Asynchronous BCI and local neural classifiers: an overview of the adaptive brain interface project
IEEE Transactions on Neural Systems and Rehabilitation EngineeringPublished 1 June 2003Open access
José del R. Millán, J. Mouriño
Citations290
SJR quartileQ1
SJR score1.31
SNIP1.62
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
An asynchronous brain-computer interface that responds every 0.5 s; a local neural classifier tries to recognize three different mental tasks; it may also respond "unknown" for uncertain samples as the classifier has incorporated statistical rejection criteria.
Abstract
In this communication, we give an overview of our work on an asynchronous brain-computer interface (where the subject makes self-paced decisions on when to switch from one mental task to the next) that responds every 0.5 s. A local neural classifier tries to recognize three different mental tasks; it may also respond "unknown" for uncertain samples as the classifier has incorporated statistical rejection criteria. We report our experience with 15 subjects. We also briefly describe two brain-actuated applications we have developed: a virtual keyboard and a mobile robot (emulating a motorized wheelchair).
Keywords
Computer ScienceNeuroscience
Electroencephalography and Clinical NeurophysiologySpherical splines for scalp potential and current density mapping
2,777 Citations1989Fabien Perrin, J. Pernier +2 more
Description of mapping methods using spherical splines, both to interpolate scalp potentials (SPs) and to approximate scalp current densities (SCDs) with greater accuracy in areas with few electrodes.
Proceedings of the IEEEMotor imagery and direct brain-computer communication
1,932 Citations2001G. Pfurtscheller, Christa Neuper
At this time, a tetraplegic patient is able to operate an EEG-based control of a hand orthosis with nearly 100% classification accuracy by mental imagination of specific motor commands.
NatureA spelling device for the paralysed
1,566 Citations1999Niels Birbaumer, N. Ghanayim +7 more
A new means of communication for the completely paralysed that uses slow cortical potentials of the electro-encephalogram to drive an electronic spelling device is developed.
Electroencephalography and Clinical NeurophysiologyMultichannel EEG-based brain-computer communication
450 Citations1994Jonathan R. Wolpaw, Dennis J. McFarland
This study learned to use two channels of bipolar EEG activity to control 2-dimensional movement of a cursor on a computer screen using multichannel EEG-based communication to help those with severe motor disabilities.
IEEE Transactions on Neural NetworksA local neural classifier for the recognition of EEG patterns associated to mental tasks
185 Citations2002José del R. Millán, J. Mouriño +5 more
Analysis of learned EEG patterns confirms that for a subject to operate satisfactorily a brain interface, the latter must fit the individual features of the former.
IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)Rapid, safe, and incremental learning of navigation strategies
104 Citations1996José del R. Millán
A reinforcement connectionist learning architecture that allows an autonomous robot to acquire efficient navigation strategies in a few trials and has high tolerance to noisy sensory data and good generalization abilities is proposed.
Communications of the ACMAdaptive brain interfaces
100 Citations2003José del R. Millán
Users interact with physical devices through nothing more than the voluntary control of their own mental activity.
Biological CyberneticsRelevant EEG features for the classification of spontaneous motor-related tasks
92 Citations2002José del R. Millán, Marco Franzé +3 more
This study empirically demonstrates the benefits of heuristic feature selection methods for EEG-based classification of mental tasks and shows that the classifier performance improves for all the considered subjects with only a small proportion of features.
Medical & Biological Engineering & ComputingReal-time brain-computer interfacing: A preliminary study using Bayesian learning
91 Citations2000Stephen Roberts, W.D. Penny
It is shown that uncertainty in decisions is taken into account under a Bayesian formalism and that this may be used to reject uncertain samples, thus dramatically improving system performance.
Electroencephalography and Clinical NeurophysiologyEOG correction: a new perspective
60 Citations1998Rodney J. Croft, Robert J. Barry
The findings are consistent with the thesis that eye movement related fields propagate similarly for a range of EOG types and frequencies, suggesting that the B differences reported in the literature are artifactual, and indicating the need for a new correction procedure.
Medical Engineering & PhysicsRecognition of imagined hand movements with low resolution surface Laplacian and linear classifiers
55 Citations2001Fabio Babiloni, Febo Cincotti +6 more
Recognition scores for mental EEG-patterns were obtained with the low-resolution surface Laplacian transformation of the recorded potentials when compared with those obtained by using full resolution SL (82%).
IEEE Transactions on Rehabilitation EngineeringBrain-computer interface research at the Neil Squire Foundation
49 Citations2000Gary E. Birch, S.G. Mason
The ultimate goal of this research is to utilize voluntary motor-related potentials recorded from the scalp in a direct Brain Computer Interface for asynchronous control applications.
International Joint Conference on Artificial IntelligenceNon-invasive brain-actuated control of a mobile robot
49 Citations2003José del R. Millán, F. Renkens +2 more
A portable non-invasive brain-computer interface is reported that makes possible the continuous control of a mobile robot in a house-like environment and shows that, after a few days of training, two human subjects successfully moved a robot between several rooms by mental control only.
Journal of Intelligent SystemsEffects of Variations in Neural Network Topology and Output Averaging on the Discrimination of Mental Tasks from Spontaneous Electroencephalogram
30 Citations1997Charles W. Anderson
Electroencephalogram signals from one subject who performed three mental tasks are classified by neural networks using a sixth-order autoregressive (AR) model of half-second windows of six-channel EEG, and a classification accuracy of 89% on test data is achieved.
Spatial filtering in the training process of a brain computer interface
15 Citations2005J. Mouriño, José del R. Millán +4 more
This study shows the evolution in the selection of the most appropriate spatial filter when subjects are training to control a brain-computer interface.
Brain-Computer Interfaces
11 Citations2023Martin Groß, Birgit Hennig
Lecture notes in computer scienceTemporal Processing of Brain Activity for the Recognition of EEG Patterns
8 Citations2002Alexandre Hauser, Pierre‐Edouard Sottas +1 more
It turns out that the simple local neural classifier currently embedded in the BCI, which averages the response to 8 consecutive EEG samples, is to be preferred to more complex time-processing networks such as TDNN and Elman-like.