AmbiLoc — A year-long dataset for ambient indoor localization

Ambient indoor localization is a research field that studies indoor localization systems based on ambient signals of opportunity, such as those from broadcasting TV and FM radio stations or GSM networks. By using already existing high-power transmitters, such systems provide very wide coverage (in contrast to current short-range solutions). However, the need for specialized receivers and laborious data collection complicate further research in this area, despite the promising initial results.

AmbiLoc solves this problem by providing a ready-made dataset of ambient radio fingerprints. The dataset has been systematically collected in multiple testbeds, including large-scale and multi-floor buildings, over the course of one year. Using AmbiLoc, any researcher can quickly experiment with ambient indoor localization, create, evaluate and compare novel localization methods.

News

2017-09-18
First public release at IPIN-2017: RSS fingerprints of FM, TV and GSM-900.

Dataset

AmbiLoc is a collection of ambient radio fingerprints (RSS and more), collected in multiple predefined locations across several testbeds. All the locations were systematically sampled in a time-lapse manner: 2-second long samples for each radio type, at each location, approximately twice a month, during one year.

TestbedDimensionsFloorsTest pointsDurationSessions
Offices 100×50 m 1, 0, -2 33+36+16 12 months 23
Campus 80×80 m 1, 0 13+13 12 months 20
Apartment 14×7 m 3 37 3 months 6

For more technical details, please refer to documentation.

License

AmbiLoc is available under a permissive Creative Commons Attribution 4.0 International License.
Creative Commons License

For attribution, please use this reference:

Andrei Popleteev. AmbiLoc: A year-long dataset of FM, TV and GSM fingerprints for ambient indoor localization. Proceedings of the 8th International Conference on Indoor Positioning and Indoor Navigation (IPIN-2017), Sapporo, Japan, September 2017.

Publications

The following list includes publications based on and related to AmbiLoc.

Acknowledgments

AmbiLoc is part of the INDOORS project lead by Dr. Andrei Popleteev and funded by the National Research Fund of Luxembourg.

Contact

For questions, suggestions and comments please email Email address is protected from spam. Please enable JavaScript to reveal the email.