Download PPT - Spatial Database Group

Modeling Spatial and Spatio-temporal
Co-occurrence Patterns
Mete Celik
Spatial Database / Data Mining Group
Department of Computer Science
University of Minnesota
[email protected]
Advisor: Shashi Shekhar
MDCOP Motivating Example : Input
• Manpack stinger
(2 Objects)
• M1A1_tank
(3 Objects)
• M2_IFV
(3 Objects)
• Field_Marker
(6 Objects)
• T80_tank
(2 Objects)
• BRDM_AT5
(enemy) (1 Object)
• BMP1
(1 Object)
6
MDCOP Motivating Example : Output
• Manpack stinger
(2 Objects)
• M1A1_tank
(3 Objects)
• M2_IFV
(3 Objects)
• Field_Marker
(6 Objects)
• T80_tank
(2 Objects)
• BRDM_AT5
(enemy) (1 Object)
• BMP1
(1 Object)
7
Real Dataset Description

Vehicle movement dataset




15 time slots, x and y coordinates are in meter
22 distinct vehicle types and their instances
Minimum instance number 2, maximum instance number 78
Average instance number 19
Example Input from Spatio-temporal Dataset
Output: Spatio-temporal Co-occurrence Pattern
(Manpack_stinger <M1, M2> ,
fire cover (e,g., Bradley tank <T1, T2>))
36
Spatio-temporal Co-occurrence Pattern Taxonomy
1. Spatial co-location

Global and zonal co-location patterns, etc.
2. Co-occurrence patterns of moving objects

Flock pattern, mixed-drove pattern, follow pattern, moving clusters, etc.
3. Emerging or vanishing co-occurrence patterns


Emerging pattern: Interest measure getting stronger by the time
Vanishing pattern: Interest measure getting weaker by the time
Multidrug-resistant tuberculosis
Drug-resistant Malaria
Hepatitis C
SARS
4. Co-evolving patterns
West
Nile
5. Periodic co-occurrence patterns
Influenza
H5N1
http://upload.wikimedia.org/wikipedia/en/c/cd/Original_distribution_of_wolf_subspecies.GIF
http://www.argentinapurses.com/football/formLabel.gif
 ICDM05 - Discovering
co-evolving spatio-temporal event sets
6. Spatio-temporal
cascade
patterns
Game (tactics)
– mixed-drove pattern
Dengue
Colera
HIV/AIDS
Ecology – zonal co-location pattern
Emerging and
Infectious
Diseases
. . .TKDE08
ICDM06
- Mixed-Drove Spatio-Temporal Co-occurrence
Mining
Sustained
emerging
co-occurrence
patterns
 Pattern
ICDM07
– Zonal
Co-location
Pattern Mining
 ICDE-STDM07
- Mining
At Most
Top-K% Mixed-drove
Spatio-temporal
ICTAI06
Emerging
Spatio-temporal
Co-occurrence
Pattern Mining
ICDM05 –- Sustained
Joinless
Approach
for
Co-location
Pattern
Mining
Co-occurrence Patterns
50
Chapter 2- Zonal Co-location Pattern Discovery
Given: different object
types of spatial
events and zone
boundaries
Find : Co-located
subset of event
types specific to
zones
Method: A novel
algorithm by using
an indexing
structure.
1
2
4
3
Zones 2,4
Zone 3
51
Chapter 4 - Sustained Emerging ST Co-occurrence Pattern
Discovery



Given: A set P of
Boolean ST object-types
over a common ST
framework
Find: Sustained
emerging spatiotemporal co-occurrence
patterns whose
prevalence measure
increase over time.
Multidrug-resistant tuberculosis
Drug-resistant Malaria
Hepatitis C
SARS
West
Nile
Dengue
Influenza
H5N1
Colera
HIV/AIDS
Method: Developing
novel algorithms by
defining monotonic
interest measures.
52
Future Work – Short Term
1.
Spatial co-location


2.
Co-occurrence patterns of moving objects

3.
Flock pattern, mixed-drove pattern, follow
pattern, cross pattern, moving clusters, etc.
Efficient methods
•
Comparison of int.
measures with
statistical int. measures
Emerging or vanishing co-occurrence
patterns


4.
Interest measure: participation index
Global and zonal co-location patterns, etc.
•
Emerging pattern: Interest measure getting
stronger by the time
Vanishing pattern: Interest measure getting
weaker by the time
Co-evolving patterns
5. Periodic co-occurrence patterns
6. Spatio-temporal cascade patterns
53
Future Work – Long Term

Spatial and Spatio-temporal Pattern Mining Design


Crime Analysis, GIS, Epidemiology
Challenges

discovering patterns and anomalies from enormous frequently updated
spatial and spatio-temporal datasets,

developing an ontological framework for spatial and spatio-temporal
analysis,

integrating spatial and spatio-temporal data from multiple agencies,
distributed data, and multi-scale data
54
Acknowledgements

Adviser: Prof. Shashi Shekhar

Committee: Prof. Jaideep Srivastava, Prof. Arindam Banerjee, and Prof.
Sudipto Banerjee

Spatial Databases and Data Mining Group

TEC collaborators: James P. Rogers, James A. Shine

Dept. of Computer Science
55
References
[1] J. Gudmundsson, M. v. Kreveld, and B. Speckmann, Efficient Detection of Motion
Patterns in Spatio-Temporal Data Sets, ACM-GIS,250-257, 2004.
[2] P. Laube and S. Imfeld, Analyzing relative motion within groups of trackable
moving point objects, in In GIScience, number 2478 in Lecture notes in Computer
Science. Berlin: Springer, pp. 132-144, 2002.
[3] P. Kalnis, N. Mamoulis, and S. Bakiras, On Discovering Moving Clusters in Spatiotemporal Data, 9th Int'l Symp. on Spatial and Temporal Databases (SSTD), Angra
dos Reis, Brazil, 2005.
[4] Y. Huang, S. Shekhar, and H. Xiong, Discovering Co-location Patterns from Spatial
Datasets: A General Approach, IEEE Trans. on Knowledge and Data Eng. (TKDE),
vol. 16(12), pp. 1472-1485, 2004.
[5] M. Hadjieleftheriou, G. Kollios, P. Bakalov, and V. J. Tsotras, Complex SpatioTemporal Pattern Queries, VLDB, pp. 877-888, 2005.
[6] C. du Mouza and P. Rigaux, Mobility Patterns, GeoInformatica, 9(4), 297-319,
2005.
[7] J. S. Yoo and S. Shekhar, A Join-less Approach for Mining Spatial Co-location
Patterns, IEEE Trans. on Knowledge and Data Eng. (TKDE), Vol.18, No.10, 2006.
56