Developing attention focus metrics for autonomous hypothesis generation in data mining

Authors:
Bing Wang;Kathryn E. Merrick;Hussein A. Abbass
Affiliations:
School of Engineering and Information Technology, University of New South Wales, Canberra, Australia;School of Engineering and Information Technology, University of New South Wales, Canberra, Australia;School of Engineering and Information Technology, University of New South Wales, Canberra, Australia
Venue:
SEAL'12 Proceedings of the 9th international conference on Simulated Evolution and Learning
Year:
2012

Citing 5
Cited 0

Data mining and knowledge discovery in databases

Communications of the ACM
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series)

Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series)
Ontology-driven hypothesis generation to explain anomalous patient responses to treatment

Knowledge-Based Systems
Intrinsic Motivation Systems for Autonomous Mental Development

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

When facing a data mining task, human experts tend to be responsible for proposing the hypotheses that lead to the discovery of interesting patterns. Recently, there is interest in automating the hypothesis generation process to reduce the load on the human expert during data mining. However, if we want an artificial agent to undertake this new role, we also need new metrics to measure the success of the hypothesis generation mechanism. This paper explores the design of metrics for evaluating hypothesis generation algorithms in terms of differences in the way they focus attention in the data mining search-space. We demonstrate our new metrics applied to three stochastic search based prototype hypothesis generation algorithms. Results show that some differences in attention focus can be identified using our metrics. Directions for further work in attention focus metrics and hypothesis generation algorithms are discussed.