electroencephalography
PulseAugur coverage of electroencephalography — every cluster mentioning electroencephalography across labs, papers, and developer communities, ranked by signal.
- used by Alzheimer's disease 95%
- developed Alzheimer's disease 95%
- instance of alphaXiv 90%
- developed CatalyzeX 90%
- developed Gotit.pub 90%
- used by brain–computer interface 90%
- instance of THINGS-EEG2 90%
- instance of CHB-MIT 90%
- instance of Meg 90%
- used by NeuraDock Agent 90%
- used by THINGS-EEG 90%
- instance of cause 90%
19 day(s) with sentiment data
-
New foundation models advance EEG analysis for brain-computer interfaces
Researchers have developed two new foundation models for electroencephalography (EEG) data, aiming to improve brain-computer interface (BCI) applications. ScaleBrain focuses on scale-consistent pre-training by aligning …
-
Mixed-reality EEG interface shows feasibility for target selection
Researchers have developed a mixed-reality (MR) interface that utilizes electroencephalography (EEG) to enable target selection in a disappearing-stimulus environment. The study tested the feasibility of this interface,…
-
Language models can now "train" neural networks by editing weights, outperforming gradient descent
Researchers have explored "weight-space programming," a method where language models can directly edit the weights of trained neural networks, enabling "training" through reasoning rather than gradient descent. This tec…
-
Wearable sleep trackers harvest brainwave data for AI training without consent
Wearable sleep tracker companies are reportedly using millions of hours of customer brainwave data (EEG) to train AI models without explicit consent. Companies like Interaxon, maker of the Muse headband, and Emotiv have…
-
New SPSC framework enhances EEG-to-image reconstruction accuracy
Researchers have developed a new framework called SPSC to improve the reconstruction of images from EEG data, particularly in zero-shot cross-subject scenarios. This framework addresses the challenge of semantic shifts …
-
New AttrEcho Framework Enhances EEG-to-Image Decoding with Visual Attributes
Researchers have developed a new framework called AttrEcho to improve the accuracy of decoding brain activity (EEG) into images. This method enhances existing visual representations by incorporating explicit visual attr…
-
EEG foundation model adapters show no consistent advantage over simpler controls
A study published on arXiv explored the effectiveness of different adapter designs for electroencephalography (EEG) foundation models. Researchers compared a "backbone-informed" adapter, which models relationships acros…
-
LLaMA 3.1 aids AI in correcting sleep stage classification errors
Researchers have developed a novel method to improve the accuracy of sleep stage classification from EEG data by using LLaMA 3.1 to identify and remove unreliable sleep-stage annotations. This LLM-assisted pipeline firs…
-
PhysioWave-T: Efficient Foundation Models for Biosignal Analysis
Researchers have introduced PhysioWave-T, a family of foundation models designed for efficient processing of biosignals like EEG, ECG, and sEMG. The models utilize a technique called Dynamic Scale Folding to significant…
-
New framework uses physics-informed AI for EEG source imaging
Researchers have introduced PINR-ESI, a novel physics-informed self-supervised implicit neural representation framework designed for electroencephalography (EEG) extended-source imaging. This method aims to accurately l…
-
AutoBCI framework uses AI agents to discover optimal EEG brain-computer interfaces
A new research paper introduces AutoBCI, an agentic framework designed to discover and select optimal neural architectures for EEG-based brain-computer interfaces. The framework employs a Designer Agent for architecture…
-
EEG Foundation Models: Quantifying Trait-State Hierarchy for BCI Performance
Researchers have developed a method to quantify the hierarchy of trait and state information within electroencephalography (EEG) embeddings. Their findings indicate that EEG features primarily form a macro-trait hierarc…
-
BrainBind framework maps EEG and fMRI to video embeddings
Researchers have developed BrainBind, a novel framework designed to map synchronized electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) data into shared video embedding spaces. This approach t…
-
New method adapts Sleep Foundation Models for precise EEG sleep spindle localization
Researchers have developed a novel method to adapt frozen Sleep Foundation Models (SleepFM) for precise sleep spindle localization in electroencephalography (EEG) data. The approach incorporates a local time-frequency p…
-
Vision and Language Models Adapted for EEG Analysis and Diagnostics · 4 sources tracked
Researchers are exploring the adaptation of visual language models (VLMs) and large language models (LLMs) for analyzing electroencephalography (EEG) data, moving beyond traditional supervised models. One approach recas…
-
New EEG methods detect depression by modeling normative deviations
Researchers have developed novel methods for detecting depression using electroencephalography (EEG) data, addressing the challenge of individual variability in recordings. The proposed approaches, Scalar-level Normativ…
-
NeuroBridge decodes images from EEG using bio-inspired AI
Researchers have developed NeuroBridge, a novel self-supervised architecture designed for decoding images from electroencephalography (EEG) brain activity. This system integrates Cognitive Prior Augmentation (CPA) and a…
-
BridgeRouter algorithm optimizes cross-modal biosignal transfer
Researchers have developed BridgeRouter, a novel algorithm designed to optimize the transfer of information between different biosignal modalities using lightweight representation bridges. This system intelligently rout…
-
AI offers modest gains for 20-year-old brain decoder, training-free variant excels
A recent study explored the effectiveness of AI in improving brain-computer interfaces (BCIs), specifically focusing on EEG decoders for SSVEP spellers. While a 20-year-old algorithm called Canonical Correlation Analysi…
-
New DP-STCL framework enhances cross-subject EEG emotion recognition
Researchers have developed a novel Dual-Path Spatiotemporal Contrastive Learning (DP-STCL) framework to improve the accuracy of EEG-based emotion recognition across different subjects. This method utilizes two distinct …