Interactive evolutionary multiobjective optimization with modular physical user interface

Abstract

Incorporating the preferences of a domain expert, a decision-maker (DM), in solving multiobjective optimization problems increased in popularity in recent years. The DM can choose to use different types of preferences depending on his/her comfort, requirements, or the problem being solved. Most papers, where preference-based and interactive algorithms have been proposed, do not pay attention to the user interfaces and input devices. If they do, they use character or graphics-based preference input methods. We propose the option of using a physical or tactile input device that gives the DM a better sense of control over providing his/her preferences.However, off the shelf hardware devices are not tailored to solve multiobjective optimization problems and provide many controls that may increase the cognitive load on the DM. In this paper, we propose a fully modular physical user interface to input preference information for solving multiobjective optimization problems. The modularity allows to arrange each input module in various ways depending on the algorithm, DM's requirements, or the problem being solved. The device can be used with any computer and uses web-based visualizations. We demonstrate the potential of the physical interface by solving a real-world problem with an interactive decomposition-based multiobjective evolutionary algorithm.