Breaking the habit: measuring and predicting departures from routine in individual human mobility


McInerney, J., Stein, S., Rogers, A and Jennings, N. R. (2013) Breaking the habit: measuring and predicting departures from routine in individual human mobility. Pervasive and Mobile Computing, 9, (6), 808-822. (doi:10.1016/j.pmcj.2013.07.016).

Download

[img]
Preview
PDF
Download (316Kb) | Preview
[img]
Preview
PDF
Download (880Kb) | Preview

Description/Abstract

Researchers studying daily life mobility patterns have recently shown that humans are typically highly predictable in their movements. However, no existing work has examined the boundaries of this predictability, where human behaviour transitions temporarily from routine patterns to highly unpredictable states. To address this shortcoming, we tackle two interrelated challenges. First, we develop a novel information-theoretic metric, called instantaneous entropy, to analyse an individual’s mobility patterns and identify temporary departures from routine. Second, to predict such departures in the future, we propose the first Bayesian framework that explicitly models breaks from routine, showing that it outperforms current state-of-the-art predictors

Item Type: Article
Digital Object Identifier (DOI): doi:10.1016/j.pmcj.2013.07.016
ISSNs: 1574-1192 (print)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Physical Sciences and Engineering > Electronics and Computer Science > Agents, Interactions & Complexity
ePrint ID: 356175
Date :
Date Event
September 2013Made publicly available
2013Published
Date Deposited: 02 Sep 2013 10:18
Last Modified: 31 Mar 2016 14:57
Projects:
HUMAN-AGENT COLLECTIVES: FROM FOUNDATIONS TO APPLICATIONS [ORCHID]
Funded by: EPSRC (EP/I011587/1)
Led by: Nick Jennings
1 January 2011 to 31 December 2015
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/356175

Actions (login required)

View Item View Item

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics