An intuitive and traceable human-based evolutionary computation system for solving problems in human organizations
Journal
GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion
Pages
1457-1464
Date Issued
2019
Author(s)
Abstract
Human-based evolutionary computation (EC), for which people act as executors of all evolutionary operators, can be used to solve problems in human organizations. We previously developed a human-based EC system that represents solutions as tags (words) and allows people to evaluate solutions by clicking corresponding tags. Although the system was easy and intuitive to use, it could not handle problems for which solutions are represented as long sentences. In addition, the system could not trace the evolution of solutions. Traceability is a must for the system to be widely and reliably used. In this study, we thus develop a human-based EC system that allows solutions to be represented as both sentences and tags. A function for tracing the evolution of solutions is embedded into the system. The function asks a solution creator to specify which existing solutions influenced the solution creation. We conduct an experiment in which 18 human subjects use the system and then fill out a survey. The results show that the system creates better solutions than those created by each human subject independently. Furthermore, the evolution tree generated from the information given by solution creators is used to confirm that the system allows the evolution of solutions to be traced.
SDGs
Type
conference paper