Modelling heterogeneous location habits in human populations for location prediction under data sparsity


McInerney, James, Zheng, Jiangchuan, Rogers, Alex and Jennings, Nicholas R. (2013) Modelling heterogeneous location habits in human populations for location prediction under data sparsity At International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2013), Switzerland. 08 - 12 Sep 2013. 10 pp, pp. 469-478. (doi:10.1145/2493432.2493437).

Download

[img] PDF paper143.pdf - Author's Original
Download (494kB)

Description/Abstract

In recent years, researchers have sought to capture the daily life location behaviour of groups of people for exploratory, inference, and predictive purposes. However, development of such approaches has been limited by the requirement of personal semantic labels for locations or social/spatial overlap between individuals in the group. To address this shortcoming, we present a Bayesian model of mobility in populations (i.e., groups without spatial or social interconnections) that is not subject to any of these requirements. The model intelligently shares temporal parameters between people, but keeps the spatial parameters speci?c to individuals. To illustrate the advantages of population modelling, we apply our model to the dif?cult problem of overcoming data sparsity in location prediction systems, using the Nokia dataset comprising 38 individuals, and ?nd a factor of 2.4 improvement in location prediction performance against a state-of-the-art model when training on only 20 hours of observations.

Item Type: Conference or Workshop Item (Paper)
Digital Object Identifier (DOI): doi:10.1145/2493432.2493437
Venue - Dates: International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2013), Switzerland, 2013-09-08 - 2013-09-12
Related URLs:
Keywords: human behavior learning, mobile phone sensing, human activity inference, graphical models
Subjects:
Organisations: Agents, Interactions & Complexity
ePrint ID: 354656
Date :
Date Event
8 September 2013e-pub ahead of print
Date Deposited: 29 Jul 2013 10:51
Last Modified: 17 Apr 2017 15:14
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/354656

Actions (login required)

View Item View Item