Interactive Evolutionary Computation System with User Gaze Information

Abstract

We present an Interactive Evolutionary Computation (IEC) system that applies user gaze information. Historically, IEC systems have encountered the problems caused by heavy user evaluation loads. To solve these problems, researchers have employed biologically derived user information, such as heartbeats or brainwaves, to reduce the evaluation load. However, the requirement for users to wear special devices to measure this information has limited the popularity of these systems. Therefore, we applied the user gaze information approach to solve these problems. Gaze information includes the user's potential preferences, which are derived from various processes. When user gaze information is applied in the evaluation of candidate solutions, IEC systems can obtain user evaluation information while users are viewing multiple candidate solutions. In this paper, we verify the effectiveness of the eye tracking IEC system using evaluation experiments with real users. In the experiment, we use a normal IEC system as a comparison method where users manually evaluate candidate solutions using a 10-stage evaluation process. The experimental results show that the eye tracking IEC method can generate solutions with results equivalent to those of the compared system.

Character Design Generation System Using Multiple Users' Gaze Information

“…Some researchers have proposed an IEC system with users' gaze information, and verified the effectiveness of their methods [7]- [9]. Also, we have proposed an IEC system with users' gaze information and verified the effectiveness of the system in terms of reducing users evaluation loads [10]. Our previous method was more effective than an IEC system with a manual evaluation method that a user inputs evaluation value for each design.…”

“…In this case, the proposed system may obtain inaccurate evaluation information (noise) on user preferences and generate designs that do not satisfy users. However, our previous study has demonstrated that the IEC system with gaze information can generate designs based on user preferences, even if the user evaluations include inaccurate information from prior experiments [10]. Therefore, in this study, we verify whether the proposed system can generate objects that can satisfy users when using multiple user's gaze information for evaluating candidate solutions.…”

“…Thus, studies have been conducted to reduce the loads [1]. Some researchers have investigated employing user biological information such as heart rate, electroencephalogram (EEG) signal, and gaze information [5]- [10]. However, in order to acquire heart rate information and EEG signal, the users must wear the measuring device, i.e., the user loads.…”

“…However, in order to acquire heart rate information and EEG signal, the users must wear the measuring device, i.e., the user loads. Besides, we have proposed an IEC system with users' gaze information for reducing users evaluation loads [10]. User gaze information consists of the potential preferences of users.…”

IGAOD: An online design framework for interactive genetic algorithms

“…The difference between IGA and traditional genetic algorithms is that the fitness of the evolving individual is given by humans. IGA has been widely used in image retrieval [4,5], product design [6,7], music composition [8,9], software design [10,11] and many other fields.…”