DREAMT: Sleep Stage Estimation Data from Multisensor Wearables

DREAMT (Dataset for Real-time sleep stage EstimAtion using Multisensor wearable Technology) is a restricted health dataset hosted on PhysioNet. It is designed for developing machine learning models to estimate sleep stages using data from wearable devices. The dataset was last updated on the platform in March 2026.

Use Cases

• Train sleep stage classification models based on multisensor wearable data.
• Evaluate real-time sleep estimation algorithms based on the dataset's design purpose.
• Benchmark model performance for wearable-based health monitoring.
• Research correlations between sensor signals and sleep architecture.

Strengths

• Dataset is versioned (v2.1.0), indicating structured updates.
• Designed specifically for a defined ML task: real-time sleep stage estimation.
• Sourced from PhysioNet, a reputable repository for physiological data.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and file formats are unknown, which may limit suitability assessment.

Provenance

Source

PhysioNet

Collection Method

Data collected from multisensor wearable devices, likely in a clinical or research setting.

Time Range

null

Freshness

Last updated 2026-03-25 01:24:22; freshness should be verified.

Geography

null