A5055115678- EEG and Brain-Computer Interfaces
- Neuroscience and Neural Engineering
- Neural dynamics and brain function
- Blind Source Separation Techniques
- Advanced Memory and Neural Computing
- Functional Brain Connectivity Studies
- Gaze Tracking and Assistive Technology
- Muscle activation and electromyography studies
- ECG Monitoring and Analysis
- Neural and Behavioral Psychology Studies
- Neural Networks and Applications
- Epilepsy research and treatment
- Motor Control and Adaptation
- Robotics and Automated Systems
- Hearing, Cochlea, Tinnitus, Genetics
- Phonocardiography and Auscultation Techniques
- Cardiovascular Syncope and Autonomic Disorders
- Teleoperation and Haptic Systems
- Medical Imaging and Analysis
- Cholinesterase and Neurodegenerative Diseases
- Vestibular and auditory disorders
- Heart Rate Variability and Autonomic Control
- Prosthetics and Rehabilitation Robotics
- Sports Performance and Training
- Cervical and Thoracic Myelopathy
Ikerbasque
2023-2024
Basque Center on Cognition, Brain and Language
2023-2024
Berlin Institute for the Foundations of Learning and Data
2023-2024
Universidad Publica de Navarra
2006-2023
Tecnalia
2022-2023
Basque Centre for Climate Change
2023
Universidad de Navarra
2005-2023
Technische Universität Berlin
2011-2021
Fraunhofer Institute for Production Systems and Design Technology
2008-2021
For Inspiration and Recognition of Science and Technology
2008
The BCI Competition IV stands in the tradition of prior Competitions that aim to provide high quality neuroscientific data for open access scientific community. As experienced already competitions not only scientists from narrow field compete, but scholars with a broad variety backgrounds and nationalities. They include specialists as well students. goals all have always been challenge respect novel paradigms complex data. We report on following challenges: (1) asynchronous data, (2)...
In recent years, new research has brought the field of EEG-based Brain-Computer Interfacing (BCI) out its infancy and into a phase relative maturity through many demonstrated prototypes such as brain-controlled wheelchairs, keyboards, computer games. With this proof-of-concept in past, time is now ripe to focus on development practical BCI technologies that can be lab real-world applications. particular, we prospect improving lives countless disabled individuals combination technology with...
Brain–Computer Interfaces (BCIs) allow a user to control computer application by brain activity as acquired, e.g., EEG. One of the biggest challenges in BCI research is understand and solve problem "BCI Illiteracy", which that does not work for non-negligible portion users (estimated 15 30%). Here, we investigate illiteracy systems are based on modulation sensorimotor rhythms. In this paper, sophisticated adaptation scheme presented guides from an initial subject-independent classifier...
Brain-Computer Interfacing (BCI) is a steadily growing area of research. While initially BCI research was focused on applications for paralyzed patients, increasingly more alternative in healthy human subjects are proposed and investigated. In particular, monitoring mental states decoding covert user have seen strong rise interest. Here, we present some examples such novel which provide evidence the promising potential technology non-medical uses. Furthermore, discuss distinct methodological...
There is a step of significant difficulty experienced by brain-computer interface (BCI) users when going from the calibration recording to feedback application. This effect has been previously studied and supervised adaptation solution proposed. In this paper, we suggest simple unsupervised method linear discriminant analysis (LDA) classifier that effectively solves problem counteracting harmful nonclass-related nonstationarities in electroencephalography (EEG) during BCI sessions performed...
BioSig is an open source software library for biomedical signal processing. The aim of the project to foster research in processing by providing free and tools many different application areas. Some areas where can be employed are neuroinformatics, brain-computer interfaces, neurophysiology, psychology, cardiovascular systems, sleep research. Moreover, analysis biosignals such as electroencephalogram (EEG), electrocorticogram (ECoG), electrocardiogram (ECG), electrooculogram (EOG),...
Classifying motion intentions in brain–computer interfacing (BCI) is a demanding task as the recorded EEG signal not only noisy and has limited spatial resolution but it also intrinsically non-stationary. The non-stationarities may come from many different sources, for instance, electrode artefacts, muscular activity or changes of involvement, often deteriorate classification performance. This mainly because features extracted by standard methods like common patterns (CSP) are invariant to...
Brain-computer interfaces (BCIs) allow users to control a computer application by brain activity as acquired (e.g., EEG). In our classic machine learning approach BCIs, the participants undertake calibration measurement without feedback acquire data train BCI system. After training, user can and improve operation through some type of feedback. However, not all are able perform sufficiently well during operation. fact, nonnegligible portion (estimated 15%-30%) cannot system (a illiteracy...
A viable fully on-line adaptive brain computer interface (BCI) is introduced. On-line experiments with nine naive and able-bodied subjects were carried out using a continuously BCI system. The data analyzed the viability of system was studied. based on motor imagery, feature extraction performed an autoregressive model classifier used quadratic discriminant analysis. updated by estimation information matrix (ADIM). also able to provide continuous feedback subject. success studied analyzing...
All brain–computer interface (BCI) groups that have published results of studies involving a large number users performing BCI control based on the voluntary modulation sensorimotor rhythms (SMR) report could not be achieved by non-negligible subjects (estimated 20% to 25%). This failure system read intention user is one greatest problems and challenges in research. There are two main causes for this problem SMR-based systems: either no idle SMR observed over motor areas user, or rhythm...
System calibration and user training are essential for operating motor imagery based brain-computer interface (BCI) systems. These steps often unintuitive tedious the user, do not necessarily lead to a satisfactory level of control. We present an Adaptive BCI framework that provides feedback after only minutes autocalibration in two-class setup. During operation, system recurrently reselects one out six predefined logarithmic bandpower features (10-13 16-24 Hz from Laplacian derivations over...
MUNDUS is an assistive framework for recovering direct interaction capability of severely motor impaired people based on arm reaching and hand functions. It aims at achieving personalization, modularity maximization the user’s involvement in systems. To this, exploits any residual control end-user can be adapted to level severity or progression disease allowing user voluntarily interact with environment. target pathologies are high-level spinal cord injury (SCI) neurodegenerative genetic...
Brain-Computer Interfaces (BCIs) are inefficient for a non-negligible part of the population, estimated around 25%. To understand this phenomenon in Sensorimotor Rhythm (SMR) based BCIs, data from large-scale screening study conducted on 80 novice participants with Berlin BCI system and its standard machine-learning approach were investigated. Each participant performed one session resting state Encephalography, Motor Observation, Execution Imagery recordings 128 electrodes. A significant...
A study of different on-line adaptive classifiers, using various feature types is presented. Motor imagery brain computer interface (BCI) experiments were carried out with 18 naive able-bodied subjects. Experiments done three two-class, cue-based, electroencephalogram (EEG)-based systems. Two continuously classifiers tested: quadratic and linear discriminant analysis. Three analyzed, autoregressive parameters, logarithmic band power estimates the concatenation both. Results show that all...
Two groups of inexperienced brain-computer interface users underwent a purely mental EEG-BCI session that rapidly impacted on their brain. Modulations in structural and functional MRI were found after only 1 h BCI training. different types (based motor imagery or visually evoked potentials) employed analyses showed the brain plastic changes are spatially specific for respective neurofeedback. This spatial specificity promises tailored therapeutic interventions (e.g. stroke patients).A...
Objective: In electroencephalographic (EEG) data, signals from distinct sources within the brain are widely spread by volume conduction and superimposed such that sensors receive mixtures of a multitude signals. This reduction spatial information strongly hampers single-trial analysis EEG data as, for example, required brain–computer interfacing (BCI) when using features spontaneous rhythms. Spatial filtering techniques therefore greatly needed to extract meaningful EEG. Our goal is show, in...
We present the first generic theoretical formulation of co-adaptive learning problem and give a simple example two interacting linear systems, human machine.After description training protocol we define model where agents are coupled by joint loss function. The simplicity allows us to find rules for both machine that permit computing simulations.As seen in simulations, an astonishingly rich structure is found this eco-system learners. While learners shown easily stall or get out sync some...
In the last years Brain Computer Interface (BCI) technology has benefited from development of sophisticated machine leaning methods that let user operate BCI after a few trials calibration. One remarkable example is recent co-adaptive techniques proved to extend use BCIs also people not able achieve successful control with standard procedure. Especially for based on modulation Sensorimotor Rhythm (SMR) these improvements are essential, since negligible percentage users unable SMR-BCIs...
In recent years, brain-computer interfaces (BCIs) have become mature enough to immensely benefit from the expertise and tools established in field of human-computer interaction (HCI). One core objectives HCI research is design systems that provide a pleasurable user experience (UX). While majority BCI studies exclusively evaluate common efficiency measures such as classification accuracy speed, single groups begun look at further usability aspects ease use, workload learnability. However,...
Laplacian filters are widely used in neuroscience. In the context of brain–computer interfacing, they might be preferred to data-driven approaches such as common spatial patterns (CSP) a variety scenarios as, e.g., when no or few user data available calibration session with multi-channel recording is not possible, which case various applications. this paper we propose use an ensemble local CSP patches (CSPP) can considered compromise between and CSP. Our CSPP only needs very small number...