thesis_background.ppt

28
1 Location Modeling and Location Modeling and Machine Learning in Smart Machine Learning in Smart Environments Environments Robert Whitaker Robert Whitaker Supervisor: A/Prof Judy Kay Supervisor: A/Prof Judy Kay A/Prof Bob A/Prof Bob Kummerfeld Kummerfeld

Upload: butest

Post on 26-Jun-2015

210 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: thesis_background.ppt

1

Location Modeling and Machine Location Modeling and Machine Learning in Smart EnvironmentsLearning in Smart Environments

Robert WhitakerRobert Whitaker

Supervisor: A/Prof Judy KaySupervisor: A/Prof Judy Kay A/Prof Bob KummerfeldA/Prof Bob Kummerfeld

Page 2: thesis_background.ppt

2

OverviewOverview

Problem Previous Work Possible Data Sources Tools Available Issues

Page 3: thesis_background.ppt

3

Thesis TopicThesis Topic

Explore ways of determining a persons current location and activity

Explore ways of predicting a persons location/activity using Location Modeling and Machine Learning

The results returned must be scrutable

Page 4: thesis_background.ppt

4

Possible SituationPossible Situation

Where’s Boris Scenario Wish to organize a meeting with

another person where the time suits both parties

Page 5: thesis_background.ppt

5

Possible StepsPossible Steps

Contact the person you wish to meet Both people would look at their

schedules and negotiate a time Both parties agree on the time they are

to meet

Page 6: thesis_background.ppt

6

Possible ProblemsPossible Problems

One of the persons schedule may be incomplete

When you arrive at the meeting time the person is not there. Should you wait? Where is the person?

What if you can’t connect the person to organise the meeting

Page 7: thesis_background.ppt

7

High Level ViewHigh Level View

PDA

Machine Use Saving of RawData Database of Raw

Facts

Conversion intoLogical

RepresentationDatabase ofLogical DataUser Model

Creator - personisData store of

model info

User

Where is X mostlikely to be?

Build Result Setusing Markov

Model

Page 8: thesis_background.ppt

8

Previous WorkPrevious Work

Active Badge Project Lancaster Guide Project Doppelganger Activity Compass Project

Page 9: thesis_background.ppt

9

Active Badge ProjectActive Badge Project

First Indoor positioning system Users wear badges to emit their

location Applied to teleporting Active Bat project extended the basic

concepts developed

Source: Nigel Davies and Hans-Werner Gellersen Beyond Prototypes: Challenges in Deploying Ubiquitous Systems. IEEE Pervasive Computing, Volume 1 (Jan-March 2002). 26-35.

Page 10: thesis_background.ppt

10

Lancaster Guide ProjectLancaster Guide Project

A tourist guide for the city of Lancaster Used tablet PC’s connected to a

802.11 network Limited by the infrastructure

capabilities.

Source: 1. Nigel Davies and Hans-Werner Gellersen Beyond Prototypes: Challenges in Deploying Ubiquitous Systems. IEEE Pervasive Computing, Volume 1 (Jan-March 2002). 26-35.2. The Guide Project, http://www.guide.lancs.ac.uk

Page 11: thesis_background.ppt

11

Lancaster Guide InterfaceLancaster Guide Interface

Source: The Guide Project, http://www.guide.lancs.ac.uk

Page 12: thesis_background.ppt

12

DoppelgangerDoppelganger

Generalized tool for gathering, processing and providing information about users

Learning Techniques Beta Distribution Linear Prediction Markov Models

DopMail

Source: Orwant, J., Heterogeneous Learning in the Doppelganger User Modeling System. in User Modeling and User-Adapted Interaction, (1995), 107-130.

Page 13: thesis_background.ppt

13

DoppelgangerDoppelganger

Applications

BetaDistribution

Linear Prediction

MarkovModels

LearningToolboxSensors

Source: Orwant, J., Heterogeneous Learning in the Doppelganger User Modeling System. in User Modeling and User-Adapted Interaction, (1995), 107-130.

Page 14: thesis_background.ppt

14

Activity Compass ProjectActivity Compass Project

Location Modeling to help disabled PDA device application developed to

assist with location tracking Tracking movements and comparing

them to a map Prediction algorithms used Relational

Markov Models

Source: Patterson, D.J., Etzioni, O. and Kautz, H. The Activity Compass, University of Washington, 2003.

Page 15: thesis_background.ppt

15

Prototype of Activity CompassPrototype of Activity Compass

Source: Patterson, D.J., Etzioni, O. and Kautz, H. The Activity Compass, University of Washington, 2003.

Page 16: thesis_background.ppt

16

Possible Data SourcesPossible Data Sources

Bluetooth Devices Machine Learning

Windows Based Unix Based

Page 17: thesis_background.ppt

17

ToolsTools

Personis Elvin Messaging Bspy Markov Modeling Toolkits Manual Logs for Evaluation Purposes

Page 18: thesis_background.ppt

18

PersonisPersonis

User modeling software Accretion representation

Consists of components which model aspects of the user

Allows the user model to be scruntised

Source: Kay, J., Kummerfeld, B. and Lauder, P., Managing private user models and shared personas. in Workshop on User Modelling for Ubiquitous Computing, (Pittsburgh, USA, 2003).

Page 19: thesis_background.ppt

19

Example of User ModelExample of User Model

Output from Personis: Modeling the locations where the user has been

Page 20: thesis_background.ppt

20

Elvin MessagingElvin Messaging

Publish/Subscribe Messaging System Messages routed by content Application: sending messages

between sensors and modeling software

Elvin Router

Client

Client Client

Client

Source: Mantara Software Elvin Administrator's Guide, 2003.

Page 21: thesis_background.ppt

21

BspyBspy

Bluetooth positioning system Detects Bluetooth devices and logs

them to a database Uses Elvin messages to send

information from sensor to database

Page 22: thesis_background.ppt

22

Example DataExample Data

Page 23: thesis_background.ppt

23

Markov Modeling ToolkitsMarkov Modeling Toolkits

Hidden Markov Modeling Package – Python

Matlab Hidden Markov Package Markov Chain Algorithm Cambridge Markov Modeling Toolkit

Page 24: thesis_background.ppt

24

Manual LogsManual Logs

Records activity and location in 15 min blocks

Provides some example data to develop the algorithms off

Used for the evaluation of the learning algorithm

Page 25: thesis_background.ppt

25

Code SheetCode Sheet

Page 26: thesis_background.ppt

26

Manual LogManual Log

Page 27: thesis_background.ppt

27

Research IssuesResearch Issues

Representation of location and activity Creation of data sets Modeling Time

Page 28: thesis_background.ppt

28

QuestionsQuestions