A four command BCI system based on the SSVEP protocol

Writing Blindly in Incomplete Locked-In Syndrome with A Custom-Made Switch-Operated Voice-Scanning Communicator—A Case Report

Background: Locked-In Syndrome (LIS) is a rare neurological condition in which patients’ ability to move, interact, and communicate is impaired despite their being conscious and awake. After assessing the patient’s needs, we developed a customized device for an LIS patient, as the commercial augmentative and alternative communication (AAC) devices could not be used. Methods: A 51-year-old woman with incomplete LIS for 15 years came to our laboratory seeking a communication tool. After excluding the available AAC devices, a careful evaluation led to the creation of a customized device (hardware + software). Two years later, we assessed the patient’s satisfaction with the device. Results: A switch-operated voice-scanning communicator, which the patient could control by residual movement of her thumb without seeing the computer screen, was implemented, together with postural strategies. The user and her family were generally satisfied with the customized device, with a top rating for its effectiveness: it fit well the patient’s communication needs. Conclusions: Using customized AAC and strategies provides greater opportunities for patients with LIS to resolve their communication problems. Moreover, listening to the patient’s and family’s needs can help increase the AAC’s potential. The presented switch-operated voice-scanning communicator is available for free on request to the authors.

Progress in EEG-Based Brain Robot Interaction Systems

The most popular noninvasive Brain Robot Interaction (BRI) technology uses the electroencephalogram- (EEG-) based Brain Computer Interface (BCI), to serve as an additional communication channel, for robot control via brainwaves. This technology is promising for elderly or disabled patient assistance with daily life. The key issue of a BRI system is to identify human mental activities, by decoding brainwaves, acquired with an EEG device. Compared with other BCI applications, such as word speller, the development of these applications may be more challenging since control of robot systems via brainwaves must consider surrounding environment feedback in real-time, robot mechanical kinematics, and dynamics, as well as robot control architecture and behavior. This article reviews the major techniques needed for developing BRI systems. In this review article, we first briefly introduce the background and development of mind-controlled robot technologies. Second, we discuss the EEG-based brain signal models with respect to generating principles, evoking mechanisms, and experimental paradigms. Subsequently, we review in detail commonly used methods for decoding brain signals, namely, preprocessing, feature extraction, and feature classification, and summarize several typical application examples. Next, we describe a few BRI applications, including wheelchairs, manipulators, drones, and humanoid robots with respect to synchronous and asynchronous BCI-based techniques. Finally, we address some existing problems and challenges with future BRI techniques.

Regularized Linear Discriminant Analysis of EEG Features in Dementia Patients

The present study explores if EEG spectral parameters can discriminate between healthy elderly controls (HC), Alzheimer's disease (AD) and vascular dementia (VaD) using. We considered EEG data recorded during normal clinical routine with 114 healthy controls (HC), 114 AD, and 114 VaD patients. The spectral features extracted from the EEG were the absolute delta power, decay from lower to higher frequencies, amplitude, center and dispersion of the alpha power and baseline power of the entire frequency spectrum. For discrimination, we submitted these EEG features to regularized linear discriminant analysis algorithm with a 10-fold cross-validation. To check the consistency of the results obtained by our classifiers, we applied bootstrap statistics. Four binary classifiers were used to discriminate HC from AD, HC from VaD, AD from VaD, and HC from dementia patients (AD or VaD). For each model, we measured the discrimination performance using the area under curve (AUC) and the accuracy of the cross-validation (cv-ACC). We applied this procedure using two different sets of predictors. The first set considered all the features extracted from the 22 channels. For the second set of features, we automatically rejected features poorly correlated with their labels. Fairly good results were obtained when discriminating HC from dementia patients with AD or VaD (AUC = 0.84). We also obtained AUC = 0.74 for discrimination of AD from HC, AUC = 0.77 for discrimination of VaD from HC, and finally AUC = 0.61 for discrimination of AD from VaD. Our models were able to separate HC from dementia patients, and also and to discriminate AD from VaD above chance. Our results suggest that these features may be relevant for the clinical assessment of patients with dementia.

A multi-command SSVEP-based BCI system based on single flickering frequency half-field steady-state visual stimulation

Steady-state visual evoked potentials (SSVEPs) are widely employed in brain-computer interface (BCI) applications, especially to control machines. However, the use of SSVEPs leads to eye fatigue and causes lower accuracy over the long term, particularly when multi-commands are required. Therefore, this paper proposes a half-field steady-state visual stimulation pattern and paradigm to increase the limited number of commands that can be achieved with existing SSVEP-based BCI methods. Following the theory of vision perception and existing half-field SSVEP-based BCI systems, the new stimulation pattern generates four commands using only one frequency flickering stimulus and has an average classification accuracy of approximately 75 %. According to the proposed stimulus pattern, using only one frequency without requiring users to stare directly at the flickering stimulus allows users to easily focus on the system and experience less visual fatigue compared to existing systems. Furthermore, new half-field SSVEP-based BCI systems are proposed, incorporating our proposed feature extraction and decision-making algorithm. Extracting the signal from the occipital area and using a reference electrode position at the parietal area yielded better results compared to the central area. In addition, we recommend using an LED or LCD as the visual stimulus device (at the recommended size), which yielded comparable results to our proposed feature extraction and decision-making algorithm. Finally, an application of the proposed system is demonstrated for real-time television control.

Steering a tractor by means of an EMG-based human-machine interface

An electromiographic (EMG)-based human-machine interface (HMI) is a communication pathway between a human and a machine that operates by means of the acquisition and processing of EMG signals. This article explores the use of EMG-based HMIs in the steering of farm tractors. An EPOC, a low-cost human-computer interface (HCI) from the Emotiv Company, was employed. This device, by means of 14 saline sensors, measures and processes EMG and electroencephalographic (EEG) signals from the scalp of the driver. In our tests, the HMI took into account only the detection of four trained muscular events on the driver's scalp: eyes looking to the right and jaw opened, eyes looking to the right and jaw closed, eyes looking to the left and jaw opened, and eyes looking to the left and jaw closed. The EMG-based HMI guidance was compared with manual guidance and with autonomous GPS guidance. A driver tested these three guidance systems along three different trajectories: a straight line, a step, and a circumference. The accuracy of the EMG-based HMI guidance was lower than the accuracy obtained by manual guidance, which was lower in turn than the accuracy obtained by the autonomous GPS guidance; the computed standard deviations of error to the desired trajectory in the straight line were 16 cm, 9 cm, and 4 cm, respectively. Since the standard deviation between the manual guidance and the EMG-based HMI guidance differed only 7 cm, and this difference is not relevant in agricultural steering, it can be concluded that it is possible to steer a tractor by an EMG-based HMI with almost the same accuracy as with manual steering.

A comparison of monopolar and bipolar EEG recordings for SSVEP detection

This paper presents a comparative study over the detection of Steady-State Visual Evoked Potential (SSVEP) with monopolar or bipolar electroencephalographic (EEG) recordings in a Brain-Computer Interface experiment. Five subjects participated in this study. They were stimulated with four flickering lights at 13, 14, 15 and 16 Hz and the EEG was measured simultaneously with two bipolar channels (O(1)-P(3) and O(2)-P(4)) and with six monopolar channels at O(1), O(2), P(3), P(4), T(5) and T(6) referenced to F(Z). The EEG was processed by means of spectral analysis and the estimation of power at each stimulation frequency and its harmonics. In average, the monopolar recordings present accuracy in classification of 74.5% against an 80.1% for bipolar recordings. It was found that bipolar recording are better than monopolar recordings for detection of SSVEP.

A survey of stimulation methods used in SSVEP-based BCIs

Brain-computer interface (BCI) systems based on the steady-state visual evoked potential (SSVEP) provide higher information throughput and require shorter training than BCI systems using other brain signals. To elicit an SSVEP, a repetitive visual stimulus (RVS) has to be presented to the user. The RVS can be rendered on a computer screen by alternating graphical patterns, or with external light sources able to emit modulated light. The properties of an RVS (e.g., frequency, color) depend on the rendering device and influence the SSVEP characteristics. This affects the BCI information throughput and the levels of user safety and comfort. Literature on SSVEP-based BCIs does not generally provide reasons for the selection of the used rendering devices or RVS properties. In this paper, we review the literature on SSVEP-based BCIs and comprehensively report on the different RVS choices in terms of rendering devices, properties, and their potential influence on BCI performance, user safety and comfort.