Paper Info
Title
Methodologies for Continuous Cellular Tower Data Analysis
Abstract
This paper presents novel methodologies for the analysis of continuous cellular tower data from 215 randomly sampled subjects in a major urban city. We demonstrate the potential of existing community detection methodologies to identify salient locations based on the network generated by tower transitions. The tower groupings from these unsupervised clustering techniques are subsequently validated using data from Bluetooth beacons placed in the homes of the subjects. We then use these inferred locations as states within several dynamic Bayesian networks (DBNs) to predict dwell times within locations and each subject's subsequent movements with over 90% accuracy. We also introduce the X-Factor model, a DBN with a latent variable corresponding to abnormal behavior. By calculating the entropy of the learned X-Factor model parameters, we find there are individuals across demographics who have a wide range of routine in their daily behavior. We conclude with a description of extensions for this model, such as incorporating contextual and temporal variables already being logged by the phones.
Year
DOI
Venue
2009
10.1007/978-3-642-01516-8_23
Pervasive
Keywords
Field
DocType
tower transition,community detection methodology,daily behavior,x-factor model,abnormal behavior,continuous cellular tower data,dwell time,x-factor model parameter,dynamic bayesian network,tower grouping,factor model,latent variable,data analysis
Beacon,Data mining,Tower,Computer science,Latent variable,Artificial intelligence,Mobile phone,Cluster analysis,Machine learning,Bluetooth,Salient,Dynamic Bayesian network
Conference
Volume
ISSN
Citations 
5538
0302-9743
10
PageRank 
References 
Authors
0.68
15
3
Name
Order
Citations
PageRank
Nathan Eagle11806141.61
John A. Quinn212814.49
Aaron Clauset32033146.18