Spatio-temporal dataset of building occupants

Area of Science:

• Indoor positioning and tracking
• Building informatics
• Human mobility patterns

Background:

• Understanding building occupant behavior is crucial for optimizing space utilization and energy efficiency.
• Accurate spatio-temporal data is essential for developing intelligent building management systems.
• Existing methods for tracking occupants often face limitations in granularity and coverage.

Purpose of the Study:

• To present a novel spatio-temporal dataset of building occupants.
• To facilitate research in indoor localization and human mobility analysis within built environments.
• To provide a foundation for developing advanced building management and analysis tools.

Main Methods:

• Deployment of 200 Bluetooth Low Energy (BLE) beacons across two buildings.
• Collection of 8426 spatio-temporal data points from 11 building occupants.
• Data acquisition with a 5-second sampling rate over a 12-day period.
• Integration of location and time data with OpenStreetMap (OSM) for visualization.

Main Results:

• A comprehensive dataset detailing the movement of 11 individuals within two buildings.
• Spatio-temporal data points capturing location and time with high temporal resolution (5 seconds).
• The dataset is visualized using OpenStreetMap, providing spatial context to occupant movements.

Conclusions:

• The presented dataset offers a valuable resource for studying indoor human mobility.
• This data can inform the design and operation of smart buildings.
• Further research can leverage this dataset for developing predictive models of occupant behavior.