@inproceedings {pub4009,
	title = {Optimal Evolutionary Optimization Hyperparameters to Mimic Human User Behaviour},
	author = {Sneha Saha AND Thiago de Jesus de Araujo Rios AND Leandro L. Minku AND Xin Yao AND Zhao Xu AND Bernhard Sendhoff AND Stefan Menzel},
	year = {2019},
	month = {December},
	abstract = {Shape morphing methods are a key representation in human user-centered design as well as computational optimization of engineering applications in the automotive domain. 3D digital objects are modified using deformation algorithms to alter the shape for optimal product performance or design aesthetics. We imagine a system which can learn from historic user deformation sequences and support the user in present design tasks by predicting potential design variations based on currently observed design changes carried out by the user. Towards a practical realization, a large amount of human user deformation sequence data is required which is practically not available. In the present paper, we propose to find the optimal hyperparameters of an evolutionary optimization algorithm according to exemplary human user sequences. We implemented a simplified yet practically relevant interactive target shape matching process to collect human user data and aligned it successfully to an evolutionary optimizer by parameter grid search and dynamic time warping of sequences. In addition, we classified the user sequences to experience levels based on their variance. These user experience-tuned evolutionary optimizers allow us in future to mimic different user behavior and generate a large amount of deformation sequences in an automated fashion.},
	publisher = {IEEE},
	booktitle = {IEEE Symposium Series on Computational Intelligence}
}