A comprehensive review of EEG-based brain–computer interface paradigms

Journal of Neural Engineering, Journal Year: 2018, Volume and Issue: 16(1), P. 011001 - 011001

Published: Nov. 15, 2018

Advances in brain science and computer technology the past decade have led to exciting developments brain-computer interface (BCI), thereby making BCI a top research area applied science. The renaissance of opens new methods neurorehabilitation for physically disabled people (e.g. paralyzed patients amputees) with injuries stroke patients). Recent technological advances such as wireless recording, machine learning analysis, real-time temporal resolution increased interest electroencephalographic (EEG) based approaches. Many studies focused on decoding EEG signals associated whole-body kinematics/kinetics, motor imagery, various senses. Thus, there is need understand experimental paradigms used EEG-based systems. Moreover, given that are many available options, it essential choose most appropriate application properly manipulate neuroprosthetic or device. current review evaluates regarding their advantages disadvantages from variety perspectives. For each paradigm, algorithms classification evaluated. applications these targeted summarized. Finally, potential problems systems discussed, possible solutions proposed.

Language: Английский

---

EEG-Based Brain-Computer Interfaces (BCIs): A Survey of Recent Studies on Signal Sensing Technologies and Computational Intelligence Approaches and Their Applications

IEEE/ACM Transactions on Computational Biology and Bioinformatics, Journal Year: 2021, Volume and Issue: 18(5), P. 1645 - 1666

Published: Aug. 25, 2021

Brain-Computer interfaces (BCIs) enhance the capability of human brain activities to interact with environment. Recent advancements in technology and machine learning algorithms have increased interest electroencephalographic (EEG)-based BCI applications. EEG-based intelligent systems can facilitate continuous monitoring fluctuations cognitive states under monotonous tasks, which is both beneficial for people need healthcare support general researchers different domain areas. In this review, we survey recent literature on EEG signal sensing technologies computational intelligence approaches applications, compensating gaps systematic summary past five years. Specifically, first review current status collecting reliable signals. Then, demonstrate state-of-the-art techniques, including fuzzy models transfer deep algorithms, detect, monitor, maintain task performance prevalent Finally, present a couple innovative BCI-inspired applications discuss future research directions research.

Language: Английский

---

Functional Near-Infrared Spectroscopy and Its Clinical Application in the Field of Neuroscience: Advances and Future Directions

Frontiers in Neuroscience, Journal Year: 2020, Volume and Issue: 14

Published: July 9, 2020

Similar to functional magnetic resonance imaging (fMRI), near-infrared spectroscopy (fNIRS) detects the changes of hemoglobin species inside brain, but via differences in optical absorption. Within spectrum, light can penetrate biological tissues and be absorbed by chromophores, such as oxyhemoglobin deoxyhemoglobin. What makes fNIRS more advantageous is its portability potential for long-term monitoring. This paper reviews basic mechanisms current clinical applications, limitations toward widespread usage fNIRS, efforts improve temporal spatial resolution robust within subjects. Oligochannel adequate estimating global cerebral function it has become an important tool critical care setting evaluating oxygenation autoregulation patients with stroke traumatic brain injury. When comes a sophisticated utilization, becomes critical. Multichannel NIRS improved mapping certain task modalities, language mapping. However, averaging group analysis are currently required, limiting use monitoring real-time event detection individual Advances signal processing have moved detecting types seizures, assessing autonomic cortical spreading depression. lack accuracy precision been major obstacle fNIRS. The high-density whole head optode arrays, precise sensor locations relative head, anatomical co-registration, short-distance channels, multi-dimensional combined sensitivity increase wide-spread assessment function.

Language: Английский

---

Feature Extraction and Classification Methods for Hybrid fNIRS-EEG Brain-Computer Interfaces

Frontiers in Human Neuroscience, Journal Year: 2018, Volume and Issue: 12

Published: June 28, 2018

In this study, a brain-computer interface (BCI) framework for hybrid functional near-infrared spectroscopy (fNIRS) and electroencephalography (EEG) locked-in syndrome (LIS) patients is investigated. Brain tasks, channel selection methods, feature extraction classification algorithms available in the literature are reviewed. First, we categorize various types of with cognitive motor impairments to assess suitability BCI each them. The prefrontal cortex identified as suitable brain region imaging. Second, activity that contributes generation hemodynamic signals Mental arithmetic word formation tasks found be use LIS patients. Third, since specific targeted needed BCI, methods determining interest combination bundled-optode configuration threshold-integrated vector phase analysis turns out promising solution. Fourth, usable fNIRS features EEG For signal peak mean highest band powers promising. classification, linear discriminant has been most widely used. However, further research on classifier multiple commands desirable. Overall, proper identification will improve accuracy. conclusion, five future issues identified, new scheme, including therapy using fNIRS-EEG provided.

Language: Английский

---

Deep learning for hybrid EEG-fNIRS brain–computer interface: application to motor imagery classification

Journal of Neural Engineering, Journal Year: 2018, Volume and Issue: 15(3), P. 036028 - 036028

Published: Feb. 15, 2018

Objective. Brain–computer interface (BCI) refers to procedures that link the central nervous system a device. BCI was historically performed using electroencephalography (EEG). In last years, encouraging results were obtained by combining EEG with other neuroimaging technologies, such as functional near infrared spectroscopy (fNIRS). A crucial step of is brain state classification from recorded signal features. Deep artificial neural networks (DNNs) recently reached unprecedented complex outcomes. These performances achieved through increased computational power, efficient learning algorithms, valuable activation functions, and restricted or back-fed neurons connections. By expecting significant overall performances, we investigated capabilities fNIRS recordings state-of-the-art deep procedures. Approach. We guided left right hand motor imagery task on 15 subjects fixed response time 1 s experiment length 10 min. Left versus accuracy DNN in multi-modal recording modality estimated it compared standalone classifiers. Main results. At group level increase performance when considering classifier synergistic effect. Significance. can be significantly improved employing provide electrical hemodynamic activity information, combination advanced non-linear

Language: Английский

---

A Systemic Review of Functional Near-Infrared Spectroscopy for Stroke: Current Application and Future Directions

Frontiers in Neurology, Journal Year: 2019, Volume and Issue: 10

Published: Feb. 5, 2019

Survivors of stroke often experience significant disability and impaired quality life. The recovery motor or cognitive function requires long periods. Neuroimaging could measure changes in the brain monitor process order to offer timely treatment assess effects therapy. A novel neuroimaging noninvasive technique NIRS with its ambulatory, portable, low-cost nature without fixation subjects has attracted extensive attention. We conducted a comprehensive literature review use post-stroke patients. Overall, we reviewed 61 papers. wide range application, including monitoring upper limb, lower limb recovery, learning, cortical cerebral hemodynamic changes, oxygenation, as well therapeutic method, clinical researches evaluation risk for stroke. Among them, shown great potential monitoring, research tool. Further studies give more emphasize on combination other techniques utility prevention

Language: Английский

---

An EEG/EMG/EOG-Based Multimodal Human-Machine Interface to Real-Time Control of a Soft Robot Hand

Frontiers in Neurorobotics, Journal Year: 2019, Volume and Issue: 13

Published: March 29, 2019

Brain-computer interface (BCI) technology shows potential for application to motor rehabilitation therapies that use neural plasticity restore function and improve quality of life stroke survivors. However, it is often difficult BCI systems provide the variety control commands necessary multi-task real-time soft robot naturally. In this study, a novel multimodal human-machine system (mHMI) developed using combinations electrooculography (EOG), electroencephalography (EEG), electromyogram (EMG) generate numerous instructions. Moreover, we also explore subject acceptance an affordable wearable move basic hand actions during robot-assisted movement. Six healthy subjects separately perform left right imagery, looking-left looking-right eye movements, different gestures in modes actions. The results indicate number mHMI instructions significantly greater than achievable with any individual mode. Furthermore, can achieve average classification accuracy 93.83% information transfer rate 47.41 bits/min, which entirely equivalent speed 17 per minute. study expected construct more user-friendly help or disabled persons movements friendly convenient way.

Language: Английский

---

Data Analytics in Steady-State Visual Evoked Potential-Based Brain–Computer Interface: A Review

IEEE Sensors Journal, Journal Year: 2020, Volume and Issue: 21(2), P. 1124 - 1138

Published: Aug. 18, 2020

Electroencephalograph (EEG) has been widely applied for brain-computer interface (BCI) which enables paralyzed people to directly communicate with and control external devices, due its portability, high temporal resolution, ease of use low cost. Of various EEG paradigms, steady-state visual evoked potential (SSVEP)-based BCI system uses multiple stimuli (such as LEDs or boxes on a computer screen) flickering at different frequencies explored in the past decades fast communication rate signal-to-noise ratio. In this article, we review current research SSVEP-based BCI, focusing data analytics that continuous, accurate detection SSVEPs thus information transfer rate. The main technical challenges, including signal pre-processing, spectrum analysis, decomposition, spatial filtering particular canonical correlation analysis variations, classification techniques are described article. Research challenges opportunities spontaneous brain activities, mental fatigue, learning well hybrid also discussed.

Language: Английский

---

Stress Assessment Based on Decision Fusion of EEG and fNIRS Signals

IEEE Access, Journal Year: 2017, Volume and Issue: 5, P. 19889 - 19896

Published: Jan. 1, 2017

emergingFusion of electroencephalography (EEG) and functional near infrared spectroscopy (fNIRS) is an emerging approach in the field psychological neurological studies. We developed a decision fusion technique to combine output probabilities EEG fNIRS classifiers. The explored support vector machine as classifier for each modality, optimized classifiers based on their receiver operating characteristic curve values. signal were acquired simultaneously while performing mental arithmetic task under control stress conditions. Experiment results from 20 subjects demonstrated significant improvement detection rate by +7.76% (p <; 0.001) +10.57% 0.0005), compared with sole modality fNIRS, respectively.

Language: Английский

---

Effects of Acupuncture Therapy on MCI Patients Using Functional Near-Infrared Spectroscopy

Frontiers in Aging Neuroscience, Journal Year: 2019, Volume and Issue: 11

Published: Aug. 30, 2019

Acupuncture therapy (AT) is a non-pharmacological method of treatment that has been applied to various neurological diseases. However, studies on its longitudinal effect the neural mechanisms patients with mild cognitive impairment (MCI) for purposes are still lacking in literature. In this clinical study, we assess effects ATs MCI using two methods: (i) Montreal Cognitive Assessment test (MoCA-K, Korean version), and (ii) hemodynamic response (HR) analyses functional near-infrared spectroscopy (fNIRS). fNIRS signals working memory (WM) task were acquired from prefrontal cortex. Twelve elderly 12 healthy people recruited as target control (HC) groups, respectively. Each group went through an scanning procedure three times: The initial data obtained without any ATs, subsequently total 24 AT sessions conducted (i.e., MCI-0: prior MCI-1: after 6 weeks, MCI-2: another weeks). mean HR responses all MCI-0-2 cases lower than those HCs. To compare patients, MoCA-K results, temporal data, spatial activation patterns t-maps) examined. addition, connectivity (FC) graph theory upon WM tasks conducted. With averaged scores improved (MCI-1, p = 0.002; MCI-2, 2.9e-4); was increased (p < 0.001); (iii) t-maps MCI-1 MCI-2 enhanced. Furthermore, FC cortex both MCI-1/MCI-2 comparison MCI-0 0.01), increasing trend parameters observed. All these findings reveal have positive impact improving function patients. conclusion, can be used therapeutic tool (Clinical trial registration number: KCT 0002451 https://cris.nih.go.kr/cris/en/).

Language: Английский

---