A parametric feature extraction and classification strategy for brain-computer interfacing.

Parametric modeling strategies are explored in conjunction with linear discriminant analysis for use in an electroencephalogram (EEG)-based brain-computer interface (BCI). A left/right self-paced typing exercise is analyzed by extending the usual autoregressive (AR) model for EEG feature extraction with an AR with exogenous input (ARX) model for combined filtering and feature extraction. The ensemble averaged Bereitschafts potential (an event related potential preceding the onset of movement) forms the exogenous signal input to the ARX model. Based on trials with six subjects, the ARX case of modeling both the signal and noise was found to be considerably more effective than modeling the noise alone (common in BCI systems) with the AR method yielding a classification accuracy of 52.8+/-4.8% and the ARX method an accuracy of 79.1+/-3.9 % across subjects. The results suggest a role for ARX-based feature extraction in BCIs based on evoked and event-related potentials.     

A practical VEP-based brain-computer interface.

This paper introduces the development of a practical brain-computer interface at Tsinghua University. The system uses frequency-coded steady-state visual evoked potentials to determine the gaze direction of the user. To ensure more universal applicability of the system, approaches for reducing user variation on system performance have been proposed. The information transfer rate (ITR) has been evaluated both in the laboratory and at the Rehabilitation Center of China, respectively. The system has been proved to be applicable to > 90% of people with a high ITR in living environments.     

A virtual reality testbed for brain-computer interface research.

Virtual reality promises to extend the realm of possible brain-computer interface (BCI) prototypes. Most of the work using electroencephalograph (EEG) signals in VR has focussed on brain-body actuated control, where biological signals from the body as well as the brain are used. We show that when subjects are allowed to move and act normally in an immersive virtual environment, cognitive evoked potential signals can still be obtained and used reliably. A single trial accuracy average of 85% for recognizing the differences between evoked potentials at red and yellow stop lights will be presented and future directions discussed.     

A decision tree for brain-computer interface devices

This paper is a first attempt to present a "decision tree" to assist in choosing a brain-computer interface device for patients who are nearly or completely "locked-in" (cognitively intact but unable to move or communicate.) The first step is to assess any remaining function. There are six inflexion points in the decision-making process. These depend on the functional status of the patient: 1) some residual movement; 2) no movement, but some residual electromyographic (EMG) activity; 3) fully locked-in with no EMG activity or movements but with conjugate eye movements; 4) same as 3 but with disconjugate eye movements; 5) same as 4 but with inadequate assistance from the available EEG-based systems; 6) same as 5 and accepting of an invasive system.     

A general framework for brain-computer interface design

The Brain-Computer Interface (BCI) research community has acknowledged that researchers are experiencing difficulties when they try to compare the BCI techniques described in the literature. In response to this situation, the community has stressed the need for objective methods to compare BCI technologies. Suggested improvements have included the development and use of benchmark applications and standard data sets. However, as a young, multidisciplinary research field, the BCI community lacks a common vocabulary. As a result, this deficiency leads to poor intergroup communication, which hinders the development of the desired methods of comparison. One of the principle reasons for the lack of common vocabulary is the absence of a common functional model of a BCI System. This paper proposes a new functional model for BCI System design. The model supports many features that facilitate the comparison of BCI technologies with other BCI and non-BCI user interface technologies. From this model, taxonomy for BCI System design is developed. Together the model and taxonomy are considered a general framework for BCI System design. The representational power of the proposed framework was evaluated by applying it to a set of existing BCI technologies. The framework could effectively describe all of the BCI System designs tested.     

Sensorimotor rhythm-based brain-computer interface (BCI): feature selection by regression improves performance.

People can learn to control electroencephalogram (EEG) features consisting of sensorimotor rhythm amplitudes and can use this control to move a cursor in one or two dimensions to a target on a screen. In the standard one-dimensional application, the cursor moves horizontally from left to right at a fixed rate while vertical cursor movement is continuously controlled by sensorimotor rhythm amplitude. The right edge of the screen is divided among 2-6 targets, and the user's goal is to control vertical cursor movement so that the cursor hits the correct target when it reaches the right edge. Up to the present, vertical cursor movement has been a linear function of amplitude in a specific frequency band [i.e., 8-12 Hz (mu) or 18-26 Hz (beta)] over left and/or right sensorimotor cortex. The present study evaluated the effect of controlling cursor movement with a weighted combination of these amplitudes in which the weights were determined by an regression algorithm on the basis of the user's past performance. Analyses of data obtained from a representative set of trained users indicated that weighted combinations of sensorimotor rhythm amplitudes could support cursor control significantly superior to that provided by a single feature. Inclusion of an interaction term further improved performance. Subsequent online testing of the regression algorithm confirmed the improved performance predicted by the offline analyses. The results demonstrate the substantial value for brain-computer interface applications of simple multivariate linear algorithms. In contrast to many classification algorithms, such linear algorithms can easily incorporate multiple signal features, can readily adapt to changes in the user's control of these features, and can accommodate additional targets without major modifications.     

EEG and MEG brain-computer interface for tetraplegic patients.

We characterized features of magnetoencephalographic (MEG) and electroencephalographic (EEG) signals generated in the sensorimotor cortex of three tetraplegics attempting index finger movements. Single MEG and EEG trials were classified offline into two classes using two different classifiers, a batch trained classifier and a dynamic classifier. Classification accuracies obtained with dynamic classifier were better, at 75%, 89%, and 91% in different subjects, when features were in the 0.5-3.0-Hz frequency band. Classification accuracies of EEG and MEG did not differ.     

Real-world applications for brain-computer interface technology

The mission of the Georgia State University BrainLab is to create and adapt methods of human-computer interaction that will allow brain-computer interface (BCI) technologies to effectively control real-world applications. Most of the existing BCI applications were designed largely for training and demonstration purposes. Our goal is to research ways of transitioning BCI control skills learned in training to real-world scenarios. Our research explores some of the problems and challenges of combining BCI outputs with human-computer interface paradigms in order to achieve optimal interaction. We utilize a variety of application domains to compare and validate BCI interactions, including communication, environmental control, neural prosthetics, and creative expression. The goal of this research is to improve quality of life for those with severe disabilities.     

Robust classification of EEG signal for brain-computer interface.

We report the implementation of a text input application (speller) based on the P300 event related potential. We obtain high accuracies by using an SVM classifier and a novel feature. These techniques enable us to maintain fast performance without sacrificing the accuracy, thus making the speller usable in an online mode. In order to further improve the usability, we perform various studies on the data with a view to minimizing the training time required. We present data collected from nine healthy subjects, along with the high accuracies (of the order of 95% or more) measured online. We show that the training time can be further reduced by a factor of two from its current value of about 20 min. High accuracy, fast learning, and online performance make this P300 speller a potential communication tool for severely disabled individuals, who have lost all other means of communication and are otherwise cut off from the world, provided their disability does not interfere with the performance of the speller.     

ECoG factors underlying multimodal control of a brain-computer interface.

Most current brain-computer interface (BCI) systems for humans use electroencephalographic activity recorded from the scalp, and may be limited in many ways. Electrocorticography (ECoG) is believed to be a minimally-invasive alternative to electroencephalogram (EEG) for BCI systems, yielding superior signal characteristics that could allow rapid user training and faster communication rates. In addition, our preliminary results suggest that brain regions other than the sensorimotor cortex, such as auditory cortex, may be trained to control a BCI system using similar methods as those used to train motor regions of the brain. This could prove to be vital for users who have neurological disease, head trauma, or other conditions precluding the use of sensorimotor cortex for BCI control.     

An improved P300-based brain-computer interface.

A brain-computer interface (BCI) is a system for direct communication between brain and computer. The BCI developed in this work is based on a BCI described by Farwell and Donchin in 1988, which allows a subject to communicate one of 36 symbols presented on a 6 x 6 matrix. The system exploits the P300 component of event-related brain potentials (ERP) as a medium for communication. The processing methods distinguish this work from Donchin's work. In this work, independent component analysis (ICA) was used to separate the P300 source from the background noise. A matched filter was used together with averaging and threshold techniques for detecting the existence of P300s. The processing method was evaluated offline on data recorded from six healthy subjects. The method achieved a communication rate of 5.45 symbols/min with an accuracy of 92.1% compared to 4.8 symbols/min with an accuracy of 90% in Donchin's work. The online interface was tested with the same six subjects. The average communication rate achieved was 4.5 symbols/min with an accuracy of 79.5 % as apposed to the 4.8 symbols/min with an accuracy of 56 % in Donchin's work. The presented BCI achieves excellent performance compared to other existing BCIs, and allows a reasonable communication rate, while maintaining a low error rate.     

A new brain-computer interface design using fuzzy ARTMAP

This paper proposes a new brain-computer interface (BCI) design using fuzzy ARTMAP (FA) neural network, as well as an application of the design. The objective of this BCI-FA design is to classify the best three of the five available mental tasks for each subject using power spectral density (PSD) values of electroencephalogram (EEG) signals. These PSD values are extracted using the Wiener-Khinchine and autoregressive methods. Ten experiments employing different triplets of mental tasks are studied for each subject. The findings show that the average BCI-FA out- puts for four subjects gave less than 6% of error using the best triplets of mental tasks identified from the classification performances of FA. This implies that the BCI-FA can be successfully used with a tri-state switching device. As an application, a proposed tri-state Morse code scheme could be utilized to translate the outputs of this BCI-FA design into English letters. In this scheme, the three BCI-FA outputs correspond to a dot and a dash, which are the two basic Morse code alphabets and a space to denote the end (or beginning) of a dot or a dash. The construction of English letters using this tri-state Morse code scheme is determined only by the sequence of mental tasks and is independent of the time duration of each mental task. This is especially useful for constructing letters that are represented as multiple dots or dashes. This combination of BCI-FA design and the tri-state Morse code scheme could be developed as a communication system for paralyzed patients.     

Phase synchronization for the recognition of mental tasks in a brain-computer interface

Brain-computer interfaces (BCIs) may be a future communication channel for motor-disabled people. In surface electroencephalogram (EEG)-based BCIs, the extracted features are often derived from spectral estimates and autoregressive models. We examined the usefulness of synchronization between EEG signals for classifying mental tasks. To this end, we investigated the performance of features derived from the phase locking value (PLV) and from the spectral coherence and compared them to the classification rates resulting from the power densities in alpha, beta1, beta2, and 8-30-Hz frequency bands. Five recordings of 60 min, acquired from three subjects while performing three different mental tasks, were analyzed offline. No artifacts were removed or rejected. We noticed significant differences between PLV and mean spectral coherence. For sole use of synchronization measures, classification accuracies up to 62% were achieved. In general, the best result was obtained combining phase synchronization measures with alpha power spectral density estimates. The results demonstrate that phase synchronization provides relevant information for the classification of spontaneous EEG during mental tasks.     

An adaptive P300-based online brain-computer interface.

The P300 component of an event related potential is widely used in conjunction with brain-computer interfaces (BCIs) to translate the subjects intent by mere thoughts into commands to control artificial devices. A well known application is the spelling of words while selection of the letters is carried out by focusing attention to the target letter. In this paper, we present a P300-based online BCI which reaches very competitive performance in terms of information transfer rates. In addition, we propose an online method that optimizes information transfer rates and/or accuracies. This is achieved by an algorithm which dynamically limits the number of subtrial presentations, according to the subject's current online performance in real-time. We present results of two studies based on 19 different healthy subjects in total who participated in our experiments (seven subjects in the first and 12 subjects in the second one). In the first, study peak information transfer rates up to 92 bits/min with an accuracy of 100% were achieved by one subject with a mean of 32 bits/min at about 80% accuracy. The second experiment employed a dynamic classifier which enables the user to optimize bitrates and/or accuracies by limiting the number of subtrial presentations according to the current online performance of the subject. At the fastest setting, mean information transfer rates could be improved to 50.61 bits/min (i.e., 13.13 symbols/min). The most accurate results with 87.5% accuracy showed a transfer rate of 29.35 bits/min.     

Single-trial EEG classification using in-phase average for brain-computer interface

Communication signals should be estimated by a single trial in a brain-computer interface. Since the relativity of visual evoked potentials from different sites should be stronger than those of the spontaneous electroencephalogram (EEG), this paper adopted the time-lock averaged signals from multi-channels as features. 200 trials of EEG recordings evoked by target or non-target stimuli were classified by the support vector machine (SVM). Results show that a classification accuracy of higher than 97% can be obtained by merely using the 250–550 ms time section of the averaged signals with channel Cz and Pz as features. It suggests that a possible approach to boost communication speed and simplify the designation of the brain-computer interface (BCI) system is worthy of an attempt in this way. __________ Translated from Journal of Huazhong University of Science and Technology (Nature Science Edition), 2007, 35(1): 11–13 [译自: 华中科技大学学报(自然科学版)]     

Application of tripolar concentric electrodes and prefeature selection algorithm for brain-computer interface.

For persons with severe disabilities, a brain-computer interface (BCI) may be a viable means of communication. Lapalacian electroencephalogram (EEG) has been shown to improve classification in EEG recognition. In this work, the effectiveness of signals from tripolar concentric electrodes and disc electrodes were compared for use as a BCI. Two sets of left/right hand motor imagery EEG signals were acquired. An autoregressive (AR) model was developed for feature extraction with a Mahalanobis distance based linear classifier for classification. An exhaust selection algorithm was employed to analyze three factors before feature extraction. The factors analyzed were 1) length of data in each trial to be used, 2) start position of data, and 3) the order of the AR model. The results showed that tripolar concentric electrodes generated significantly higher classification accuracy than disc electrodes.     

Implementation of a telemonitoring system for the control of an EEG-based brain-computer interface

By the use of a brain-computer interface (BCI), it is possible for completely paralyzed patients, who have lost their ability to speak, to have a new possibility to communicate with their environment. The training with such a BCI system can be performed at the patient's home, if there is a responsible person present who is familiar with the system. This person has to adjust different parameters and to adapt the training individually to each patient. Since this function is usually taken over by the developers of the system, the number of patients who can be included in regular BCI training is restricted due to geographical distances. This paper describes the implementation of a telemonitoring system, which makes it possible for the developer to control and supervise the BCI training from his or her own place of work. First experiences with a patient living far away from the developer's lab are reported.     

A facial feature communications interface for the non-vocal

A viable communications interface for the nonvocal handicapped that is a by-product of recent face recognition research is described. The system uses either the Karhunen-Loeve transform (KLT) or the discrete cosine transform (DCT) to encode video camera images on a subject's face. The encoding differentiates among three expressions: tongue out which is classified as `yes'; mouth open, which is classified as `no'; and mouth closed, which is classified as `null'. A review of the theory of the KLT and DCT is included     

α波和运动想象的混合范式脑-机接口系统

提出将α波和运动想象2种范式以串行的方式相结合控制的脑-机接口系统,该系统利用α波的阻断现象控制状态选择,选择成功后发出提示音,被试听到提示音后,通过左右手运动想象来完成多个任务。通过这样的混合范式有效的实现了较少种类的脑电信号对外部设备的多任务控制。实验结果表明,5名被试都能顺利完成外部设备的多任务控制,平均正确率为77%,最高正确率可达90%。本系统实现了混合范式下的脑电信号对外部设备的多任务控制,为进一步开发复杂的混合范式的脑-机接口系统奠定基础。     

The mental prosthesis: assessing the speed of a P300-based brain-computer interface.

We describe a study designed to assess a brain-computer interface (BCI), originally described by Farwell and Donchin [9] in 1988. The system utilizes the fact that the rare events in the oddball paradigm elicit the P300 component of the event-related potential (ERP). The BCI presents the user with a matrix of 6 by 6 cells, each containing one letter of the alphabet. The user focuses attention on the cell containing the letter to be communicated while the rows and the columns of the matrix are intensified. Each intensification is an event in the oddball sequence, the row and the column containing the attended cell are "rare" items and, therefore, only these events elicit a P300. The computer thus detects the transmitted character by determining which row and which column elicited the P300. We report an assessment, using a boot-strapping approach, which indicates that an off line version of the system can communicate at the rate of 7.8 characters a minute and achieve 80% accuracy. The system's performance in real time was also assessed. Our data indicate that a P300-based BCI is feasible and practical. However, these conclusions are based on tests using healthy individuals.