SLEEP-EDF
PulseAugur coverage of SLEEP-EDF — every cluster mentioning SLEEP-EDF across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Explainable AI framework enhances sleep stage classification accuracy
Researchers have developed an explainable AI framework called SleepXAI to improve the interpretability of automated sleep staging. This framework was tested on single-channel electroencephalogram data using the Sleep-ED…
-
New MM-Net model enhances sleep staging and apnea assessment after stroke
Researchers have developed MM-Net, a novel multimodal multi-task network designed to improve the accuracy of sleep staging and sleep apnea assessment, particularly in patients who have experienced an ischemic stroke. Th…
-
New on-device LLM for smartphones prioritizes privacy with soft-prompting
Researchers have developed PocketTSLM, a novel on-device time-series language model designed for smartphones that prioritizes privacy. This model, based on OpenTSLM SoftPrompt, processes physiological data directly on t…
-
New simulator StressSim exposes AI agent weaknesses · 2 sources tracked
Researchers have developed StressSim, a novel framework for evaluating multi-turn AI agents by simulating adversarial users. This system aims to stress-test agents by creating challenging, yet valid, user interactions t…
-
NanoSleep: Efficient AI for Sleep Stage Classification on Wearables
Researchers have developed NanoSleep, a compact hybrid temporal convolutional network designed for efficient sleep stage classification from single-channel EEG data. This model addresses the challenge of deploying accur…
-
RG-Flow Transformer shows interpretability gains on scarce neural data
Researchers have developed an RG-Flow Transformer, a novel architecture designed to handle scarce neural data by incorporating a renormalization-group (RG) inductive bias. This model was tested on sleep stage classifica…
-
New criterion predicts effectiveness of time-lagged spectral embeddings
Researchers have developed a new criterion to determine the applicability of training-free time-lagged spectral embeddings for multivariate time series. This criterion, based on stationarity and temporal coupling, predi…
-
EEG Foundation Models Leak Data Despite Standard Audits
Researchers have developed a new auditing framework for EEG foundation models that goes beyond single-endpoint evaluations. This framework jointly audits multiple endpoints, revealing that models cleared by individual t…
-
New framework uses conditional diffusion models for multimodal federated learning
Researchers have developed a new framework called CondI to address missing data in multimodal federated learning, particularly in clinical settings. This approach uses conditional diffusion models to explicitly impute u…