The Smoking Event Detection (SED) and Free-living Smoking Event Detection (SED-FL) datasets

The SED and SED-FL datasets were collected by the Multimedia Understanding Group towards the investigation of in-the-wild smoking behavior (using cigarettes). Both datasets contain the 3D acceleration and orientation velocity signals (6 DoF) recorded using a commercial smartwatch (The Mobvoi Ticwatchâ„¢).

Description

The SED dataset consists of 11 subjects performing 20 smoking sessions, with a total duration of 2.69 hours. The SED-FL dataset consists of 10 all-day sessions from 7 subjects, with a total duration of 78.3 hours. Three of the subjects participate in both datasets. It should be emphasized that we asked from the subjects to smoke naturally; as a result, they were free to engage in a discussion or perform additional activities. In order to label the data in SED, we recorded the smoking sessions using the camera from a typical smartphone. To produce the GT for the all-day, in-the-wild sessions of SED-FL, a smartwatch application was developed that enabled subjects to easily note the start and end timestamps of their smoking sessions. It is worth noting that both datasets deal with the consumption of tobacco using cigarettes; no electronic cigarettes (also known as vaping devices), pipes or heated tobacco products were used.

Download

The SED and SED-FL datasets are available for download at Zenodo at a pickle format. The Zenodo link also provides access to helpful python scripts that help extract statistics and visualize the recordings.

History

  • 5/2/2021 created the dataset page

Contact

For any inquiries about the SED and SED-FL datasets contact Konstantinos Kyritsis at kokirits@mug.ee.auth.gr