Fig 4 - uploaded by Dan Zhang
Content may be subject to copyright.
A) Correlation between the offline and online classification accuracies. B) Relation between online accuracy and the similarity of EEG topographies between offline and online session. Dots are labeled with the subject number. https://doi.org/10.1371/journal.pone.0178385.g004
Source publication
A promising approach for brain-computer interfaces (BCIs) employs the steady-state visual evoked potential (SSVEP) for extracting control information. Main advantages of these SSVEP BCIs are a simple and low-cost setup, little effort to adjust the system parameters to the user and comparatively high information transfer rates (ITR). However, tradit...
Similar publications
Individuals with severe speech and physical impairments may have concomitant visual acuity impairments (VAI) or ocular motility impairments (OMI) impacting visual BCI use. We report on use of the Shuffle Speller typing interface for SSVEP BCI copy-spelling with simulated VAI, simulated OMI, and unimpaired vision. To mitigate the effects of visual i...
Citations
... Table I summarizes the stimulation paradigms, frequencies, and performance of user-friendly four-target BCI systems in recent years. Research methods to improve user experience in low and medium frequency bands include applying spatial encoding strategies to reduce the number of stimuli [37] or designing new stimulus paradigms [20], [21], etc. This study achieved higher classification accuracy and ITR than previous studies by using grid stimulation paradigms with high comfort in low and medium frequency bands. ...
In steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) systems, traditional flickering stimulation patterns face challenges in achieving a trade-off in both BCI performance and visual comfort across various frequency bands. To investigate the optimal stimulation paradigms with high performance and high comfort for each frequency band, this study systematically compared the characteristics of SSVEP and user experience of different stimulation paradigms with a wide stimulation frequency range of 1-60 Hz. The findings suggest that, for a better balance between system performance and user experience, ON and OFF grid stimuli with a Weber contrast of 50% can be utilized as alternatives to traditional flickering stimulation paradigms in the frequency band of 1-25 Hz. In the 25-35 Hz range, uniform flicker stimuli with the same 50% contrast are more suitable. In the higher frequency band, traditional uniform flicker stimuli with a high 300% contrast are preferred. These results are significant for developing high performance and user-friendly SSVEP-based BCI systems.
... Recently, lateralized visual stimuli away from the central field of view has gained considerable interest in BCI studies because of the theory of retinotopic mapping (Yoshimura et al., 2011;Chen et al., 2017). According to retina-cortical mapping, the spatial pattern of VEPs is closely related to the position of visual stimuli in the visual field (Wurtz and Kandel, 2000). ...
Introduction
Traditional visual Brain-Computer Interfaces (v-BCIs) usually use large-size stimuli to attract more attention from users and then elicit more distinct and robust EEG responses, which would cause visual fatigue and limit the length of use of the system. On the contrary, small-size stimuli always need multiple and repeated stimulus to code more instructions and increase separability among each code. These common v-BCIs paradigms can cause problems such as redundant coding, long calibration time, and visual fatigue.
Methods
To address these problems, this study presented a novel v-BCI paradigm using weak and small number of stimuli, and realized a nine-instruction v-BCI system that controlled by only three tiny stimuli. Each of these stimuli were located between instructions, occupied area with eccentricities subtended 0.4°, and flashed in the row-column paradigm. The weak stimuli around each instruction would evoke specific evoked related potentials (ERPs), and a template-matching method based on discriminative spatial pattern (DSP) was employed to recognize these ERPs containing the intention of users. Nine subjects participated in the offline and online experiments using this novel paradigm.
Results
The average accuracy of the offline experiment was 93.46% and the online average information transfer rate (ITR) was 120.95 bits/min. Notably, the highest online ITR achieved 177.5 bits/min.
Discussion
These results demonstrate the feasibility of using a weak and small number of stimuli to implement a friendly v-BCI. Furthermore, the proposed novel paradigm achieved higher ITR than traditional ones using ERPs as the controlled signal, which showed its superior performance and may have great potential of being widely used in various fields.
... An example of the latter is to use a 5-class motor imagery (MI) BCI for piloting a wheelchair [9]. As for navigation in a virtual environment (VE), some attempts have been made to demonstrate the potential use of a BCI in games [10] and mouse control [11]. In [12], a cave automatic virtual environment (CAVE) was implemented, in which subjects navigate in a virtual street projected on active screens surrounding the subject. ...
... The navigation system we propose is based on imagined movement (IM) eliciting a power increase (event-related synchronization ERS) and decrease (event-related desynchronization ERD) in mu (8)(9)(10)(11)(12) and beta (14-25 Hz) bands in EEG recorded over the ipsiand contralateral sensorimotor cortex, respectively [26]. The EEG recording device used in this study was Mentalab [27], an 8-channel dry electrode wireless headset. ...
Navigation in virtual worlds is ubiquitous in games and other virtual reality (VR) applications and mainly relies on external controllers. As brain–computer interfaces (BCI)s rely on mental control, bypassing traditional neural pathways, they provide to paralyzed users an alternative way to navigate. However, the majority of BCI-based navigation studies adopt cue-based visual paradigms, and the evoked brain responses are encoded into navigation commands. Although robust and accurate, these paradigms are less intuitive and comfortable for navigation compared to imagining limb movements (motor imagery, MI). However, decoding motor imagery from EEG activity is notoriously challenging. Typically, wet electrodes are used to improve EEG signal quality, including a large number of them to discriminate between movements of different limbs, and a cuedbased paradigm is used instead of a self-paced one to maximize decoding performance. Motor BCI applications primarily focus on typing applications or on navigating a wheelchair—the latter raises safety concerns—thereby calling for sensors scanning the environment for obstacles and potentially hazardous scenarios. With the help of new technologies such as virtual reality (VR), vivid graphics can be rendered, providing the user with a safe and immersive experience; and they could be used for navigation purposes, a topic that has yet to be fully explored in the BCI community. In this study, we propose a novel MI-BCI application based on an 8-dry-electrode EEG setup, with which users can explore and navigate in Google Street View®. We pay attention to system design to address the lower performance of the MI decoder due to the dry electrodes’ lower signal quality and the small number of electrodes. Specifically, we restricted the number of navigation commands by using a novel middle-level control scheme and avoided decoder mistakes by introducing eye blinks as a control signal in different navigation stages. Both offline and online experiments were conducted with 20 healthy subjects. The results showed acceptable performance, even given the limitations of the EEG set-up, which we attribute to the design of the BCI application. The study suggests the use of MI-BCI in future games and VR applications for consumers and patients temporarily or permanently devoid of muscle control.
... Single-flicker SSVEP is a novel BCI that uses only one flickering stimulus to generate multiple commands from the user's brain signals [18], [19]. It is based on the principle of retinotopic mapping, which means that the brain response depends on the spatial position of the stimulus relative to the center of gaze [20]. Although it reduces visual fatigue, improves the signal-to-noise ratio, and enhances the spatial attention mechanism of the brain, it can be more sensitive to eye movements and blinks, and more affected by individual differences in retinotopic mapping. ...
... The selection of an appropriate feature extraction technique plays an important role to enhance the accuracy and reliability of the system's performance in a single-flicker frequency SSVEP-based BCIs. Power spectral density analysis (PSDA) is one of the earliest technique used for SSVEP analysis [19], [20], [23]. However, the PSDA has limited application due to the sensitivity of the SSVEP signal to noise and the low-frequency resolution in short-time windowing [24]. ...
... To the best of our knowledge, this study provides the opportunity for the first time to consider and compare several traditional methods for single-flicker SSVEP. The effectiveness of the proposed single-flicker SSVEPbased BCI technique is evaluated on two BCI dataset [20], [56], and the results are compared with previous works. The obtained results demonstrate reliable classification. ...
Brain-computer interface (BCI) systems have been developed to assist individuals with neuromuscular disorders to communicate with their surroundings using their brain signals. One attractive branch of BCI is steady-state visual evoked potential (SSVEP), which has acceptable speed and accuracy and is non-invasive. However, SSVEP-based EEG signals suffer from eye-fatigue problems, resulting in artifacts that affect the accuracy of the system. Thus, researchers are still working to improve SSVEP-based BCI systems. This paper proposes robust machine-learning algorithm for single-flicker SSVEP detection. A novel approach based on fast independent component analysis and filter-bank canonical correlation analysis (fast ICA-FBCCA) is developed to extract features from the single-flicker SSVEP signal. The clean features learned by fast ICA-FBCCA are then applied to a discrete wavelet transform (DWT) technique and fed to a convolutional neural network (CNN) with only one convolutional layer and a smaller number of parameters. The effectiveness of the proposed technique is evaluated using two datasets. The results were evaluated using two datasets. The findings clearly demonstrate that the proposed method outperforms traditional methods, with average target recognition accuracy and standard deviation values of 97 ± 3.1% among 6 subjects for dataset 1 and 82.12 ± 10.7% among 12 subjects for dataset 2. Overall, these findings suggest that the proposed method is a promising approach for improving the accuracy and reliability of the single-flicker SSVEP-based BCI systems.
... U Cuando se busca, a través de estas técnicas, obtener más de una respuesta o estado en la salida del sistema, por ejemplo, para determinar el movimiento de un cursor en una pantalla hacia 4 direcciones distintas (4 estados), lo más frecuente es que se utilicen 4 frecuencias de estimulación diferentes para cada estado, buscando que éstos sean lo suficientemente diferenciables como para que no haya confusión entre ellos (o que dicha probabilidad de confusión sea la menor posible). Sin embargo, algunos trabajos también han abordado la posibilidad de obtener este mayor número de estados, pero con una única frecuencia de estimulación [5,6]. ...
... Se utilizaron como datos a analizar, registros de EEG de libre disponibilidad online obtenidos durante la etapa de entrenamiento llevada a cabo en [5]. ...
... Tanto en [5] como en [6] se desarrollaron trabajos similares con objetivos relacionados, y en ambos casos se obtuvieron valores de energía muy prometedores, con altas tasas de transferencia de información (ITR) que permitieron realizar una buena clasificación, con niveles de precisión suficientemente elevados como para ser empleados en la obtención una mayor variedad de comandos. Dichos trabajos resultan útiles para destacar la relevancia de los resultados expuestos en el presente artículo y realizar nuevas conclusiones. ...
Brain-computer interfaces (BCIs) based on steady-state visual evoked potentials (SSVEPs) generally use flickering stimuli with different frequencies to generate multiple control commands. In recent years, the implementation of this paradigm has increased its popularity, mainly due to its high information transfer rates (ITR), low level of training required, easy implementation and low dependence of its responses on the different emotional states of the user. An interesting variant of this paradigm is obtaining multiple states after the use of a single-frequency flickering source, which is possible using electroencephalographic mapping techniques. Thus, these systems can detect the direction of the gaze with respect to the blinking source. This work proposes to objectively determine the degree of discriminability between the various states to identify which ones could be more easily differentiated and implemented with a smaller number of recording electrodes.
... One important advantage of this approach is that, unlike in frequency-coded SSVEP BCIs in which the user has to gaze at the flicker stimulus, in our spatially-coded SSVEP BCI, the flicker always appears in the extrafoveal field. We have argued that this property likely has advantages with respect to visual fatigue [15]. In addition, the high stimulation frequency that increases the temporal granularity of the dynamic stopping at the same time can also be expected to improve user comfort. ...
... Together with the corresponding class labels, these feature vectors comprised the training data for the LDA classifier. This classification method is frequently used in BCI applications, and it performed reasonably well in our previous studies [14,15]. ...
The spatially-coded SSVEP BCI exploits changes in the topography of the steady-state visual evoked response to visual flicker stimulation in the extrafoveal field of view. In contrast to frequency-coded SSVEP BCIs, the operator does not gaze into any flickering lights; therefore, this paradigm can reduce visual fatigue. Other advantages include high classification accuracies and a simplified stimulation setup. Previous studies of the paradigm used stimulation intervals of a fixed duration. For frequency-coded SSVEP BCIs, it has been shown that dynamically adjusting the trial duration can increase the system’s information transfer rate (ITR). We therefore investigated whether a similar increase could be achieved for spatially-coded BCIs by applying dynamic stopping methods. To this end we introduced a new stopping criterion which combines the likelihood of the classification result and its stability across larger data windows. Whereas the BCI achieved an average ITR of 28.4±6.4 bits/min with fixed intervals, dynamic intervals increased the performance to 81.1±44.4 bits/min. Users were able to maintain performance up to 60 minutes of continuous operation. We suggest that the dynamic response time might have worked as a kind of temporal feedback which allowed operators to optimize their brain signals and compensate fatigue.
... In such a reactive paradigm, neural modulations are exogenously generated by specific stimulations provided by the BCI system (e.g., Höhne et al., 2011). Thus, EEG-based BCIs rely on visual or auditory evoked potentials such as the P300 eventrelated potential (ERP) that occurs 300 ms after an important event (see Jin et al., 2012;Lin et al., 2018), the error-related potential (ErrP) that occurs around 200 ms after a mistake (e.g., Dal Seno et al., 2010;Yousefi et al., 2018) or steady state evoked potentials (SSEP) that are induced by oscillating stimuli (e.g., Chen et al., 2017). Interestingly, some of these reactive settings do rely on neural prediction mechanisms. ...
Recent years have been marked by the fulgurant expansion of non-invasive Brain-Computer Interface (BCI) devices and applications in various contexts (medical, industrial etc.). This technology allows agents “to directly act with thoughts,” bypassing the peripheral motor system. Interestingly, it is worth noting that typical non-invasive BCI paradigms remain distant from neuroscientific models of human voluntary action. Notably, bidirectional links between action and perception are constantly ignored in BCI experiments. In the current perspective article, we proposed an innovative BCI paradigm that is directly inspired by the ideomotor principle, which postulates that voluntary actions are driven by the anticipated representation of forthcoming perceptual effects. We believe that (1) adapting BCI paradigms could allow simple action-effect bindings and consequently action-effect predictions and (2) using neural underpinnings of those action-effect predictions as features of interest in AI methods, could lead to more accurate and naturalistic BCI-mediated actions.
... Firstly, while using an active BCI, the agent must intentionally modulate their brain activity to bring out neural characteristics that will become identifiable after mathematical processing and classification, as Motor Imagery (MI) paradigm (e.g., Salvaris, 2014). Secondly, reactive BCI relies on neural activity that is typically triggered by an external stimulus-mostly visual or auditory-and that evokes brain responses, such as P300 event-related potential (ERP) (e.g., Jin et al., 2012) or Steady State Evoked Potentials (SSEP) (e.g., Chen et al., 2017). Thirdly, passive BCI relies on brain activity which is not voluntarily modulated by the user, in order to evaluate psychological states such as drowsiness (e.g., Hongfei et al., 2011;Dehais et al., 2018), frustration, or even cognitive load (e.g., Roy et al., 2013;Myrden and Chau, 2017). ...
In the last few decades, Brain-Computer Interface (BCI) research has focused predominantly on clinical applications, notably to enable severely disabled people to interact with the environment. However, recent studies rely mostly on the use of non-invasive electroencephalographic (EEG) devices, suggesting that BCI might be ready to be used outside laboratories. In particular, Industry 4.0 is a rapidly evolving sector that aims to restructure traditional methods by deploying digital tools and cyber-physical systems. BCI-based solutions are attracting increasing attention in this field to support industrial performance by optimizing the cognitive load of industrial operators, facilitating human-robot interactions, and make operations in critical conditions more secure. Although these advancements seem promising, numerous aspects must be considered before developing any operational solutions. Indeed, the development of novel applications outside optimal laboratory conditions raises many challenges. In the current study, we carried out a detailed literature review to investigate the main challenges and present criteria relevant to the future deployment of BCI applications for Industry 4.0.
... In multi-target experiments, different targets have different spatial positions, and other targets are usually located around the stimulus target. Furthermore, the difference in the spatial location of visual stimuli and the stimulation of the peripheral vision will affect the response of the central visual field [37][38][39] . However, the influence of spatial information was not included in the signal model, so that the transferred SSVEP template could not accurately contain the response under multi-target stimulation, which decreased the performance of the proposed transfer algorithm. ...
In general, a large amount of training data can effectively improve the classification performance of the Steady-State Visually Evoked Potential (SSVEP)-based Brain-Computer Interface (BCI) system. However, it will prolong the training time and considerably restrict the practicality of the system. This study proposed a SSVEP nonlinear signal model based on the Volterra filter, which could reconstruct stable reference signals using relatively small number of training targets by transfer learning, thereby reducing the training cost of SSVEP-BCI. Moreover, this study designed a transfer-extended Canonical Correlation Analysis (t-eCCA) method based on the model to achieve cross-target transfer. As a result, in a single-target SSVEP experiment with 16 stimulus frequencies, t-eCCA obtained an average accuracy of 86.96%±12.87% across 12 subjects using only half of the calibration time, which exhibited no significant difference from the representative training classification algorithms, namely, extended canonical correlation analysis (88.32%±13.97%) and task-related component analysis (88.92%±14.44%), and was significantly higher than that of the classic non-training algorithms, namely, Canonical Correlation Analysis (CCA) as well as filter-bank CCA. Results showed that the proposed cross-target transfer algorithm t-eCCA could fully utilize the information about the targets and its stimulus frequencies and effectively reduce the training time of SSVEP-BCI.
... Thus, the subject must focus on the stimulus that flicks at the frequency corresponding to the command it intends to communicate. Using this kind of paradigm, communication systems based on spellers Chen et al. (2015), control systems for electric prostheses Muller-Putz and Pfurtscheller (2007) and exoskeletons Kwak, Müller, and Lee (2015), but also interaction systems for computer games Chen, Zhang, Engel, Gong, and Maye (2017) have been designed. ...
This work presents a supervised machine-learning approach to build an expert system that provides support to the neuroscientist in automatically classifying ERP data and matching them with a multisensorial alphabet of stimuli. To do this, two different approaches are considered: a hierarchical tree-based algorithm, XGBoost, and feedfoward neural networks, highlighting the pros and cons of both approaches in the different steps of the classification task. Moreover, the sensitivity of the classification capabilities of the tool as a function of the number of available electrodes is also studied, highlighting what can be achieved by applying the method using commercial, wearable EEG systems. The main novelty of this work consists in significantly enlarging the pool of stimuli that the expert system can recognize and comprising different, possibly mixed, sensorial domains. The obtained results open the way to the design of portable devices for augmented communication systems, which can be of particular interest for the development of advanced Brain-Computer Interfaces (BCI) for communication with different types of neurologically impaired patients.
