SEED-IV
PulseAugur coverage of SEED-IV — every cluster mentioning SEED-IV across labs, papers, and developer communities, ranked by signal.
-
New research explores advanced AI for EEG-based emotion recognition · 2 papers
Two new research papers explore advanced techniques for recognizing emotions from electroencephalography (EEG) data. The first paper introduces a multi-scale temporal framework that processes EEG signals across differen…
-
EEG Emotion Recognition: Protocol Impact and AI-Generated Architecture Insights
Two research papers explore the nuances of emotion recognition using electroencephalography (EEG) data. The first paper focuses on the critical importance of evaluation protocols and cross-subject generalization in EEG …
-
New framework reveals safety gaps in neural interface AI models
A new research paper proposes a unified safety framework for embedded neural interface models, highlighting a critical gap between formal robustness certificates and actual operational safety. The framework identifies t…
-
New deep learning models enhance EEG-based emotion recognition with improved accuracy and interpretability
Researchers are developing advanced deep learning models for EEG-based emotion recognition, aiming to improve accuracy and interpretability. One approach uses graph regularization to capture psychological interdependenc…
-
EEGDancer predicts continuous emotions from EEG using RL
Researchers have developed EEGDancer, a novel framework for predicting continuous human emotions from EEG signals. This approach utilizes a dynamic emotional latent space, integrating vector-quantized representation lea…
-
New framework enhances cross-domain emotion recognition with multimodal alignment
Researchers have developed UF-AMA, a novel framework designed to improve emotion recognition across different datasets and sessions using physiological signals. This unified approach integrates EEG and eye-tracking data…
-
New EMAG framework enhances EEG signal reconstruction from sparse data
Researchers have developed EMAG, a new differentiable framework designed to reconstruct high-density EEG signals from a sparser set of electrodes. This method represents brain electrical sources as a mixture of anisotro…