Hiroshi Takenouchi

Design support system with votes from multiple people using digital signage

We propose a system to create designs that reflect multiple user preferences obtained by voting using digital signage. When creating such designs, it is important to collect a significant number of user opinions and adopt them in the designs. However, as the number of users increases, the collection of opinions becomes more difficult. We propose an interactive evolutionary computation system using digital signage. This system presents several designs. Each user evaluates the designs by voting. In other words, this system obtains the preferences of multiple users by voting and uses the preferences to evaluate designs. Therefore, the proposed system can create designs that please multiple users. In our previous research, we proposed a paired comparison voting (PCV) method that obtains preferences from multiple users by voting and confirmed the effectiveness of the method by simulation. Here, we construct a system using the PCV method and digital signage to demonstrate its effectiveness with real users. The proposed system uses the PCV method to create designs. The experimental results show that the designs generated by the proposed system converged visually and genetically. As a result, we verified that the proposed system creates designs reflecting the preferences of multiple people.

Signboard design system through social voting technique

We propose a signboard design system with votes by multiple people. When determining a signboard design with many people, it is important that local residents agree on a single signboard design. Therefore, we created a signboard design system that determines the design by popularity using an evolutionary computation algorithm to finalize the design. We have proposed a paired comparison voting method (PCV) that allows several thousand unspecified users to participate in the evaluation of candidate solutions. Specifically, the PCV method considers multiple opinion from the Internet votes to evaluate candidate solutions, accepting votes made during a defined time parameter. In our previous study, we confirmed the effectiveness of the PCV method by numerical simulations using evaluation agents that imitate human sensitivity. In this paper, we demonstrate its effectiveness for real users using a signboard design system. The system helps users to create a signboard design by considering the suitability of the grain pattern, background and character colors, and the signboards environment. The experimental results showed that the PCV method can reduce the load on users and produce a suitable and satisfactory design, verifying the effectiveness of the PCV method for real users.

An emotion-generation model for a robot that reacts after considering the dialogist

This paper proposes an emotion-generation model for a robot that distinguishes different aspects of a humans personality. The robot reacts differently, depending on the human communication it receives. In this cutting-edge research area, several studies have demonstrated robots that generate reactions to humans by judging their interaction. However, these reactions do not change when the communicating human displays a variety of personality traits. This is because the robot only responds to the input without taking the humans personality into account. To solve this issue, we propose an emotion-generation model for robots that produces different reactions depending on the human communication it receives. In this model, the robot has a degree of intimacy that judges the humans personality. The degree of intimacy increases when the human satisfies the robots desire and decreases when he/she does not. The simulation results confirmed that the robot shows a friendly reaction to a human with a high degree of intimacy and an unfriendly reaction to one with a low degree of intimacy.

Interactive Evolutionary Computation Using Multiple Users’ Gaze Information

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.

Development of an Interactive Evolutionary Computation Catalog Interface with User Gaze Information

We propose a catalog interface for the Interactive Evolutionary Computation (IEC) system. When a user views a product catalog, the system obtains the user’s gaze information and implements evolutionary computation. We verify the effectiveness of the proposed system using evaluation experiments with real users. The experimental results show that the proposed system can generate solutions that offer results equivalent to comparable systems and reduce the evaluation load of the users.

Developing Female Clothing Coordination Generation System Using Eye Tracking Information

In this study, we examine the effectiveness of a female-clothing coordination-generation system using eye-tracking information for multiple users. In our previous study, only two subjects used an interactive evolutionary computation (IEC) system by utilizing the users eye-tracking information, which however poses two issues for actual application. First, the number of subjects simultaneously using the system was low. Moreover, they were given specific instructions on how to use the system in advance. To solve these issues, we review our previous method, and develop a female-clothing coordination-generation system using digital signage and verify its effectiveness. The experimental results demonstrate that the system can simultaneously create satisfactory clothing coordination for multiple users.

Emotional action generation model supporting real-time operation

In this paper, we propose an emotional action generation model for robots that supports real-time operation. Emotional actions make users feel better. However, some conventional robot emotion generation models do not support real-time operation and do not generate natural actions that make users feel better. The proposed model enables robots to perform natural actions that positively influence communication between the user and the robot. Through two simulations, we evaluate the generation of emotional actions and real-time operation. The experimental results confirm confirmed the effectiveness of the proposed model.

Wrist Watch Design System with Interactive Evolutionary Computation

We propose a wrist watch design system with Interactive Evolutionary Computation (IEC) using Winner-based Paired Comparison (WPC) method. Some companies have developed various product design customization systems. However, in most of these systems, users must choose each design component from multiple design components. Consequently, it is difficult for users to create a favored design because there are many design elements. In this study, we propose a system that can automatically generate product designs based on users’ subjective evaluations. We employ an IEC method to develop the system and the WPC method to reduce user evaluation loads. The WPC method passes the winning design in the current competition to the next competition. We demonstrate the effectiveness of our system by an evaluation experiment for real users. The experimental results show that the proposed system can create designs that satisfy users in a short time.

Performance Evaluation of a Kansei Retrieval Agent Model with Neural Networks

We describe the effectiveness of a Kansei Retrieval Agent (KRA) model with Neural Network (NN) for retrieving user preference data. Our system evaluates KRAs using the users evaluation and optimizes the KRA parameters using an evolutionary computation approach. While our previous study involved Kansei retrieval systems for T-shirts or music, the basic optimization performance of a KRA with NN was not examined. Therefore, in the present study, we investigate the effectiveness of the KRA model with an NN using numerical simulations. The simulation uses a pseudo user that imitates user preferences. We examine the quantization of evaluation values by the user and KRAs and compares the performances obtained using the particle swarm optimization and genetic algorithm methods. The simulation results show that the KRA model can learn user preferences.

Sympathy expression model for the bystander robot in group communication

In this paper, we propose a sympathy expression model for a bystander robot that honors the concept of moral emotion. Therefore, we pay attention to the robot that is in a bystander position, which is unrelated to the communication between participants. We propose a sympathy expression model that lets a bystander robot learn the emotional display of others and enables cooperative expressiveness. This model allows the appropriate expressiveness affecting communication of a robot in the position of a bystander. To test it, we assume the interaction of three robots with the emotion generation model using the neural network. Further, we inspect the movement of this model by using a psychology model. As a result, we confirmed the appropriate actions of this model.