Novelty search employed into the development of cancer treatment simulations

Tsompanas, Michail-Antisthenis; Bull, Larry; Adamatzky, Andrew; Balaz, Igor

Abstract

Conventional optimization methodologies may be hindered when the automated search is stuck into local optima because of a deceptive objective function landscape. Consequently, open ended search methodologies, such as novelty search, have been proposed to tackle this issue. Overlooking the objective, while putting pressure into discovering novel solutions may lead to better solutions in practical problems. Novelty search was employed here to optimize the simulated design of a targeted drug delivery system for tumor treatment under the PhysiCell simulator. A hybrid objective equation was used containing both the actual objective of an effective tumor treatment and the novelty measure of the possible solutions. Different weights of the two components of the hybrid equation were investigated to unveil the significance of each one.

Citation

Tsompanas, M., Bull, L., Adamatzky, A., & Balaz, I. (2020). Novelty search employed into the development of cancer treatment simulations. Informatics in Medicine Unlocked, 19, 100347. https://doi.org/10.1016/j.imu.2020.100347

• Journal Article Type: Article
• Acceptance Date: May 4, 2020
• Online Publication Date: May 20, 2020
• Publication Date: 2020
• Deposit Date: May 22, 2021
• Publicly Available Date: May 26, 2021
• Journal: Informatics in Medicine Unlocked
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 19
• Pages: 100347
• DOI: https://doi.org/10.1016/j.imu.2020.100347
• Public URL: https://uwe-repository.worktribe.com/output/7123600
• Publisher URL: https://doi.org/10.1016/j.imu.2020.100347
• Additional Information: This article is maintained by: Elsevier; Article Title: Novelty search employed into the development of cancer treatment simulations; Journal Title: Informatics in Medicine Unlocked; CrossRef DOI link to publisher maintained version: https://doi.org/10.1016/j.imu.2020.100347; Content Type: article; Copyright: © 2020 The Authors. Published by Elsevier Ltd.