A study evaluates EEG Foundation Models for event-based burst-suppression detection in ICU settings without patient-specific calibration. REVE-base achieved the highest event-based F1-score of 0.868 and reduced burst-per-minute error by 52.1% compared to EEGNet and 36.2% compared to adaptive thresholding, demonstrating superior performance. Ablation results show full fine-tuning outperforms other strategies, and pretrained REVE-base surpasses random initialization by 0.723 F1 points at 25% labeled data, highlighting the value of pretraining for limited datasets.
arxiv
arXiv cs.AI
·
78d ago
·
research
EEG Foundation Models for Burst-Suppression Detection in ICU
from English
Related articles
arxiv
arXiv cs.LG
·
78d ago
·
1 view
Topological Data Analysis for Real-Time Process Monitoring
A new method combines topological data analysis and machine learning to monitor high-dimensional dynamic processes. It represents time-series data as manifolds, uses topological descriptors to capture structure, and employs neural ordinary differential equations to model dynamic evolution. The approach effectively detects diverse events in industrial process data and outperforms reconstruction-based and trajectory-based alternatives.
arxiv
arXiv cs.LG
·
78d ago
SSH-Net: Deep Network for Failure Time Prediction under Competing Risks
SSH-Net is a structured deep neural network designed to predict failure time distribution functions under competing risks. It uses separate sub-networks for different covariate groups, improving accuracy by aligning neural structure with data hierarchy. The model is validated through simulation studies and applied to Titan GPU failure data.
arxiv
arXiv cs.LG
·
78d ago
Self-Adaptive Scale Handling for Time Series Forecasting
A new module called Self-Adaptive Scale-handling (AS) addresses scale heterogeneity in time series forecasting. It uses Scale Calibrating and Scaling Selection to adaptively adjust scaling factors, preserving semantic discriminability and reducing inverse-scaling errors. Experiments on fund sales data show improved performance when integrated into existing forecasting models.
arxiv
arXiv cs.LG
·
78d ago
Comparative Study of Neural Surrogates for Battery State Prediction
A comparative study evaluates four neural architectures—MLP, ResNet, U-Net, and FNO—as autoregressive predictors of internal battery states using the Doyle-Fuller-Newman model. The U-Net achieves a mean final-step nRMSE of 3% across all state variables and provides a 5.38x speed-up over numerical solvers, demonstrating the importance of spatial inductive bias in surrogate performance.
arxiv
arXiv cs.LG
·
78d ago
·
1 view
EEG Foundation Models for Burst-Suppression Detection in ICU
A study evaluates EEG Foundation Models for event-based burst-suppression detection in ICU EEG without patient-specific calibration. REVE-base achieved the highest event-based F1-score of 0.868 and reduced burst-per-minute error by 52.1% compared to EEGNet. Ablation experiments show full fine-tuning outperforms other strategies, and pretrained REVE-base surpasses random initialization by 0.723 F1 points at 25% labeled data.