Professional Documents
Culture Documents
ON
DATA MINING
TOPIC: MINING COMPLEX TYPES OF DATA
BY
P.ISWARYA
II MSC (CS)
CONTENTS
• INTRODUCTION
• MULTIDIMENSIONAL ANALYSIS AND
DESCTIPTIVE MINING OF COMPLEX
DATA OBJECTS.
• SPATIAL DATA MINING
• MULTIMEDIA DATA MINING
• CONCLUSION
• REFERENCES
1. Introduction
An increasingly important task in data mining is to
mine complex types of data, including multidimensional and
descriptive analysis of complex objects, spatial data mining,
multimedia data mining, time-series data mining, mining text data
bases and the mining in World Wide Web. In this section we are
going to discuss the first three types.
Multidimensional Analysis
Strategy
Generalize the plan base in different directions.
Look for sequential patterns in the generalized plans.
Derive high-level plans.
A multi-D model for the plan base
Multidimensional Generalization
Multi-D generalization of the plan base
Fact table
Dimension table
Spatial merge
Precomputing all: too much storage space
On-line merge: very expensive.
Methods for Computation of Spatial Data Cube
On-line aggregation: collect and store pointers to spatial objects in
a spatial data cube.
It is expensive and slow, need efficient aggregation
techniques.
Precompute and store all the possible combinations.
Huge space overhead
Precompute and store rough approximations in a spatial data
cube (e.g. use grids)
Accuracy trade-off
Selective computation: only materialize those which will be
accessed frequently
A reasonable choice
6.References
“Data mining concepts and techniques“by Jiawei Han and
Macheline Kamber.
Websites:
http://www.slideshare.net/achmatim/08-mining-type-of-
complex-data
http://www.spatial.cs.umn.edu/
http://www.warez-files.com/direct-download/2109784-
Managing-and-Mining-Multimedia-Databases.html