The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Nous étudions un calcul évolutif interactif (IEC) utilisant les informations du regard de plusieurs utilisateurs lorsque les utilisateurs participent partiellement à chaque évaluation de conception. De nombreux systèmes CEI antérieurs rencontraient un problème en raison des charges d'évaluation des utilisateurs trop importantes. Par conséquent, nous avons proposé d'utiliser les informations du regard de l'utilisateur pour évaluer les conceptions générées par les systèmes CEI afin de résoudre ce problème. Dans ce système proposé, les utilisateurs visualisent simplement les conceptions présentées, sans les évaluer, puis le système crée automatiquement les conceptions préférées des utilisateurs. Grâce aux informations du regard de l'utilisateur, le système proposé génère une coordination qui peut satisfaire de nombreux utilisateurs. Dans notre étude précédente, nous avons vérifié l’efficacité du système proposé du point de vue du fonctionnement réel du système. Cependant, nous n’avons pas pris en compte la fluctuation des utilisateurs lors de l’évaluation d’une solution candidate. Dans le fonctionnement réel du système proposé, les utilisateurs peuvent changer au cours du processus en raison de l'échange d'utilisateurs. Par conséquent, dans cette étude, nous vérifions l'efficacité du système proposé en faisant varier les utilisateurs participant à chaque évaluation pour chaque génération. Dans l’expérience, nous utilisons deux types de situations supposées dans des environnements réels. La première situation modifie le nombre d'utilisateurs évaluant les conceptions pour chaque génération. La deuxième situation fait appel à divers utilisateurs de la population prédéfinie pour évaluer les conceptions pour chaque génération. À partir des résultats expérimentaux dans la première situation, nous confirmons que, malgré le changement du nombre d'utilisateurs lors de l'évaluation de la solution candidate, le système proposé peut générer une coordination pour satisfaire de nombreux utilisateurs. De plus, à partir des résultats dans la deuxième situation, nous vérifions que le système proposé peut également générer une coordination que les deux utilisateurs qui participent à l'évaluation de la coordination peuvent mieux satisfaire.
Hiroshi TAKENOUCHI
Fukuoka Institute of Technology
Masataka TOKUMARU
Kansai University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Hiroshi TAKENOUCHI, Masataka TOKUMARU, "Character Design Generation System Using Multiple Users' Gaze Information" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 9, pp. 1459-1466, September 2021, doi: 10.1587/transinf.2020EDP7113.
Abstract: We investigate an interactive evolutionary computation (IEC) using multiple users' gaze information when users partially participate in each design evaluation. Many previous IEC systems have a problem that user evaluation loads are too large. Hence, we proposed to employ user gaze information for evaluating designs generated by IEC systems in order to solve this problem. In this proposed system, users just view the presented designs, not assess, then the system automatically creates users' favorite designs. With the user's gaze information, the proposed system generates coordination that can satisfy many users. In our previous study, we verified the effectiveness of the proposed system from a real system operation viewpoint. However, we did not consider the fluctuation of the users during a solution candidate evaluation. In the actual operation of the proposed system, users may change during the process due to the 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 in real environments. The first situation changes the number of users evaluating the designs for each generation. The second situation employs various users from the predefined population to evaluate the designs for each generation. From the experimental results in the first situation, we confirm that, despite the change in the number of users during the solution candidate evaluation, the proposed system can generate coordination to satisfy many users. Also, from the results in the second situation, we verify that the proposed system can also generate coordination which both users who participate in the coordination evaluation can more satisfy.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDP7113/_p
Copier
@ARTICLE{e104-d_9_1459,
author={Hiroshi TAKENOUCHI, Masataka TOKUMARU, },
journal={IEICE TRANSACTIONS on Information},
title={Character Design Generation System Using Multiple Users' Gaze Information},
year={2021},
volume={E104-D},
number={9},
pages={1459-1466},
abstract={We investigate an interactive evolutionary computation (IEC) using multiple users' gaze information when users partially participate in each design evaluation. Many previous IEC systems have a problem that user evaluation loads are too large. Hence, we proposed to employ user gaze information for evaluating designs generated by IEC systems in order to solve this problem. In this proposed system, users just view the presented designs, not assess, then the system automatically creates users' favorite designs. With the user's gaze information, the proposed system generates coordination that can satisfy many users. In our previous study, we verified the effectiveness of the proposed system from a real system operation viewpoint. However, we did not consider the fluctuation of the users during a solution candidate evaluation. In the actual operation of the proposed system, users may change during the process due to the 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 in real environments. The first situation changes the number of users evaluating the designs for each generation. The second situation employs various users from the predefined population to evaluate the designs for each generation. From the experimental results in the first situation, we confirm that, despite the change in the number of users during the solution candidate evaluation, the proposed system can generate coordination to satisfy many users. Also, from the results in the second situation, we verify that the proposed system can also generate coordination which both users who participate in the coordination evaluation can more satisfy.},
keywords={},
doi={10.1587/transinf.2020EDP7113},
ISSN={1745-1361},
month={September},}
Copier
TY - JOUR
TI - Character Design Generation System Using Multiple Users' Gaze Information
T2 - IEICE TRANSACTIONS on Information
SP - 1459
EP - 1466
AU - Hiroshi TAKENOUCHI
AU - Masataka TOKUMARU
PY - 2021
DO - 10.1587/transinf.2020EDP7113
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2021
AB - We investigate an interactive evolutionary computation (IEC) using multiple users' gaze information when users partially participate in each design evaluation. Many previous IEC systems have a problem that user evaluation loads are too large. Hence, we proposed to employ user gaze information for evaluating designs generated by IEC systems in order to solve this problem. In this proposed system, users just view the presented designs, not assess, then the system automatically creates users' favorite designs. With the user's gaze information, the proposed system generates coordination that can satisfy many users. In our previous study, we verified the effectiveness of the proposed system from a real system operation viewpoint. However, we did not consider the fluctuation of the users during a solution candidate evaluation. In the actual operation of the proposed system, users may change during the process due to the 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 in real environments. The first situation changes the number of users evaluating the designs for each generation. The second situation employs various users from the predefined population to evaluate the designs for each generation. From the experimental results in the first situation, we confirm that, despite the change in the number of users during the solution candidate evaluation, the proposed system can generate coordination to satisfy many users. Also, from the results in the second situation, we verify that the proposed system can also generate coordination which both users who participate in the coordination evaluation can more satisfy.
ER -