We present a framework to automatically discover people’s routines from information extracted by cell phones. The framework is built from a probabilistic topic model learned on novel bag type representations of activity-related cues (location, proximity and their temporal variations over a day) of peoples ’ daily routines. Using real-life data from the Reality Mining dataset, covering 68 000+ hours of human activities, we can successfully discover location-driven (from cell tower connections) and proximity-driven (from Bluetooth information) routines in an unsupervised manner. The resulting topics meaningfully characterize some of the underlying co-occurrence structure of the activities in the dataset, including “going to work early/late”, “being home all day”, “working constantly”, “working sporadically” and “meeting at lunch time”. 1.
Description
Discovering Human Routines from Cell Phone Data with Topic Models
%0 Generic
%1 Farrahi_discoveringhuman
%A Farrahi, Katayoun
%A Gatica-perez, Daniel
%D 2010
%K clustering toread
%T Discovering Human Routines from Cell Phone Data with Topic Models
%U http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.139.5105
%X We present a framework to automatically discover people’s routines from information extracted by cell phones. The framework is built from a probabilistic topic model learned on novel bag type representations of activity-related cues (location, proximity and their temporal variations over a day) of peoples ’ daily routines. Using real-life data from the Reality Mining dataset, covering 68 000+ hours of human activities, we can successfully discover location-driven (from cell tower connections) and proximity-driven (from Bluetooth information) routines in an unsupervised manner. The resulting topics meaningfully characterize some of the underlying co-occurrence structure of the activities in the dataset, including “going to work early/late”, “being home all day”, “working constantly”, “working sporadically” and “meeting at lunch time”. 1.
@misc{Farrahi_discoveringhuman,
abstract = {We present a framework to automatically discover people’s routines from information extracted by cell phones. The framework is built from a probabilistic topic model learned on novel bag type representations of activity-related cues (location, proximity and their temporal variations over a day) of peoples ’ daily routines. Using real-life data from the Reality Mining dataset, covering 68 000+ hours of human activities, we can successfully discover location-driven (from cell tower connections) and proximity-driven (from Bluetooth information) routines in an unsupervised manner. The resulting topics meaningfully characterize some of the underlying co-occurrence structure of the activities in the dataset, including “going to work early/late”, “being home all day”, “working constantly”, “working sporadically” and “meeting at lunch time”. 1.},
added-at = {2010-09-20T16:20:29.000+0200},
author = {Farrahi, Katayoun and Gatica-perez, Daniel},
biburl = {https://www.bibsonomy.org/bibtex/24c905f2cfc5e88c271ebc4f10d47de30/hotho},
description = {Discovering Human Routines from Cell Phone Data with Topic Models},
interhash = {5e3f9c64f6fb9ba5226e3345acd3ddd8},
intrahash = {4c905f2cfc5e88c271ebc4f10d47de30},
keywords = {clustering toread},
timestamp = {2010-09-20T16:20:29.000+0200},
title = {Discovering Human Routines from Cell Phone Data with Topic Models},
url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.139.5105},
year = 2010
}