EEG-based Based Brain-computer Interfaces Research Articles

Exploring inter-trial coherence for inner speech classification in EEG-based brain–computer interface

Objective. In recent years, electroencephalogram (EEG)-based brain–computer interfaces (BCIs) applied to inner speech classification have gathered attention for their potential to provide a communication channel for individuals with speech disabilities. However, existing methodologies for this task fall short in achieving acceptable accuracy for real-life implementation. This paper concentrated on exploring the possibility of using inter-trial coherence (ITC) as a feature extraction technique to enhance inner speech classification accuracy in EEG-based BCIs. Approach. To address the objective, this work presents a novel methodology that employs ITC for feature extraction within a complex Morlet time-frequency representation. The study involves a dataset comprising EEG recordings of four different words for ten subjects, with three recording sessions per subject. The extracted features are then classified using k-nearest-neighbors (kNNs) and support vector machine (SVM). Main results. The average classification accuracy achieved using the proposed methodology is 56.08% for kNN and 59.55% for SVM. These results demonstrate comparable or superior performance in comparison to previous works. The exploration of inter-trial phase coherence as a feature extraction technique proves promising for enhancing accuracy in inner speech classification within EEG-based BCIs. Significance. This study contributes to the advancement of EEG-based BCIs for inner speech classification by introducing a feature extraction methodology using ITC. The obtained results, on par or superior to previous works, highlight the potential significance of this approach in improving the accuracy of BCI systems. The exploration of this technique lays the groundwork for further research toward inner speech decoding.

Emotion recognition with EEG-based brain-computer interfaces: a systematic literature review

AbstractElectroencephalography (EEG)-based Brain-Computer Interface (BCI) systems for emotion recognition have the potential to assist the enrichment of human–computer interaction with implicit information since they can enable understanding of the cognitive and emotional activities of humans. Therefore, these systems have become an important research topic today. This study aims to present trends and gaps on this topic by performing a systematic literature review based on the 216 published scientific literature gathered from various databases including ACM, IEEE Xplore, PubMed, Science Direct, and Web of Science from 2016 to 2020. This review gives an overview of all the components of EEG based BCI system from the signal stimulus module which includes the employed device, signal stimuli, and data processing modality, to the signal processing module which includes signal acquisition, pre-processing, feature extraction, feature selection, classification algorithms, and performance evaluation. Thus, this study provides an overview of all components of an EEG-based BCI system for emotion recognition and examines the available evidence in a clear, concise, and systematic way. In addition, the findings are aimed to inform researchers about the issues on what are research trends and the gaps in this field and guide them in their research directions.

T-TIME: Test-Time Information Maximization Ensemble for Plug-and-Play BCIs.

An electroencephalogram (EEG)-based brain-computer interface (BCI) enables direct communication between the human brain and a computer. Due to individual differences and non-stationarity of EEG signals, such BCIs usually require a subject-specific calibration session before each use, which is time-consuming and user-unfriendly. Transfer learning (TL) has been proposed to shorten or eliminate this calibration, but existing TL approaches mainly consider offline settings, where all unlabeled EEG trials from the new user are available. This article proposes Test-Time Information Maximization Ensemble (T-TIME) to accommodate the most challenging online TL scenario, where unlabeled EEG data from the new user arrive in a stream, and immediate classification is performed. T-TIME initializes multiple classifiers from the aligned source data. When an unlabeled test EEG trial arrives, T-TIME first predicts its labels using ensemble learning, and then updates each classifier by conditional entropy minimization and adaptive marginal distribution regularization. Our code is publicized. Extensive experiments on three public motor imagery based BCI datasets demonstrated that T-TIME outperformed about 20 classical and state-of-the-art TL approaches. To our knowledge, this is the first work on test time adaptation for calibration-free EEG-based BCIs, making plug-and-play BCIs possible.

Alignment-Based Adversarial Training (ABAT) for Improving the Robustness and Accuracy of EEG-Based BCIs.

Machine learning has achieved great success in electroencephalogram (EEG) based brain-computer interfaces (BCIs). Most existing BCI studies focused on improving the decoding accuracy, with only a few considering the adversarial security. Although many adversarial defense approaches have been proposed in other application domains such as computer vision, previous research showed that their direct extensions to BCIs degrade the classification accuracy on benign samples. This phenomenon greatly affects the applicability of adversarial defense approaches to EEG-based BCIs. To mitigate this problem, we propose alignment-based adversarial training (ABAT), which performs EEG data alignment before adversarial training. Data alignment aligns EEG trials from different domains to reduce their distribution discrepancies, and adversarial training further robustifies the classification boundary. The integration of data alignment and adversarial training can make the trained EEG classifiers simultaneously more accurate and more robust. Experiments on five EEG datasets from two different BCI paradigms (motor imagery classification, and event related potential recognition), three convolutional neural network classifiers (EEGNet, ShallowCNN and DeepCNN) and three different experimental settings (offline within-subject cross-block/-session classification, online cross-session classification, and pre-trained classifiers) demonstrated its effectiveness. It is very intriguing that adversarial attacks, which are usually used to damage BCI systems, can be used in ABAT to simultaneously improve the model accuracy and robustness.

The Promotoer, a brain-computer interface-assisted intervention to promote upper limb functional motor recovery after stroke: a statistical analysis plan for a randomized controlled trial

BackgroundElectroencephalography (EEG)-based brain-computer interfaces (BCIs) allow to modulate the sensorimotor rhythms and are emerging technologies for promoting post-stroke motor function recovery. The Promotoer study aims to assess the short and long-term efficacy of the Promotoer system, an EEG-based BCI assisting motor imagery (MI) practice, in enhancing post-stroke functional hand motor recovery. This paper details the statistical analysis plan of the Promotoer study.MethodsThe Promotoer study is a randomized, controlled, assessor-blinded, single-centre, superiority trial, with two parallel groups and a 1:1 allocation ratio. Subacute stroke patients are randomized to EEG-based BCI-assisted MI training or to MI training alone (i.e. no BCI). An internal pilot study for sample size re-assessment is planned. The primary outcome is the effectiveness of the Upper Extremity Fugl-Meyer Assessment (UE-FMA) score. Secondary outcomes include clinical, functional, and user experience scores assessed at the end of intervention and at follow-up. Neurophysiological assessments are also planned. Effectiveness formulas have been specified, and intention-to-treat and per-protocol populations have been defined. Statistical methods for comparisons of groups and for development of a predictive score of significant improvement are described. Explorative subgroup analyses and methodology to handle missing data are considered.DiscussionThe Promotoer study will provide robust evidence for the short/long-term efficacy of the Promotoer system in subacute stroke patients undergoing a rehabilitation program. Moreover, the development of a predictive score of response will allow transferring of the Promotoer system to optimal clinical practice. By carefully describing the statistical principles and procedures, the statistical analysis plan provides transparency in the analysis of data.Trial registrationClinicalTrials.gov NCT04353297. Registered on April 15, 2020.

Multi-Class Transfer Learning and Domain Selection for Cross-Subject EEG Classification

Transfer learning (TL) has been proven to be one of the most significant techniques for cross-subject classification in electroencephalogram (EEG)-based brain-computer interfaces (BCI). Hence, it is widely used to address the challenges of cross-session and cross-subject variability with more accurate intention prediction. In this case, TL utilizes knowledge (signal features) in the source domain(s) to improve the classification in the target domain. However, current existing transfer learning approaches on EEG-based BCI are mostly limited to two-class cross-subject classification problems, while multi-class problems are only implemented with a focus on within-subject classification due to the complexity of multi-class cross-subject classification problems. In this paper, we first extended the transfer learning approaches to a multi-class cross-subject scenario, then investigated the reason for transfer learning performance being poor in multi-class cross-subject classification. Secondly, we address the challenge of significant sessional and subject-to-subject variations originating from both known and unknown factors. It is discovered that such variations have a massive influence on the classification because of the negative transfer (NT) across domains. Based on this discovery, we propose a multi-class transfer learning approach based on multi-source manifold feature transfer learning (MMFT) framework and an enhanced version to minimize the effects of NT. The proposed multi-class transfer learning approach extends the existing MMFT to multi-class cases. Then enhanced multi-class MMFT firstly searches for domains with high transferability and selects only the best combination among source domains (SD), then utilize the best-selected combination of domains for transfer learning. Experimental results illustrate that the proposed multi-class MMFT can be employed in the cross-subject classification of both three-class and four-class problems. Experimental results also demonstrated that the enhanced multi-class MMFT could effectively minimize the effect of negative transfer and significantly increase the prediction rates across individual target domains (TD). The highest classification accuracy (CA) of 98% is obtained by the enhanced multi-class MMFT.

Raw Electroencephalogram-Based Cognitive Workload Classification Using Directed and Nondirected Functional Connectivity Analysis and Deep Learning.

With the phenomenal rise in internet-of-things devices, the use of electroencephalogram (EEG) based brain-computer interfaces (BCIs) can empower individuals to control equipment with thoughts. These allow BCI to be used and pave the way for pro-active health management and the development of internet-of-medical-things architecture. However, EEG-based BCIs have low fidelity, high variance, and EEG signals are very noisy. These challenges compel researchers to design algorithms that can process big data in real-time while being robust to temporal variations and other variations in the data. Another issue in designing a passive BCI is the regular change in user's cognitive state (measured through cognitive workload). Though considerable amount of research has been conducted on this front, methods that could withstand high variability in EEG data and still reflect the neuronal dynamics of cognitive state variations are lacking and much needed in literature. In this research, we evaluate the efficacy of a combination of functional connectivity algorithms and state-of-the-art deep learning algorithms for the classification of three different levels of cognitive workload. We acquire 64-channel EEG data from 23 participants executing the n-back task at three different levels; 1-back (low-workload condition), 2-back (medium-workload condition), and 3-back (high-workload condition). We compared two different functional connectivity algorithms, namely phase transfer entropy (PTE) and mutual information (MI). PTE is a directed functional connectivity algorithm, whereas MI is non-directed. Both methods are suitable for extracting functional connectivity matrices in real-time, which could eventually be used for rapid, robust, and efficient classification. For classification, we use the recently proposed BrainNetCNN deep learning model, designed specifically to classify functional connectivity matrices. Results reveal a classification accuracy of 92.81% with MI and BrainNetCNN and a staggering 99.50% with PTE and BrainNetCNN on test data. PTE can yield a higher classification accuracy due to its robustness to linear mixing of the data and its ability to detect functional connectivity across a range of analysis lags.

A hybrid steady-state visual evoked response-based brain-computer interface with MEG and EEG

While recent developments in electroencephalogram (EEG)-based brain-computer interfaces (BCIs) have enabled a bridge between the brain and external devices with relatively high communication speed, there is still room for improvement. Notably, the phenomenon of “BCI illiteracy,” which refers to the 15%–30% of people who struggle to type or control devices using BCI, remains unsolved, limiting the practical application of BCI systems. The EEG-based BCIs performance is constrained by the low-quality scalp EEG signals due to the attenuation and distortion of the skull. To address these limitations, this study proposes a hybrid BCI system combining EEG with magnetoencephalogram (MEG), a neuroimaging technology not influenced by the volume conduction effect, to boost BCI performance by enhancing signal quality. Comparative experiments involving 22 subjects showed that the steady-state visual evoked response (SSVER) from MEG has a wider range of effective bandwidth and higher signal-to-noise ratio than EEG. Moreover, differences in the spectral and spatiotemporal characteristics of MEG and EEG explain better performance. Simultaneous MEG-EEG recording experiments suggested that the hybrid MEG-EEG BCI achieved a significantly higher information transfer rate than either modality alone (hybrid: 312 ± 17 bits/min, MEG: 272 ± 17 bits/min, EEG: 240 ± 27 bits/min). Moreover, the 40-target classification accuracy of “BCI illiterate” increased from 50% to 95% with the help of MEG. These results highlight the methodological advantages of a hybrid MEG-EEG BCI, suggesting a promising paradigm for implementing high-speed BCIs.

Adversarial robustness benchmark for EEG-based brain–computer interfaces

Many machine learning approaches have been successfully applied to electroencephalogram (EEG) based brain–computer interfaces (BCIs). Most existing approaches focused on making EEG-based BCIs more accurate, but few have considered their security. Recent studies have shown that EEG-based BCIs are vulnerable to adversarial attacks. To our knowledge, there is no study on adversarial defenses in EEG-based BCIs. This paper, for the first time, explores multiple classical and state-of-the-art adversarial defense approaches in EEG-based BCIs. Specifically, we demonstrated the performances of nine adversarial defense approaches on three convolutional neural networks and two EEG datasets, and established a comprehensive benchmark to evaluate their effectiveness in BCIs. Based on the evaluation results, we drew some key observations, hoping to inspire future adversarial defense research and attract more attention to the adversarial security of EEG-based BCIs.

A Review of Online Classification Performance in Motor Imagery-Based Brain–Computer Interfaces for Stroke Neurorehabilitation

Motor imagery (MI)-based brain–computer interfaces (BCI) have shown increased potential for the rehabilitation of stroke patients; nonetheless, their implementation in clinical practice has been restricted due to their low accuracy performance. To date, although a lot of research has been carried out in benchmarking and highlighting the most valuable classification algorithms in BCI configurations, most of them use offline data and are not from real BCI performance during the closed-loop (or online) sessions. Since rehabilitation training relies on the availability of an accurate feedback system, we surveyed articles of current and past EEG-based BCI frameworks who report the online classification of the movement of two upper limbs in both healthy volunteers and stroke patients. We found that the recently developed deep-learning methods do not outperform the traditional machine-learning algorithms. In addition, patients and healthy subjects exhibit similar classification accuracy in current BCI configurations. Lastly, in terms of neurofeedback modality, functional electrical stimulation (FES) yielded the best performance compared to non-FES systems.

Cross-modal guiding and reweighting network for multi-modal RSVP-based target detection

Rapid Serial Visual Presentation (RSVP) based Brain–Computer Interface (BCI) facilities the high-throughput detection of rare target images by detecting evoked event-related potentials (ERPs). At present, the decoding accuracy of the RSVP-based BCI system limits its practical applications. This study introduces eye movements (gaze and pupil information), referred to as EYE modality, as another useful source of information to combine with EEG-based BCI and forms a novel target detection system to detect target images in RSVP tasks. We performed an RSVP experiment, recorded the EEG signals and eye movements simultaneously during a target detection task, and constructed a multi-modal dataset including 20 subjects. Also, we proposed a cross-modal guiding and fusion network to fully utilize EEG and EYE modalities and fuse them for better RSVP decoding performance. In this network, a two-branch backbone was built to extract features from these two modalities. A Cross-Modal Feature Guiding (CMFG) module was proposed to guide EYE modality features to complement the EEG modality for better feature extraction. A Multi-scale Multi-modal Reweighting (MMR) module was proposed to enhance the multi-modal features by exploring intra- and inter-modal interactions. And, a Dual Activation Fusion (DAF) was proposed to modulate the enhanced multi-modal features for effective fusion. Our proposed network achieved a balanced accuracy of 88.00% (±2.29) on the collected dataset. The ablation studies and visualizations revealed the effectiveness of the proposed modules. This work implies the effectiveness of introducing the EYE modality in RSVP tasks. And, our proposed network is a promising method for RSVP decoding and further improves the performance of RSVP-based target detection systems.

EEG-Based Brain–Computer Interfaces are Vulnerable to Backdoor Attacks

Research and development of electroencephalogram (EEG) based brain-computer interfaces (BCIs) have advanced rapidly, partly due to deeper understanding of the brain and wide adoption of sophisticated machine learning approaches for decoding the EEG signals. However, recent studies have shown that machine learning algorithms are vulnerable to adversarial attacks. This paper proposes to use narrow period pulse for poisoning attack of EEG-based BCIs, which makes adversarial attacks much easier to implement. One can create dangerous backdoors in the machine learning model by injecting poisoning samples into the training set. Test samples with the backdoor key will then be classified into the target class specified by the attacker. What most distinguishes our approach from previous ones is that the backdoor key does not need to be synchronized with the EEG trials, making it very easy to implement. The effectiveness and robustness of the backdoor attack approach is demonstrated, highlighting a critical security concern for EEG-based BCIs and calling for urgent attention to address it.

Investigating User Proficiency of Motor Imagery for EEG-Based BCI System to Control Simulated Wheelchair.

The research on the electroencephalography (EEG)-based brain-computer interface (BCI) is widely utilized for wheelchair control. The ability of the user is one factor of BCI efficiency. Therefore, we focused on BCI tasks and protocols to yield high efficiency from the robust EEG features of individual users. This study proposes a task-based brain activity to gain the power of the alpha band, which included eyes closed for alpha response at the occipital area, attention to an upward arrow for alpha response at the frontal area, and an imagined left/right motor for alpha event-related desynchronization at the left/right motor cortex. An EPOC X neuroheadset was used to acquire the EEG signals. We also proposed user proficiency in motor imagery sessions with limb movement paradigms by recommending motor imagination tasks. Using the proposed system, we verified the feature extraction algorithms and command translation. Twelve volunteers participated in the experiment, and the conventional paradigm of motor imagery was used to compare the efficiencies. With utilized user proficiency in motor imagery, an average accuracy of 83.7% across the left and right commands was achieved. The recommended MI paradigm via user proficiency achieved an approximately 4% higher accuracy than the conventional MI paradigm. Moreover, the real-time control results of a simulated wheelchair revealed a high efficiency based on the time condition. The time results for the same task as the joystick-based control were still approximately three times longer. We suggest that user proficiency be used to recommend an individual MI paradigm for beginners. Furthermore, the proposed BCI system can be used for electric wheelchair control by people with severe disabilities.

Privacy-Preserving Domain Adaptation for Motor Imagery-Based Brain-Computer Interfaces.

Electroencephalogram (EEG) is one of the most widely used signals in motor imagery (MI) based brain-computer interfaces (BCIs). Domain adaptation has been frequently used to improve the accuracy of EEG-based BCIs for a new user (target domain), by making use of labeled data from a previous user (source domain). However, this raises privacy concerns, as EEG contains sensitive health and mental information. It is very important to perform privacy-preserving domain adaptation, which simultaneously improves the classification accuracy for a new user and protects the privacy of a previous user. We propose augmentation-based source-free adaptation (ASFA), which consists of two parts: 1) source model training, where a novel data augmentation approach is proposed for MI EEG signals to improve the cross-subject generalization performance of the source model; and, 2) target model training, which simultaneously considers uncertainty reduction for domain adaptation and consistency regularization for robustness. ASFA only needs access to the source model parameters, instead of the raw EEG data, thus protecting the privacy of the source domain. We further extend ASFA to a stricter privacy-preserving scenario, where the source model's parameters are also inaccessible. Experimental results on four MI datasets demonstrated that ASFA outperformed 15 classical and state-of-the-art MI classification approaches. This is the first work on completely source-free domain adaptation for EEG-based BCIs. Our proposed ASFA achieves high classification accuracy and strong privacy protection simultaneously, important for the commercial applications of EEG-based BCIs.

Meta-Learning for Fast and Privacy-Preserving Source Knowledge Transfer of EEG-Based BCIs

Electroencephalogram (EEG) based brain-computer interfaces (BCIs) are used in many applications, due to their low-risk, low-cost, and convenience. Because of EEG’s high variations across subjects and sessions, a long calibration session is usually needed to adjust the system before each use, which is time-consuming and user-unfriendly. Though various machine learning approaches have been proposed to cope with this problem, none of them considered individual differences, data scarcity and data privacy simultaneously. In this paper, a Multi-Domain Model-Agnostic Meta-Learning (MDMAML) approach is proposed to address challenging cross-subject, few-shot and source-free (privacy protection) classification tasks in EEG-based BCIs. Experiments on four datasets from two different BCI paradigms demonstrated that MDMAML outperformed several classical and state-of-the-art approaches in both online and offline applications.

SSVEP-Based Emotion Recognition for IoT via Multiobjective Neural Architecture Search

Emotion recognition is one of the significant research areas and applications of electroencephalography (EEG)-based brain–computer interface (BCI), which is widely concerned in the Internet of Things (IoT) framework. Steady-state visual evoked potential (SSVEP) is frequently used in EEG-based BCI (EEG-BCI) due to its high signal-to-noise ratio and short response time. However, there are few related studies and applications on the emotional features of SSVEP. In this article, we build an SSVEP-based BCI (SSVEP-BCI) for affective computing in the IoT system and utilize neural architecture search (NAS) to analyze the emotional information of SSVEP signals. Our proposed NAS is capable of optimizing the classification performance and model size of the deep neural networks simultaneously, thus enhancing the sentiment analysis accuracy for SSVEP and improving the response speed of the actual BCI system for IoT implementation. Furthermore, we employ network morphism and Bayesian optimization in the offspring generation algorithm of the NAS framework to apply knowledge inheritance and performance estimation for the child models, respectively. The experimental results show that the proposed NAS outperforms the baseline models in terms of accuracy and model size for valence and arousal dimensions. Moreover, the offspring generation algorithm is able to promote the search efficiency of NAS.

A Comprehensive Review of Endogenous EEG-Based BCIs for Dynamic Device Control.

Electroencephalogram (EEG)-based brain–computer interfaces (BCIs) provide a novel approach for controlling external devices. BCI technologies can be important enabling technologies for people with severe mobility impairment. Endogenous paradigms, which depend on user-generated commands and do not need external stimuli, can provide intuitive control of external devices. This paper discusses BCIs to control various physical devices such as exoskeletons, wheelchairs, mobile robots, and robotic arms. These technologies must be able to navigate complex environments or execute fine motor movements. Brain control of these devices presents an intricate research problem that merges signal processing and classification techniques with control theory. In particular, obtaining strong classification performance for endogenous BCIs is challenging, and EEG decoder output signals can be unstable. These issues present myriad research questions that are discussed in this review paper. This review covers papers published until the end of 2021 that presented BCI-controlled dynamic devices. It discusses the devices controlled, EEG paradigms, shared control, stabilization of the EEG signal, traditional machine learning and deep learning techniques, and user experience. The paper concludes with a discussion of open questions and avenues for future work.

Friend-guard adversarial noise designed for electroencephalogram-based brain–computer interface spellers

An electroencephalogram (EEG)–based brain–computer interface (BCI) speller is a system that conveys thought to enable communication between humans and computers using brain conduction. This system is useful for patients with severe disabilities and provides a way for them to communicate with computers or with other people. The EEG-based BCI speller system is being studied in various ways, but it is vulnerable to adversarial examples. An adversarial example is an attack sample created by adding a little noise to an original sample in such a way that it appears normal to humans but will be misclassified by the model. Adversarial examples can be useful in situations such as military scenarios in which there is a mixture of friendly models and enemy models. When a friendly BCI speller and an enemy BCI speller coexist, an adversarial example may be mistakenly taken by the enemy BCI speller to signal an incorrect intention on the part of the person with a disability; in another scenario, an enemy BCI speller may leak personal information of the individual with a disability or initiate unwanted financial transactions. In this paper, we propose a method to create such a sample, called a “friend-guard” EEG adversarial example. In the proposed method, a very small EEG signal is added to an original sample, creating an adversarial example that the friendly model will classify correctly but the enemy model will classify incorrectly. A P300 dataset was used in the experimental evaluation of the method, and linear regression models were used as target models. In the experiment, the proposed method was able to generate friend-guard EEG adversarial examples that were incorrectly classified with success rates of 88.4% and 69.7% by the enemy model for subject A and subject B, respectively, while maintaining the accuracy of the friendly model at 85.9% and 74.4% for subjects A and B, respectively.

A P300-Detection Method Based on Logistic Regression and a Convolutional Neural Network.

BackgroundElectroencephalogram (EEG)-based brain-computer interface (BCI) systems are widely utilized in various fields, including health care, intelligent assistance, identity recognition, emotion recognition, and fatigue detection. P300, the main event-related potential, is the primary component detected by EEG-based BCI systems. Existing algorithms for P300 classification in EEG data usually perform well when tested in a single participant, although they exhibit significant decreases in accuracy when tested in new participants. We attempted to address this lack of generalizability associated with existing classification methods using a novel convolutional neural network (CNN) model developed using logistic regression (LR).Materials and MethodsWe proposed an LR-CNN model comprising two parts: a combined LR-based memory model and a CNN-based generalization model. The LR-based memory model can learn the individual features of participants and addresses the decrease in accuracy caused by individual differences when applied to new participants. The CNN-based generalization model can learn the common features among participants, thereby reducing overall classification bias and improving overall classification accuracy.ResultsWe compared our method with existing, commonly used classification methods through three different sets of experiments. The experimental results indicated that our method could learn individual differences among participants. Compared with other commonly used classification methods, our method yielded a marked improvement (>90%) in classification among new participants.ConclusionThe accuracy of the proposed model in the face of new participants is better than that of existing, commonly used classification methods. Such improvements in cross-subject test accuracy will aid in the development of BCI systems.

Past, Present, and Future of EEG-Based BCI Applications.

An electroencephalography (EEG)-based brain–computer interface (BCI) is a system that provides a pathway between the brain and external devices by interpreting EEG. EEG-based BCI applications have initially been developed for medical purposes, with the aim of facilitating the return of patients to normal life. In addition to the initial aim, EEG-based BCI applications have also gained increasing significance in the non-medical domain, improving the life of healthy people, for instance, by making it more efficient, collaborative and helping develop themselves. The objective of this review is to give a systematic overview of the literature on EEG-based BCI applications from the period of 2009 until 2019. The systematic literature review has been prepared based on three databases PubMed, Web of Science and Scopus. This review was conducted following the PRISMA model. In this review, 202 publications were selected based on specific eligibility criteria. The distribution of the research between the medical and non-medical domain has been analyzed and further categorized into fields of research within the reviewed domains. In this review, the equipment used for gathering EEG data and signal processing methods have also been reviewed. Additionally, current challenges in the field and possibilities for the future have been analyzed.