I=
Pakistan Research Repository Home
 

Title of Thesis

Classification and Associative Classification Rule Discovery Using Ant Colony Optimization

Author(s)

Waseem Shahzad

Institute/University/Department Details
Department of Computer Science / Fast-National University of Computer and Emerging Sciences, Islamabad
Session
2010
Subject
Computer Science
Number of Pages
164
Keywords (Extracted from title, table of contents and abstract of thesis)
Research, Models, Associative, Ability, Classification, Optimization, Distributed, Discovery, Decrease, Rule, Colony, Variants, Ant, Features, Experiments

Abstract
The primary goal of this research is to investigate the suitability of ant colony optimization, a swarm intelligence based meta-heuristic developed by mimicking some aspects of the food foraging behavior of ants, for building accurate and comprehensible classifiers which can be learned in reasonable time even for large datasets. Towards this end, a novel classification rule discovery algorithm called AntMiner-C and its variants are proposed.Various aspects and parameters of the proposed algorithms are investigated by experimentation on a number of benchmark datasets. Experimental results indicate that the proposed approach builds more accurate models when compared with commonly used classification algorithms.It is also computationally less expensive than previously available ant colony algorithm based classification rules discovery algorithms.
A hybrid classifier using ant colony optimization is also proposed that combines association rules mining and supervised classification. Experiments show that the proposed algorithm has the ability to discover high quality rules. Furthermore, it has the advantage that association rules of each class can be mined in parallel if distributed processing is used. Experimental results demonstrate that the proposed hybrid classifier achieves higher accuracy rates when compared with other commonly used classification algorithms.
A feature subset selection algorithm is also proposed which is based on ant colony optimization and decision trees.Experiments show that better accuracy is achieved if the subset of features selected by the proposed approach is used instead of full feature set and number of rules is also decreased substantially.

Download Full Thesis
2,965 KB
S. No. Chapter Title of the Chapters Page Size (KB)
1 0 CONTENTS

 

iv
148 KB
2

1

INTRODUCTION

1.1 Research Background
1.2 Research Contributions
1.3 Layout of Thesis

1
302 KB
3 2 CLASSIFICATION SYSTEM AND CLASSIFICATION TECHNIQUES

2.1 Classification
2.2 Performance Evaluation of Classification Methods
2.3 Types of Classifiers
2.4 Summary

5
143 KB
4 3 SWARM INTELLIGENCE AND ANT MINERS

3.1 Swarm intelligence
3.2 Ant Colony Optimization
3.3 ACO Based Classification Rule Discovery: AntMiner Algorithms
3.4 Summary

12
184 KB
5

4

CORRELATION BASED ANT MINER

4.1 Introduction
4.2 Correlation Based AntMiner (AntMiner–C)
4.3 Summary

22
743 KB
6

5

INVESTIGATION OF COMPONENTS AND PARAMETER OPTIMIZATION

5.1 Experiments and Analysis
5.2 Analysis of Different Algorithmic Components
5.3 Improved AntMiner-C
5.4 Parameter Optimization
5.5 Results and Comparisons
5.6 Time Complexity of AntMiner-C
5.7 Summary

44
271 KB
7

6

FURTHER IMPROVEMENTS AND INVESTIGATIONS

6.1 Modified Algorithm: AntMiner-CC
6.2 Differences with previous versions
6.3 Heuristic Function of AntMiner-CC
6.4 Default Rule
6.5 Experiments and Analysis
6.6 Comparison with Other Algorithms
6.7 Summary

70
261 KB
8

7

ASSOCIATIVE CLASSIFICATION USING ANT COLONY OPTIMIZATION

7.1 Associative Rules Mining and Associative Classification
7.2 Differences with AntMiner-C and AntMiner-CC
7.3 Proposed Technique
7.4 Experiments and Analysis
7.5 Time Complexity of ACO-AC
7.6 Summary

89
690 KB
9

8

FEATURE SELECTION BASED ON ANT COLONY OPTIMIZATION

8.1 Introduction
8.2 Decision Trees
8.3 Proposed Technique
8.4 Experimentation and Analysis
8.5 Summary

113
709 KB
10

9

CONCLUSIONS & FUTURE WORK

9.1 Conclusion
9.2 Future Work
 

132
110 KB
11

10

REFERENCES

 

135
172 KB