An Approach to Active Spatial Data Mining - PowerPoint PPT Presentation

About This Presentation
Title:

An Approach to Active Spatial Data Mining

Description:

Conclusions STING+ is an efficient approach to active spatial data mining. Users can define triggers to monitor the change of spatial data. – PowerPoint PPT presentation

Number of Views:85
Avg rating:3.0/5.0
Slides: 15
Provided by: weiwang
Learn more at: https://www.cs.unc.edu
Category:

less

Transcript and Presenter's Notes

Title: An Approach to Active Spatial Data Mining


1
An Approach to Active Spatial Data Mining
STING
  • Wei Wang
  • Data Mining Lab, UCLA
  • March 24, 1999

2
Outline
  • Introduction
  • Spatial Data Mining Triggers
  • Strategies
  • Performance
  • Conclusions

3
Introduction
  • Huge amount of spatial data are generated
    everyday.
  • Earth Observing System
  • National Spatial Data Infrastructure
  • National Image Mapping Agency
  • one meter resolution data
  • digital earth
  • Users are usually interested in the hidden
    information.
  • Aggregate information
  • Clustering
  • Patterns

4
Introduction
  • Knowledge discovery processes are computationally
    expensive.
  • Todays technology advances provide necessary
    computing power to carry out such complicated
    processes.

5
Spatial Data mining Triggers
  • Since data evolves over time, interesting
    patterns are likely to emerge or change.
  • Goal identify and find (most of) interesting
    patterns
  • Problems
  • Knowledge discovery processes are expensive.
  • It is not feasible to re-process the entire
    data set for every change.
  • Approach to periodically examine the data.
  • Long delays
  • Transient patterns might be missed
  • Natural solution Usage of triggers.

6
Spatial Data mining Triggers
  • Traditional database triggers can not be directly
    applied
  • Expressive power of traditional database triggers
    is limited, especially in describing spatial
    relationships.
  • Example Trigger bandwidth reallocation when the
    size of a cluster exceeds 20.

7
Strategies
  • STING was designed to introduce and support
    spatial triggers efficiently.
  • Observation (spatial locality) Only objects
    added to the shaded area will contribute to the
    growth of cluster size at this moment.

8
Strategies
  • STING Strategy Monitor only the area occupied
    by potential clusters and its neighborhood.
  • Observation (cumulative effect) at least 4 more
    objects are needed in order to make the cluster
    size be 20.
  • STING Strategy Space is organized in a
    hierarchy so that updates can be suspended at
    some level in the hierarchy until the cumulative
    effect might cause the trigger to be fired.

9
Strategies
  • Space is recursively divided into smaller
    rectangular cells down to a specified granularity
    and is organized via the inherit pyramid
    hierarchy.

Level 1
10
Strategies
  • STING decomposes a trigger into a set of
    sub-triggers associated with individual cells in
    the hierarchical structure to monitor the
    cumulative effect of data changes within the cell.

Sub-trigger on cell
Higher level sub-trigger on cell
11
Strategies
  • Updates/insertions are suspended at some level in
    the hierarchy until such time that the cumulative
    effect of these insertions might cause the
    trigger condition to become satisfied.

.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.








.
.
.
.
.
.
.
.
.
.
Level 1
Level 0
12
Strategies
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.








.
.
.
.
.
.
.
.
.
.
Level 3
Level 2
No update of cluster !
13
Performance
  • Comparison with periodic re-examination
  • If the period is set to be less than 4000
    updates, STING consumes less CPU cycles.
  • Significant delay and transient patterns misses
    can occur for larger period.
  • Not acceptable in many applications
  • No delay and no transient patterns missed with
    STING.

14
Conclusions
  • STING is an efficient approach to active spatial
    data mining.
  • Users can define triggers to monitor the change
    of spatial data.
  • Updates to the data are carefully monitored
  • Evaluation of trigger is postponed until the
    cumulative effect of data updates might cause the
    trigger to be fired.
Write a Comment
User Comments (0)
About PowerShow.com