/breadcrumbsDB

This repository contains documentation of the Breadcrumbs database. Breadcrumbs is a rich mobility dataset collected from multiple sensors (incl. GPS, GSM, WiFi, Bluetooth) on the smartphones of 81 individuals. In addition to sensor data, Breadcrumbs contains ground-truth data regarding people points of interest (incl. semantic labels) as well as demographic attributes, contact records, calendar events, lifestyle information, and social relationship labels between the participants of the study.

MIT LicenseMIT

What is Breadcrumbs

Breadcrumbs is a rich mobility (geospatial) dataset. This data collection campaign was launched in the spring of 2018 and was set for a timespan of 3 months. The dataset contains multi-sensor data (incl. GPS, GSM, WiFi, Bluetooth) logged on the smartphones of 80 individuals (with their consent and all the due permissions from the ethical board), around the lake Geneva region of Switzerland. In addition to the smartphone sensor data, Breadcrumbs also contains ground-truth data regarding people points of interest (incl. semantic labels) as well as demographic attributes, contact records, calendar events, lifestyle information, and social relationship labels between the participants of the study. These unique attributes makes Breadcrumbs ideal for several research areas including: location privacy, human mobility prediction, mobility behavior modeling, benchmarking point of interest retrieval techniques to name a few.

What exactly does the dataset contain?

  • GPS coordinates: Latitude, Longitude, Altitude and Timestamp
  • Bluetooth: Scanned device UUID's and Timestamp
  • Wi-Fi: Scanned SSID's and Timestamp
  • Smartphone notification events
  • User demographics (30 different attributes)
  • Point of Interests of all participants with the description
  • Participant relationships

How do I avail Breadcrumbs Dataset?

Currently we will only share the dataset with researchers affiliated with a university. To avail Breadcrumbs fill the Dataset sharing license agreement and pay attention to the following criteria when you fill the DSLA form.

  • Fill the appropriate fields of the dataset sharing license agreement on your computer (there are editable fields to do so): pages 1, 4, 5, 8, and 10,
  • Print it,
  • Sign it manually (only wet-ink signatures are accepted, and electronic signatures are NOT recognized): pages 4 and 8,
  • Scan it,
  • And send it back to us via email breadcrumbs@unil.ch.

We will than share a (unique) link with you to download the dataset.

How does the Schema of this dataset look like?

alt text

Where can I find the complete documentation of Breadcrumbs?

Breadcrumbs Documentation

Where can I find the Breadcrumbs published research paper?

Breadcrumbs: A Rich Mobility Dataset with Point-of-Interest Annotations

What should I Cite if I use this dataset to publish my research?

Arielle Moro, Vaibhav Kulkarni, Pierre-Adrien Ghiringhelli, Bertil Chapuis, Kévin Huguenin, and Benoît Garbinato. 2019. Breadcrumbs: A Rich Mobility Dataset with Point-of-Interest Annotations. In Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPATIAL '19). Association for Computing Machinery, New York, NY, USA, 508–511. DOI:https://doi.org/10.1145/3347146.3359341