An ambient monitoring system for unsupervised user modelling

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper describes a means of unsupervised learning of recurring patterns in user activity through patterns in system level events generated by a graphical user interface. Earlier work has shown that using this distillation of the more complex behavioural interaction between the user and the application provides a symbolic representation of knowledge and goals that could be used to imply preference. Although prior research has explored the possibilities of removing this information acquisition bottleneck in such an expert system using ambient monitoring approaches, some have experienced difficulty in dealing with the varying length training sequences and segmentation of the continuous event stream. Unlike previous work the approach documented here handles interactions of varying sizes and is able to recall recurrent patterns in real time irrespective of the number of interactions learned. In addition to describing the proposed approach we also describe the shortcomings of various previously applied machine learning techniques on the same type of data. We also demonstrate a practical implementation of our approach applied to web browser usage.
LanguageEnglish
Pages557-567
Number of pages10
JournalExpert Systems with Applications
Volume28
Issue number3
DOIs
Publication statusPublished - Apr 2005

Fingerprint

Unsupervised learning
Web browsers
Graphical user interfaces
Distillation
Expert systems
Learning systems
Monitoring

Keywords

  • finite state machines
  • pattern discovery
  • behaviour modelling
  • gesture recognition
  • human computer interaction
  • user interface

Cite this

@article{9df1cfded41a4f90862d35bac0c629f2,
title = "An ambient monitoring system for unsupervised user modelling",
abstract = "This paper describes a means of unsupervised learning of recurring patterns in user activity through patterns in system level events generated by a graphical user interface. Earlier work has shown that using this distillation of the more complex behavioural interaction between the user and the application provides a symbolic representation of knowledge and goals that could be used to imply preference. Although prior research has explored the possibilities of removing this information acquisition bottleneck in such an expert system using ambient monitoring approaches, some have experienced difficulty in dealing with the varying length training sequences and segmentation of the continuous event stream. Unlike previous work the approach documented here handles interactions of varying sizes and is able to recall recurrent patterns in real time irrespective of the number of interactions learned. In addition to describing the proposed approach we also describe the shortcomings of various previously applied machine learning techniques on the same type of data. We also demonstrate a practical implementation of our approach applied to web browser usage.",
keywords = "finite state machines, pattern discovery, behaviour modelling, gesture recognition, human computer interaction, user interface",
author = "B. Stephen and L. Petropoulakis",
year = "2005",
month = "4",
doi = "10.1016/j.eswa.2004.12.017",
language = "English",
volume = "28",
pages = "557--567",
journal = "Expert Systems with Applications",
issn = "0957-4174",
number = "3",

}

An ambient monitoring system for unsupervised user modelling. / Stephen, B.; Petropoulakis, L.

In: Expert Systems with Applications, Vol. 28, No. 3, 04.2005, p. 557-567.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An ambient monitoring system for unsupervised user modelling

AU - Stephen, B.

AU - Petropoulakis, L.

PY - 2005/4

Y1 - 2005/4

N2 - This paper describes a means of unsupervised learning of recurring patterns in user activity through patterns in system level events generated by a graphical user interface. Earlier work has shown that using this distillation of the more complex behavioural interaction between the user and the application provides a symbolic representation of knowledge and goals that could be used to imply preference. Although prior research has explored the possibilities of removing this information acquisition bottleneck in such an expert system using ambient monitoring approaches, some have experienced difficulty in dealing with the varying length training sequences and segmentation of the continuous event stream. Unlike previous work the approach documented here handles interactions of varying sizes and is able to recall recurrent patterns in real time irrespective of the number of interactions learned. In addition to describing the proposed approach we also describe the shortcomings of various previously applied machine learning techniques on the same type of data. We also demonstrate a practical implementation of our approach applied to web browser usage.

AB - This paper describes a means of unsupervised learning of recurring patterns in user activity through patterns in system level events generated by a graphical user interface. Earlier work has shown that using this distillation of the more complex behavioural interaction between the user and the application provides a symbolic representation of knowledge and goals that could be used to imply preference. Although prior research has explored the possibilities of removing this information acquisition bottleneck in such an expert system using ambient monitoring approaches, some have experienced difficulty in dealing with the varying length training sequences and segmentation of the continuous event stream. Unlike previous work the approach documented here handles interactions of varying sizes and is able to recall recurrent patterns in real time irrespective of the number of interactions learned. In addition to describing the proposed approach we also describe the shortcomings of various previously applied machine learning techniques on the same type of data. We also demonstrate a practical implementation of our approach applied to web browser usage.

KW - finite state machines

KW - pattern discovery

KW - behaviour modelling

KW - gesture recognition

KW - human computer interaction

KW - user interface

U2 - 10.1016/j.eswa.2004.12.017

DO - 10.1016/j.eswa.2004.12.017

M3 - Article

VL - 28

SP - 557

EP - 567

JO - Expert Systems with Applications

T2 - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 3

ER -