total of function loss of body parts, usually limbs. Patient with an extreme motor impairment might suffers a locked-in state, resulting in the difficulty to perform any physical movements. These diseases are commonly being treated by a specific rehabilitation procedure with prescribed medication. However, the recovery process is time-consuming through such treatments. To overcome these issues, Brain-Computer Interface system is introduced in which one of its modalities is to translate thought via electroencephalography (EEG) signals by the user and generating desired output directly to an external artificial control device or human augmentation. Here, phase synchronization is implemented to complement the BCI system by analyzing the phase stability between two input signals. The motor imagery-based experiment involved ten healthy subjects aged from 24 to 30 years old with balanced numbers between male and female. Two aforementioned input signals are the respective reference data and the real time data were measured by using phase stability technique by indicating values range from 0 (least stable) to 1 (most stable). Prior to that, feature extraction was utilized by applying continuous wavelet transform (CWT) to quantify significant features on the basis of motor imagery experiment which are right and left imaginations. The technique was able to segregate different classes of motor imagery task based on classification accuracy. This study affirmed the approach’s ability to achieve high accuracy output measurements.

Sign in / Sign up

Export Citation Format

Share Document