The simulation and analysis of mathematical models of biological systems require a complete knowledge of the reaction kinetic constants. Unfortunately, these values are often difficult to measure, but they can be inferred from experimental data in a process known as Parameter Estimation (PE). In this work, we tackle the PE problem using Particle Swarm Optimization (PSO) coupled with three different reboot strategies, which aim to reinitialize particle positions to avoid local optima. In particular, we highlight the better performance of PSO coupled with the reboot strategies with respect to standard PSO. Finally, since the PE requires a huge number of simulations at each iteration of PSO, we exploit cupSODA, a GPU-powered deterministic simulator, which performs all simulations and fitness evaluations in parallel.
Spolaor, S., Tangherloni, A., Rundo, L., Cazzaniga, P., & Nobile, M. (2019). Estimation of kinetic reaction constants: exploiting reboot strategies to improve PSO’s performance. In Computational Intelligence Methods for Bioinformatics and Biostatistics. CIBB 2017 (pp.92-102). Springer Verlag [10.1007/978-3-030-14160-8_10].
Citazione: | Spolaor, S., Tangherloni, A., Rundo, L., Cazzaniga, P., & Nobile, M. (2019). Estimation of kinetic reaction constants: exploiting reboot strategies to improve PSO’s performance. In Computational Intelligence Methods for Bioinformatics and Biostatistics. CIBB 2017 (pp.92-102). Springer Verlag [10.1007/978-3-030-14160-8_10]. | |
Tipo: | paper | |
Carattere della pubblicazione: | Scientifica | |
Presenza di un coautore afferente ad Istituzioni straniere: | No | |
Titolo: | Estimation of kinetic reaction constants: exploiting reboot strategies to improve PSO’s performance | |
Autori: | Spolaor, S; Tangherloni, A; Rundo, L; Cazzaniga, P; Nobile, M | |
Autori: | ||
Data di pubblicazione: | 2019 | |
Lingua: | English | |
Nome del convegno: | 14th International Meeting on Computational Intelligence Methods for Bioinformatics and Biostatistics, CIBB 2017 | |
ISBN: | 978-3-030-14159-2 | |
Serie: | LECTURE NOTES IN COMPUTER SCIENCE | |
Digital Object Identifier (DOI): | http://dx.doi.org/10.1007/978-3-030-14160-8_10 | |
Appare nelle tipologie: | 02 - Intervento a convegno |