论文信息 - Towards a Particle Swarm Optimization-Based Regression Rule Miner

Towards a Particle Swarm Optimization-Based Regression Rule Miner

We present the work in progress on a rule mining algorithm for regression using particle swarm optimization (PSO). Sub problems occuring during development involve the encoding of rules as particles and suitable PSO parameter tuning. A key subtask is the selection of a good rule learning heuristic. We introduce a novel heuristic for which preliminary results show promise.

David Martens | Bart Minnaert | David Martens | Bart Minnaert

[1] Thomas Stützle,et al. Improvement Strategies for the F-Race Algorithm: Sampling Design and Iterative Refinement , 2007, Hybrid Metaheuristics.

[2] Nicholas I. Fisher,et al. Bump hunting in high-dimensional data , 1999, Stat. Comput..

[3] Joachim Diederich,et al. Survey and critique of techniques for extracting rules from trained artificial neural networks , 1995, Knowl. Based Syst..

[4] Bernard Ženko,et al. Learning Predictive Clustering Rules , 2005, Informatica.

[5] M J Pazzani,et al. Acceptance of Rules Generated by Machine Learning among Medical Experts , 2001, Methods of Information in Medicine.

[6] Thomas Stützle,et al. Frankenstein's PSO: A Composite Particle Swarm Optimization Algorithm , 2009, IEEE Transactions on Evolutionary Computation.

[7] Johannes Fürnkranz,et al. Separate-and-conquer Regression , 2010, LWA.

[8] W. R. Shankle,et al. Acceptance by medical experts of rules generated by machine learning , 2001 .