Interactive One-Max Problem Allows to Compare the Performance of Interactive and Human-Based Genetic Algorithms

@incollection{citeulike:1531647, abstract = {Human-based genetic algorithms (HBGA) use both human evaluation and innovation to optimize a population of solutions (Kosorukoff, 2001). The novel contribution of HBGAs is an introduction of human-based innovation operators. However, there was no attempt to measure the effect of human-based innovation operators on the overall performance of GAs quantitatively, in particular, by comparing the performance of HBGAs and interactive genetic algorithms (IGA) that do not use human innovation. This paper shows that the mentioned effect is measurable and further focuses on quantitative comparison of the efficiency of these two classes of algorithms. In order to achieve this purpose, this paper proposes an interactive analog of the one-max problem, suggests human-based innovation operators appropriate for this problem, and compares convergence results of HBGA and IGA for the same problem.}, author = {Cheng, Chihyung D. and Kosorukoff, Alexander }, citeulike-article-id = {1531647}, journal = {Genetic and Evolutionary Computation – GECCO 2004}, keywords = {evolutionary-computation, human-based-computation}, pages = {983--993}, posted-at = {2007-08-03 01:25:06}, priority = {0}, title = {Interactive One-Max Problem Allows to Compare the Performance of Interactive and Human-Based Genetic Algorithms}, url = {http://www.springerlink.com/content/bphjyhw10m0h19t9 }, year = {2004} }

TY - CHAP ID - citeulike:1531647 L3 - citeulike-article-id:1531647 TI - Interactive One-Max Problem Allows to Compare the Performance of Interactive and Human-Based Genetic Algorithms JF - Genetic and Evolutionary Computation – GECCO 2004 SP - 983 EP - 993 N2 - Human-based genetic algorithms (HBGA) use both human evaluation and innovation to optimize a population of solutions (Kosorukoff, 2001). The novel contribution of HBGAs is an introduction of human-based innovation operators. However, there was no attempt to measure the effect of human-based innovation operators on the overall performance of GAs quantitatively, in particular, by comparing the performance of HBGAs and interactive genetic algorithms (IGA) that do not use human innovation. This paper shows that the mentioned effect is measurable and further focuses on quantitative comparison of the efficiency of these two classes of algorithms. In order to achieve this purpose, this paper proposes an interactive analog of the one-max problem, suggests human-based innovation operators appropriate for this problem, and compares convergence results of HBGA and IGA for the same problem. KW - evolutionary-computation KW - human-based-computation AU - Cheng, Chihyung AU - Kosorukoff, Alexander PY - 2004/// UR - http://www.springerlink.com/content/bphjyhw10m0h19t9 ER -