Machine-learning-based coadaptive calibration for brain-computer interfaces

Authors:
Carmen Vidaurre;Claudia Sannelli;Klaus-Robert Miiller;Benjamin Blankertz
Affiliations:
Machine Learning Department, Berlin Institute of Technology, Berlin, Germany;Machine Learning Department, Berlin Institute of Technology, Berlin, Germany;Machine Learning Department, Berlin Institute of Technology, Berlin, Germany, and Bernstein Focus: Neurotechnology, Berlin, Germany;Machine Learning Department, Berlin Institute of Technology, Berlin, Germany/ Bernstein Focus: Neurotechnology, Berlin, Germany/ and Fraunhofer FIRST (IDA), Berlin, Germany
Venue:
Neural Computation
Year:
2011

Citing 6
Cited 10

A well-conditioned estimator for large-dimensional covariance matrices

Journal of Multivariate Analysis
Brain-actuated interaction

Artificial Intelligence
Covariate Shift Adaptation by Importance Weighted Cross Validation

The Journal of Machine Learning Research
Designing for uncertain, asymmetric control: Interaction design for brain-computer interfaces

International Journal of Human-Computer Studies
2009 Special Issue: Subject-independent mental state classification in single trials

Neural Networks
2009 Special Issue: Time Domain Parameters as a feature for EEG-based Brain-Computer Interfaces

Neural Networks

Improving classification performance of BCIS by using stationary common spatial patterns and unsupervised bias adaptation

HAIS'11 Proceedings of the 6th international conference on Hybrid artificial intelligent systems - Volume Part II
Modelling non-stationarities in EEG data with robust principal component analysis

HAIS'11 Proceedings of the 6th international conference on Hybrid artificial intelligent systems - Volume Part II
A co-adaptive training paradigm for motor imagery based brain-computer interface

ISNN'12 Proceedings of the 9th international conference on Advances in Neural Networks - Volume Part I
Adaptive classification on brain-computer interfaces using reinforcement signals

Neural Computation
Eeg data space adaptation to reduce intersession nonstationarity in brain-computer interface

Neural Computation
Discriminative learning of propagation and spatial pattern for motor imagery eeg analysis

Neural Computation
Brain-computer interface controlled gaming: Evaluation of usability by severely motor restricted end-users

Artificial Intelligence in Medicine
A brain-computer interface for high-level remote control of an autonomous, reinforcement-learning-based robotic system for reaching and grasping

Proceedings of the 19th international conference on Intelligent User Interfaces
A case study of linear classifiers adapted using imperfect labels derived from human event-related potentials

Pattern Recognition Letters
Robust common spatial filters with a maxmin approach

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Brain-computer interfaces (BCIs) allow users to control a computer application by brain activity as acquired (e.g., by EEG). In our classic machine learning approach to BCIs, the participants undertake a calibration measurement without feedback to acquire data to train the BCI system. After the training, the user can control a BCI and improve the operation through some type of feedback. However, not all BCI users are able to perform sufficiently well during feedback operation. In fact, a nonnegligible portion of participants (estimated 15%-30%) cannot control the system (a BCI illiteracy problem, generic to all motor-imagery-based BCIs). We hypothesize that one main difficulty for a BCI user is the transition from offline calibration to online feedback. In this work, we investigate adaptive machine learning methods to eliminate offiine calibration and analyze the performance of 11 volunteers in a BCI based on the modulation of sensorimotor rhythms. We present an adaptation scheme that individually guides the user. It starts with a subject-independent classifier that evolves to a subject-optimized state-of-the-art classifier within one session while the user interacts continuously. These initial runs use supervised techniques for robust coadaptive learning of user and machine. Subsequent runs use unsupervised adaptation to track the features' drift during the session and provide an unbiased measure of BCI performance. Using this approach, without any offline calibration, six users, including one novice, obtained good performance after 3 to 6 minutes of adaptation. More important, this novel guided learning also allows participants with BCI illiteracy to gain significant control with the BCI in less than 60 minutes. In addition, one volunteer without sensorimotor idle rhythm peak at the beginning of the BCI experiment developed it during the course of the session and used voluntary modulation of its amplitude to control the feedback application.