Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
The LifeCycle Model: Combining Particle Swarm Optimisation, Genetic Algorithms and HillClimbers
PPSN VII Proceedings of the 7th International Conference on Parallel Problem Solving from Nature
| Hi-index | 0.00 |
Electron paramagnetic resonance (EPR) spectroscopy is a nondestructive technique suitable for inspection of biological systems. Characterization of such a system is much more reliable when relevant spectral characteristics are extracted from a biophysical model of the system. To tune the model parameters, stochastic optimization techniques are used more and more frequently. Since many single-point algorithms require time-consuming preparation of promising starting points to produce reasonable results, we have addressed the problem with population-based, evolutionary computation approach. We have applied a genetic algorithm to the EPR spectral parameter optimization and evaluated it on synthetic spectra. Preliminary numerical experiments show the new approach is beneficial in that it produces satisfactory results and reduces the time a spectroscopist spends for navigating the optimization process.