Improving the performance of hierarchical classification with swarm intelligence

Authors:
Nicholas Holden;Alex A. Freitas
Affiliations:
Computing Laboratory, University of Kent, Canterbury, UK;Computing Laboratory, University of Kent, Canterbury, UK
Venue:
EvoBIO'08 Proceedings of the 6th European conference on Evolutionary computation, machine learning and data mining in bioinformatics
Year:
2008

Citing 5
Cited 3

Swarm intelligence

Swarm intelligence
Introduction to Evolutionary Computing

Introduction to Evolutionary Computing
Ant Colony Optimization

Ant Colony Optimization
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)
A hybrid PSO/ACO algorithm for classification

Proceedings of the 9th annual conference companion on Genetic and evolutionary computation

Novel top-down approaches for hierarchical classification and their application to automatic music genre classification

SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
A survey of hierarchical classification across different application domains

Data Mining and Knowledge Discovery
Selecting different protein representations and classification algorithms in hierarchical protein function prediction

Intelligent Data Analysis

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper we propose a new method to improve the performance of hierarchical classification. We use a swarm intelligence algorithm to select the type of classification algorithm to be used at each "classifier node" in a classifier tree. These classifier nodes are used in a top-down divide and conquer fashion to classify the examples from hierarchical data sets. In this paper we propose a swarm intelligence based approach which attempts to mitigate a major drawback with a recently proposed local search-based, greedy algorithm. Our swarm intelligence based approach is able to take into account classifier interactions whereas the greedy algorithm is not. We evaluate our proposed method against the greedy method in four challenging bioinformatics data sets and find that, overall, there is a significant increase in performance.