中 / EN

EEG

218 entries

Electroencephalography is the most widely used signal acquisition technique in BCI, offering low cost, portability, and non-invasiveness for applications from lab research to consumer products. This topic covers EEG hardware, signal processing methods, and novel electrode materials.

October 2026
10-14 Papers Foundations & Methods

Imagined Speech Decoders Perform Near Chance Across People in Three EEG Corpora

Researchers analyzed three public corpora to test whether imagined speech decoders trained on one person's scalp EEG could work for another. Across 482 ordered participant pairs, none remained significant after multiple-comparison correction; mean transfer accuracy was within 0.006 of chance in every corpus. A signal distinguishing the imagery task from pre-stimulus rest instead reflected a post-stimulus state. Only the competition corpus exceeded the within-subject threshold for every participant, but its frequency profile failed an artifact audit. The findings apply to these corpora and the representations examined, not to all imagined speech decoding.
View details →
10-14 Papers Foundations & Methods

Study Finds Muscle Signals Dominate Overt-Speech Controls in EEG Decoding

Researchers audited three public corpora and found that decoding overt speech may not establish a pipeline's ability to recognize brain-derived speech signals. In ds003626, two lip electrodes achieved an accuracy of 0.7430, compared with 0.4231 for the 128-channel scalp montage; no decodable signal remained in the 8-30 Hz band. By injecting effects of known amplitude into real recordings, the team also measured detection floors and found differences between methods. The authors conclude that muscle signals dominate the overt-speech positive controls in these corpora and recommend reporting band-limited performance, artifact-channel accuracy, and measured detection floors.
View details →
10-13 Industry News

Muse Plans Weekly Brain Age Estimates Using EEG and Cognitive Tests

Muse announced Brain Age, a feature combining headband-recorded EEG with four one-time cognitive tests. It will show whether estimated brain age is younger than, aligned with, or older than chronological age, expressed as a difference in years. According to the company, the first reading requires 10 qualifying minutes on each of 7 different days and completion of all four tests, with updates every Monday thereafter. The feature supports Muse 2, Muse S, and Muse S Athena. The first reading is free; subsequent readings require Muse Premium. Muse describes it as a general wellness feature whose readings are not for medical use; the company does not promise that practice changes brain age.
View details →
10-13 · Beijing Sport University China Papers Foundations & Methods

Beijing Sport University Model Gains Lose Significance Under Broader Statistical Correction

Researchers at Beijing Sport University developed a motor imagery EEG decoding model and evaluated it offline on three public datasets using subject-specific and cross-subject protocols. Against the baseline with the highest mean accuracy, subject-specific gains on two datasets were 3.56 and 1.62 percentage points; another cross-subject comparison showed a 2.08-point difference. These three comparisons had statistical support after correction within their respective settings, but none remained significant under a broader correction covering 56 comparisons. The findings offer limited support for integrating local and longer-range EEG information in stages, rather than establishing benefits for online control or clinical use.
View details →
10-12 Papers Foundations & Methods

Stage-Aware EEG Window Selection Improves Motor Imagery Decoding in Benchmark Tests

Researchers propose an adaptive EEG window-selection framework for motor imagery classification. Instead of independently retaining or discarding each segment, it considers event phases and relationships between successive windows. Each window receives a Discard, Onset, Sustain, or Offset role, with constraints blocking selections that violate phase order. The authors report consistent decoding improvements across multiple benchmark datasets in both cross-session and cross-subject settings. Visualizations further suggest that the learned policy aligns with neurophysiological principles. These dataset experiments do not establish equivalent gains during online BCI use. This study is a preprint and has not been peer reviewed.
View details →
10-11 Papers Foundations & Methods

EEG Transform Reduces Cross-Session Identity Recognition at a Cost to Motor Imagery Decoding

Researchers developed an EEG transform that requires no trained privacy model to reduce features linking recordings from the same person across sessions. Tests on two public datasets used five attackers spanning four covariance-space representations. The strongest attacker's accuracy fell from 90.8% to 15.6% on BCI Competition IV-2a and from 90.8% to 9.9% on OpenBMI. Relative to the 8-30 Hz input, motor imagery decoding accuracy decreased by 7.0 and 2.1 percentage points, respectively. The transform was fitted on one session and applied unchanged to a held-out later session. This study is a preprint and has not been peer reviewed.
View details →
10-10 Industry News

WABO Wins Startup First Prize for Human Neural Intent Project

WABO won first prize in the startup group of the 2026 Global Artificial Intelligence Innovation and Entrepreneurship Contest for its project to build a human neural intent model. According to the company, the contest was organized by the Chinese Association for Artificial Intelligence and received 340 applications. Twenty teams reached the final, with ten each in the startup and growth groups and one first prize per group. WABO is developing a model that combines EEG, EMG, and task context to interpret high-level human intent under specific task conditions and connect it to intelligent-device actions. The award reflects the contest's project evaluation, not validation of intent recognition or device-control performance.
View details →
10-09 Papers Foundations & Methods

Study Screens Lattice Structures for Lightweight, Compliant BCI Helmet Pads

The study proposes generating finite element models directly from voxels to screen BCI helmet-pad structures for lower material use and greater compliance under compression. It generated 200 gyroid triply periodic minimal surface models, of which 199 yielded valid mechanical results, and used regression that predicts both outcomes and uncertainty to support screening. Under simulated flat-plate compression, the authors report that a representative structure increased compliance by approximately 12 times while reducing material usage by approximately 75%. These structural simulation results do not directly establish improved wearing comfort or EEG contact quality.
View details →
10-09 Papers Rehabilitation & Assistance

Adult Study Links BCI Learning to Reading Gains in Dyslexia Research

Researchers developed a non-invasive EEG brain-computer interface combining auditory input with visual feedback to support phonological processing relevant to developmental dyslexia, then tested it first in adults with and without dyslexia. Participants completed 16 sessions and underwent pre- and post-training assessments of phonological awareness, single-word reading and non-word reading. Among participants who learned the BCI, offline learning scores were significantly associated with non-word reading gains in both groups. BCI learning was also significantly associated with improvements in real-word reading and amplitude rise time discrimination. These associations do not establish that training caused the gains or demonstrate benefits in infants or children.
View details →
10-09 Clinical Launch & Registration

Registered Study Plans to Assess Tinnitus Using a Non-Invasive Brain-Computer Interface

A registered observational case-control study plans to explore objective assessment of subjective tinnitus using non-invasive brain-computer interface technology. It aims to enroll 150 people with chronic tinnitus and 150 healthy controls. The primary outcome is auditory event-related potentials, brain electrical responses associated with sound events. Secondary measures include tinnitus handicap, anxiety and depression scale scores, pure-tone thresholds, noise exposure, and medication history. Controls will be matched to patients by age and other relevant characteristics, and neither group will receive an intervention. Recruitment is pending; the study does not yet establish diagnostic accuracy or treatment effects.
View details →
10-07 Industry News Foundations & Methods

Mobile EEG Links Driving Thrill to Control, Not Speed

Ten drivers wore EEG, heart rate variability, skin response and eye tracking gear through 6 conditions, from low-speed off-road driving to track laps in a McLaren. The strongest flow-state signature — elevated frontal-midline theta with preserved alpha — appeared on the track; the high-speed passenger ride instead showed falling theta and alpha with rising beta, a pattern the team read as anxiety rather than thrill. Karting produced clearer signs of engaged, positive arousal than the passenger ride despite lower speeds. The team says the recordings show that EEG good enough to separate engagement from stress can be collected in a moving vehicle.
View details →
10-07 Papers Foundations & Methods

Ulsan Finds Motor Imagery Information Rises Fastest 0.60–0.75 Seconds After a Cue

A University of Ulsan study analyzed two independent public datasets to examine when brain rhythms begin to weaken across regions during cue-paced motor imagery and when information distinguishing imagined movements emerges. Regional changes followed an ordered sequence. Class-discriminative information rose most steeply 0.60-0.75 seconds after the cue and saturated within a further 0.3 seconds. In every participant across both datasets, this transition was closer to sensorimotor desynchronization onset than to cue presentation. However, windows centered on each region's own onset classified equivalently to reassigned windows. The authors interpret the sequence as a timing landmark for analysis rather than a directly decodable feature.
View details →
10-06 Papers Foundations & Methods

Semi-Dry Smarting Mobile EEG Matches Gel Lab System on Individual Auditory ERPs

An independent study found that a 24-channel wireless Smarting EEG cap with saline-sponge electrodes detected individual-level N100 and P300 auditory responses, which appear about 100 and 300 milliseconds after a sound, in 34 of 36 tests, versus 34 of 40 for a 64-channel wired gel BioSemi system in the same shielded lab. Participants heard a sound sequence containing occasional target and novel tones. The Smarting group had only 9 participants, and the researchers caution that this is not a strict hardware comparison.
View details →
10-05 Clinical Launch & Registration

Tan Tock Seng Hospital Registers Stroke BCI Rehab Trial

After a stroke, can the brain's intent to move still drive arm rehabilitation? A trial registered by Tan Tock Seng Hospital will read scalp EEG as acute stroke patients attempt movement and use those signals to trigger functional electrical stimulation of the arm. The study focuses on how these brain signals change over time after stroke and what that means for BCI-based rehabilitation. It plans to enroll 12 patients, is not yet recruiting, and expects primary completion in December 2027.
View details →
10-05 Papers Foundations & Methods

New Method Aligns EEG Across Users Without Labels

EEG-based brain-computer interfaces lose accuracy when the user or session changes, because the signal distribution shifts, and users usually have to sit through labeled calibration. SPDAlign tackles this without labels. The researchers show theoretically that shifts caused by the forward process, linked to factors such as head geometry, can be recovered solely through linear transformations on the Symmetric Positive Definite manifold. The framework aligns domain-specific means, then corrects global rotations with an optimal transport technique called Wasserstein Procrustes. The authors report competitive performance on public EEG datasets and say the method can identify relevant frequency ranges and spatial patterns. The study is a preprint and has not been peer reviewed.
View details →
10-05 · Neuropsychology Lab Canada Papers Sensation & Feedback

German Team Decodes Listener Attention With Ear EEG, but Walking Adds Artifacts

Researchers in Germany fitted participants with lightweight EEG electrodes around the ear and a portable hearing aid research platform, then tested auditory attention while they sat and walked. Speech reconstructed from the EEG followed earlier lab findings: most accurate for a single talker, then the attended talker of two, and least for the ignored one. Walking introduced a speech-synchronized artifact, possibly from hearing aid cables touching the electrodes, which affected accuracy; the researchers conclude feasibility is shown only for stationary settings.
View details →
10-05 Papers Foundations & Methods

Online Updates Beat Drift in 13 of 14 BCI Models

EEG signals drift, so a brain-computer interface model calibrated in the lab often loses accuracy in everyday use. This preprint puts Common Spatial Patterns (CSP) and Riemannian covariance-based pipelines through the same time-ordered evaluation: predict first, then update after the true label arrives. Across 4 public datasets, label-revealed updates lifted accuracy in 13 of 14 model/dataset pairs on the 2 largest streams, up to about 18% over a frozen model. A Shapley-based valuation gave the most recent time block the highest mean value in all 3 datasets analyzed, while older blocks retained positive value.
View details →
10-05 Papers Foundations & Methods

Involuntary Facial Muscle Activity Contributes to EEG Emotion Decoding During Imagined Vocalisation

Researchers recorded EEG during overt and imagined vocalisation to distinguish five emotion categories: anger, happiness, neutral, sadness, and pleasure. The overt experiment involved 14 participants and the imagined experiment involved 21, yielding single-trial decoding accuracies of 78.1% and 36.4%, respectively, against 20% chance. Facial surface EMG recorded in five participants during imagined vocalisation indicated that involuntary muscle activity contributed to EEG spectral and spatial patterns used for classification. One lateral-channel pattern was stronger during imagined happy vocalisations. The results mean that decoding accuracy cannot be attributed entirely to brain-derived emotion information.
View details →
10-05 Papers Foundations & Methods

ISAE-SUPAERO Semi-Dry BCI Achieves 99.8% Accuracy in a 30-Participant Screen Typing Test

An ISAE-SUPAERO study tested a brain-computer interface combining semi-dry EEG acquisition with visual stimulation. Thirty participants completed an 11-class keypad typing task on a standard screen. With 33 s of calibration data, the system achieved 99.8% accuracy and a mean decoding time of 4.3 s. No spurious commands occurred during a 2-min video-viewing idle condition between two online typing sessions. A virtual reality proof of concept reached 100% online accuracy with a mean decoding time of 5.6 s. Participants reported high visual comfort and little peripheral distraction in both conditions, but greater fatigue in VR. The short idle test does not establish long-term performance.
View details →
10-04 Papers Rehabilitation & Assistance

EEG Intention Matrix Drives Rehab Lower-Limb Exoskeleton

Researchers built a control framework, the Intention Matrix, that classifies brain-wave signals to infer a user's intended leg movement and fuses that with data from the exoskeleton's own sensors to generate low-level control commands. Intention reading begins after the user initiates the limb movement. The authors say the results show preliminary feasibility for supporting the EXOS-1 exoskeleton in therapy; the abstract reports no participant numbers or accuracy figures.
View details →
10-02 · Hangzhou Dianzi University China Papers Foundations & Methods

Network Decodes Motor Intent From New Users' EEG

EEG signals vary between people and drift over time, so a brain-computer interface usually has to be recalibrated for each new user. Researchers at Hangzhou Dianzi University built TSMD-Net, which learns from several existing subjects without any data from the new user, then pools what it learned about each one into a single classifier. It reached mean accuracies of 70.21%, 77.82% and 79.53% on three public EEG datasets.
View details →
10-02 · The University of Texas at Austin United States Papers Foundations & Methods

Stretchable EEG Cap Holds Signal Quality Through Hair

A stretchable EEG platform called MindStretcH maintained stable scalp contact through hair over prolonged use, with no measurable drop in recording quality across repeated online brain-computer interface sessions, researchers at The University of Texas at Austin reported. The system combines a kirigami-patterned elastomer mesh, liquid-metal interconnects and detachable hydrogel electrodes. The abstract does not disclose participant numbers or session duration.
View details →
10-02 Papers Foundations & Methods

Preprint: Heart, Breath and Pupil Signals Beat EEG at Decoding Arousal

Researchers found that a decoder trained on peripheral physiological signals (heart rate, heart rate variability, respiration, electrodermal activity and pupil diameter) read arousal more accurately than EEG, reaching a within-subject area under the curve (AUC) of 93.0%, versus 85.2% for an EEG-only decoder and 79.8% for the original filter-bank common spatial pattern decoder. The offline analysis used a public simulated-flight dataset. Only the peripheral decoder reproduced the inverted-U relationship between arousal and performance, and EEG neurofeedback did not change overall arousal trajectories, suggesting its effect may come from regulation at task-critical moments. The study is a preprint and has not been peer reviewed.
View details →
10-02 · East China University of Science and Technology +1 more China Papers Foundations & Methods

New Network Boosts SSVEP BCI Accuracy With Less Calibration

When a user looks at targets flickering at different frequencies, the visual cortex produces EEG responses at matching frequencies, known as steady-state visual evoked potentials (SSVEP), which a brain-computer interface can use to infer the intended target. Such systems usually need calibration data, and more data means more user fatigue. Researchers propose SCR-FTSDNN, a deep convolutional network that moves EEG into the frequency domain, then extracts temporal and spatial features with added spatial and channel reconstruction modules. Tested on the public Benchmark and BETA datasets, the authors report higher recognition accuracy and stability than several existing methods, especially with limited calibration data. The abstract gives no specific figures, and the results come from offline tests.
View details →
10-02 Papers Foundations & Methods

Study Gauges Driver Acceptance of BCI Assistance

Would drivers accept a car that reads their brain signals and steps in when they are overloaded? In an online experiment, 1201 participants each viewed 1 of 12 animated driving scenarios. In each scenario, a wearable, non-invasive brain-computer interface detected high workload and triggered assistance. Acceptance varied systematically across scenarios. It was higher when the system supported driving-related functions and when the driver shown had a disability. The 2 automation activation modes tested made no difference.
View details →
10-01 Papers Foundations & Methods

EEG-Text Fusion Model Classifies Emotions at 89.7% Accuracy, Author Reports

A study combines EEG data with multilingual text to classify emotions, since EEG alone is prone to noise while language models read sentiment in words but miss implicit changes in the brain. The author reports 89.7% accuracy for the fused model, versus 75% for EEG alone and 79% for text alone, with an F1-score of 0.88 and an average inference latency of 180 ms, enough for real-time recognition. The abstract does not state the number of participants or the datasets used.
View details →
10-01 · Singapore Institute of Technology Singapore Papers Foundations & Methods

Singapore Institute of Technology Decodes Same-Hand Direction From EEG at 58.7%

Researchers at the Singapore Institute of Technology decoded online whether 20 healthy subjects were imagining moving their dominant hand left or right, without actually moving, reaching an average accuracy of 58.7±8%, which they say beats existing deep learning models. The difficulty is that neural activity for different directions of the same hand overlaps heavily in space. The model uses EEGNet convolutional filters to extract temporal and spatial features, is trained first as a general model on pooled multi-subject calibration data and then fine-tuned per person, and its squeeze-and-excitation layers rank each electrode's contribution, offering a basis for personalized electrode layouts. Earlier studies mostly compared left versus right hand, largely offline. The work targets stroke rehabilitation but has been tested only in healthy people.
View details →
10-01 Papers Foundations & Methods

CortexBridge Adapter Unifies EEG Electrode Layouts, Improving 13 of 15 Evaluations

Researchers have proposed CortexBridge, a lightweight adapter that lets EEG foundation models, usually pretrained on a single fixed electrode layout, handle any montage. It combines EEG features with electrode and brain-atlas coordinates to map signals into a shared cortical latent space before passing them to the pretrained model, which is left unchanged. On 5 BCI datasets from the public MOABB benchmark, tested with 3 frozen foundation models, EEGPT, LaBraM and CBraMod, it improved performance in 13 of 15 evaluations, raising balanced accuracy by an average of 0.80%, 0.70% and 3.26% respectively, with a maximum gain of 13.02% on 12-class steady-state visually evoked potential classification. The study is a preprint and has not been peer reviewed.
View details →
September 2026
09-30 Papers Foundations & Methods

MetaIDNet Cuts EEG Color Vision Test Time by 70%

Color vision tests usually rely on what the subject reports, while a brain-computer interface can read the brain's response to color differences directly: the more two flickering light sources differ in perceived color, the stronger the steady-state visual evoked potential in the EEG. Existing systems sample color space evenly and repeat measurements at each point, which is accurate but slow. MetaIDNet, a closed-loop system, instead uses Gaussian process regression and a neural network to decide where to measure next. Offline, it made assessment 70% faster at the same accuracy; online, it improved accuracy by 40% at the same speed. The offline and online experiments involved only 10 and 8 participants.
View details →
09-30 Industry News Progress & Expansion

Neurotechnology Launches Mobile App for Computer-Free BrainAccess EEG Recording

Neurotechnology has released BrainAccess Mobile, a free Android app (Android 7 and later) that brings the core functions of its desktop software BrainAccess Board to phones and tablets. The app connects to one or more BrainAccess EEG devices over Bluetooth and handles device setup, signal acquisition, real-time viewing, electrode impedance checks, playback and data management, with data stored locally or streamed to a computer via the LSL protocol. The company says it suits outdoor state monitoring, synchronized multi-person recording and home sleep studies, but is not yet suited to experiments that require precise stimulus-response alignment, such as event-related potential and P300 paradigms, for which it still recommends a computer. The existing BrainAccess Mobile Lite will remain free.
View details →
© 2026 BCIwiki.com Digest Topics Tips Subscribe Revisions About