The effects of mutation and directed intervention crossover when applied to scheduling chemotherapy

This paper discusses the effects of mutation and directed intervention crossover approaches when applied to the derivation of cancer chemotherapy treatment schedules. Unlike traditional Uniform Crossover (UC), the directed intervention techniques actively choose the intervention level based on the fitness of the parents selected for crossover. This work describes how directed intervention crossover principles are more robust to mutation and lead to significant improvement over UC when applied to cancer chemotherapy treatment scheduling. Categories and Subject Descriptors F.2.2 [Problem Solving, Control Methods, and Search]: Sequencing and scheduling; G.3 [Probability and Statistics]: Time series analysis; I.2.8 [Problem Solving, Control Methods, and Search]: Scheduling General Terms Algorithms Keywords Genetic Algorithms, Time Series, Chemotherapy, Crossover

• Type: Conference
• Year: 2008
• Where: GECCO
• Authors: Paul M. Godley, David E. Cairns, Julie Cowie, Kevin Swingler, John A. W. McCall
• Keywords: Cancer Chemotherapy Treatment, GECCO 2008, Intervention Crossover, Intervention Crossover Principles, Optimization