Machine-Learning-Based Coadaptive Calibration for Brain-Computer Interfaces

ArticleinNeural Computation 23(3) · December 2010with48 Reads
DOI: 10.1162/NECO_a_00089 · Source: PubMed
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. We investigate adaptive machine learning methods to eliminate offline 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.
    • "In order to compensate for variability in BCI signals, recent work has leveraged adaptive classification algorithms to distinguish between mental gestures [10], [11], [8]. Automated calibration procedures have turned BCI novices into competent users over the course of hours instead of days or weeks, and without manual calibration [11]. During calibration, users perform labeled (i.e. "
    [Show abstract] [Hide abstract] ABSTRACT: While brain-computer interfaces (BCI) based on electroencephalography (EEG) have improved dramatically over the past five years, their inconvenient, head-worn form factor has challenged their wider adoption. In this paper, we investigate how EEG signals collected from the ear could be used for "gestural" control of a brain-computer interface (BCI). Specifically, we investigate the efficacy of a support vector classifier (SVC) in distinguishing between mental tasks, or gestures, recorded by a modified, consumer headset. We find that an SVC reaches acceptable BCI accuracy for nine of the subjects in our pool (n=12), and distinguishes at least one pair of gestures better than chance for all subjects. User surveys highlight the need for longer-term research on user attitudes toward in-ear EEG devices, for discreet, non-invasive BCIs.
    Full-text · Conference Paper · Jun 2016 · Neural Computing and Applications
    • "However, in both cases, only one subject is reported demonstrating that sensorimotor rhythms can appear within one training session. In [1], discriminability increase is shown for most subjects between the beginning and the end of a training session on a certain feature, but it is still unclear to what extent its magnitude has a substantial impact. Similar results are extracted in a P300 BCI in [20]. "
    [Show abstract] [Hide abstract] ABSTRACT: Objective: This work presents a first motor imagery-based, adaptive brain-computer interface (BCI) speller, which is able to exploit application-derived context for improved, simultaneous classifier adaptation and spelling. Online spelling experiments with ten able-bodied users evaluate the ability of our scheme, first, to alleviate non-stationarity of brain signals for restoring the subject's performances, second, to guide naive users into BCI control avoiding initial offline BCI calibration and, third, to outperform regular unsupervised adaptation. Approach: Our co-adaptive framework combines the BrainTree speller with smooth-batch linear discriminant analysis adaptation. The latter enjoys contextual assistance through BrainTree's language model to improve online expectation-maximization maximum-likelihood estimation. Main results: Our results verify the possibility to restore single-sample classification and BCI command accuracy, as well as spelling speed for expert users. Most importantly, context-aware adaptation performs significantly better than its unsupervised equivalent and similar to the supervised one. Although no significant differences are found with respect to the state-of-the-art PMean approach, the proposed algorithm is shown to be advantageous for 30% of the users. Significance: We demonstrate the possibility to circumvent supervised BCI recalibration, saving time without compromising the adaptation quality. On the other hand, we show that this type of classifier adaptation is not as efficient for BCI training purposes.
    Article · May 2016
    • "These methods, however, require a large amount of historic data to be available. Other techniques have sought to reduce the calibration phase through the use of co-adaptive methods or semi-supervised learning approaches161718192021. These methods may initially have a limited performance, but it improves after a considerable adaptation time. "
    [Show abstract] [Hide abstract] ABSTRACT: Motor imagery-based brain–computer interface (MI-BCI) has been proposed as a rehabilitation tool to facilitate motor recovery in stroke. However, the calibration of a BCI system is a time-consuming and fatiguing process for stroke patients, which leaves reduced time for actual therapeutic interaction. Studies have shown that passive movement (PM) (i.e., the execution of a movement by an external agency without any voluntary motions) and motor imagery (MI) (i.e., the mental rehearsal of a movement without any activation of the muscles) induce similar EEG patterns over the motor cortex. Since performing PM is less fatiguing for the patients, this paper investigates the effectiveness of calibrating MI-BCIs from PM for stroke subjects in terms of classification accuracy. For this purpose, a new adaptive algorithm called filter bank data space adaptation (FB-DSA) is proposed. The FB-DSA algorithm linearly transforms the band-pass-filtered MI data such that the distribution difference between the MI and PM data is minimized. The effectiveness of the proposed algorithm is evaluated by an offline study on data collected from 16 healthy subjects and 6 stroke patients. The results show that the proposed FB-DSA algorithm significantly improved the classification accuracies of the PM and MI calibrated models (p < 0.05). According to the obtained classification accuracies, the PM calibrated models that were adapted using the proposed FB-DSA algorithm outperformed the MI calibrated models by an average of 2.3 and 4.5 % for the healthy and stroke subjects respectively. In addition, our results suggest that the disparity between MI and PM could be stronger in the stroke patients compared to the healthy subjects, and there would be thus an increased need to use the proposed FB-DSA algorithm in BCI-based stroke rehabilitation calibrated from PM.
    Full-text · Article · Mar 2016
Show more