FitBit Sleep: Minute-Level Sleep State Data from Wearable Trackers

Detailed sleep tracking information segmented into one-minute intervals for a group of users. The dataset includes a binary indicator of sleep state per minute, unique user and log identifiers, and timestamped records. It was authored by Mobius and is shared under a CC0-1.0 license.

Use Cases

• Identify sleep patterns and assess sleep quality based on minute-level binary state data.
• Correlate sleep habits with potential health outcomes using longitudinal user data.
• Test and validate sleep detection algorithms for wearable devices based on the temporal data.
• Analyze sleep consistency, duration, and disturbances for quantitative health recommendations.

Strengths

• Data is recorded at a high temporal resolution of one-minute intervals.
• Includes a binary sleep state indicator enabling clear classification of asleep vs. awake minutes.
• Contains unique identifiers for both users and sleep logs, facilitating session-level analysis.

Limitations

• Row count, file formats, and dataset size are unknown, which may limit suitability assessment.
• Column-level documentation beyond the four described attributes is absent; field semantics for any additional columns must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Mobius via OpenML

Collection Method

Likely collected from FitBit wearable devices tracking user sleep.

Time Range

null

Freshness

null

Geography

null