Interactive evolutionary computation using multiple users’ gaze information

Abstract

We propose an interactive evolutionary computation (IEC) method that uses the gaze information of multiple users to reduce user evaluation loads. The IEC method employs user sensitivity to evaluate candidate solutions of evolutionary computation. However, IEC has a problem that user evaluation loads of candidate solutions are large. To solve this problem, some researchers have proposed various methods using a simple evaluation of candidate solutions or biological information. Therefore, we use the gaze information of users to evaluate candidate solutions in IEC. By using gaze information, the system can reduce the user evaluation load without the need for users to wear a special measuring device. We created a women’s clothing coordination system using IEC with gaze information. We conducted an evaluation experiment to verify the effectiveness of the proposed system. The experimental results show that the proposed system is effective for incorporating users’ gaze information into IEC evaluation.