Interactive Evolutionary Computation System Using Multiple Users’ Gaze Information Considering User’s Partial Evaluation Participation

Abstract

We investigate an interactive evolutionary computation using multiple users’ gaze information when users partially participate in each design evaluation. In the previous study, we confirmed the effectiveness of the proposed system from a viewpoint of real system operation. However, the fluctuation of the users during solution candidate evaluation was not considered. In the actual operation of the proposed system, users may change during the process due to user interchange. Therefore, in this study, we verify the effectiveness of the proposed system when varying the users participating in each evaluation for each generation. In the experiment, we employ two types of situations as assumed real environments. The first situation changes the number of users evaluating the designs at each generation. The second situation employs various users from the predefined population to evaluate the designs at each generation. The experimental results show that, despite the change in the number of users during the solution candidate evaluation, the proposed system can generate coordination to satisfy many users.