|
Affiliation |
Information Technology center |
|
Title |
Associate Professor |
|
External Link |
|
AOKI Kenji
|
|
|
Degree 【 display / non-display 】
-
Doctor (Engineering) ( 2010.3 Kagoshima University )
-
修士（情報工学） ( 2000.3 九州工業大学 )
Research Areas 【 display / non-display 】
-
Informatics / Database
-
Informatics / Theory of informatics
-
Humanities & Social Sciences / Educational technology
Papers 【 display / non-display 】
-
Simplification of Rip Current Detection by Image Averaging Based on the Number of Wave Breaks Reviewed
Hamasuna O., Kimura L., Ikeda S., Ohe K., Aoki K., Takei A., Kudo A., Sakamoto M.
Proceedings of International Conference on Artificial Life and Robotics 609 - 612 2025
Publishing type：Research paper (scientific journal) Publisher：Proceedings of International Conference on Artificial Life and Robotics
According to a National Police Agency report, there were 1,392 water accidents in 2023, with 368 victims (dead or missing) in the sea, mainly due to rip currents. Detecting rip currents is crucial, and past studies have used image averaging, often relying on fixed-point cameras or lengthy videos, making it difficult for individuals to apply. This study proposes using smartphone videos, with durations adjusted by the number of wave breaks, to enable easier rip current detection. To test this, smartphone footage was recorded at Hitotsuba Surf Point in Miyazaki Prefecture for analysis.
-
Investigating Visual Illusions in Convolutional Neural Networks Using Spiral Illusion Images Reviewed
Aoki K., Togo T., Sakamoto M.
Lecture Notes in Electrical Engineering 1321 LNEE 388 - 397 2025
Authorship：Lead author, Corresponding author Publishing type：Research paper (scientific journal) Publisher：Lecture Notes in Electrical Engineering
Convolutional Neural Networks (CNNs), inspired by the local receptive fields of the visual cortex in the brain, have been widely used across various domains, including image recognition. The unraveling of the mechanisms of visual illusion generation via CNNs could enhance our understanding of the brain’s visual processing mechanisms and potentially aid in recognizing and mitigating the risks of misclassification by CNNs. In this study, we used spiral illusion images to verify whether the illusion occurs in a CNN. We constructed a CNN model and trained it to distinguish between concentric circle images and spiral images. We then introduced 14 spiral illusion images into the trained CNN model and tasked it with classifying them as either concentric circle images or spiral images. This process, from training to classification, was repeated 10 times, and the results were aggregated. The findings revealed that in all trials, 57% of the images (8 out of 14) were classified as spiral images, indicating the occurrence of a spiral illusion. Conversely, 29% of the images (4 out of 14) were consistently classified as concentric circle images, suggesting the absence of a visual illusion. These results suggest that the CNN model developed in this study is highly likely to generate spiral illusions. Furthermore, it was deduced that certain images are more prone to inducing illusions than others. Specifically, images with thick black-and-white lines alternately connected at the ends of concentric circles were the most prone to generate the spiral illusion.
-
Influence of CNN Layer Depth on Spiral Visual Illusions Reviewed
Aoki K., Sakamoto M.
Proceedings of International Conference on Artificial Life and Robotics 649 - 652 2025
Authorship：Lead author, Corresponding author Publishing type：Research paper (scientific journal) Publisher：Proceedings of International Conference on Artificial Life and Robotics
Understanding the mechanism of visual illusion generation through Convolutional Neural Networks (CNNs) that mimic the receptive fields of the visual cortex can contribute to elucidating the mechanisms of visual information processing in the brain. In our previous research, we demonstrated the potential for Fraser's spiral illusion to manifest in CNNs. In this study, we focused on the depth of the CNN layer structure and examined the impact of the number of layers on the manifestation of the visual illusion. We provided 14 types of spiral illusion images to three different CNN patterns with varying layer structures and tasked them with distinguishing between concentric circles and spirals. The results indicated that CNNs with fewer layers were more prone to the illusion, whereas CNNs with more layers were less likely to exhibit the illusion. These results suggest that the number of layers in a CNN influences the manifestation of visual illusions.
-
Ide M., Beppu M., Ikeda S., Ohe K., Aoki K., Takei A., Kudo A., Sakamoto M.
Proceedings of International Conference on Artificial Life and Robotics 628 - 631 2025
Publishing type：Research paper (scientific journal) Publisher：Proceedings of International Conference on Artificial Life and Robotics
This study developed a web application and video content to help raise awareness and interest in the myths surrounding the local shrine, Yakudo Shrine, and the annual festival, Chibikko Sumo Tournament, as well as to help participants establish memories of the event, and evaluate its usefulness. The application is designed to be used not only this year but also over the long term, and incorporates features that will allow easy maintenance and updating by non-technical personnel and the next generation of management members. The main functions are as follows: (1) accurate and convenient provision of detailed event information, (2) AR photo function utilizing original character illustrations to capture memorable photos, and (3) administrator-only functions to update and edit necessary information. web application can be used from publication to The web application delivered accurate and detailed information to a large number of people from the day of the festival to the day of the festival, helping to increase the number of festival participants by 2.5 times compared to the previous year. The video content, in particular, increased awareness of and interest in shrine-related myths.
-
Development of a plant growing experience application for physically challenged children using VR Reviewed
Beppu M., Ide M., Ohe K., Ikeda S., Aoki K., Takei A., Kudo A., Sakamoto M.
Proceedings of International Conference on Artificial Life and Robotics 618 - 622 2025
Publishing type：Research paper (scientific journal) Publisher：Proceedings of International Conference on Artificial Life and Robotics
In 2016, the “first year of VR,” many VR platforms emerged, making VR technology more accessible. Currently, technology is expected to be applied and utilized in various fields. Application to the education sector is being promoted as part of the educational use of ICT. However, it is difficult to get the benefits of implementing VR due to lack of technology and equipment for teachers. Therefore, it is necessary to limit the scope of coverage. This research will focus on limb-challenged children and develop a VR application that allows them to experience plant growing. We believe that this will solve the problems that have been a concern for children with physical disabilities, such as the inability to perform exercises using soil and the lack of opportunities for trial-and-error. In this study, we also asked men and women in their teens to 40s to experience the apps we developed and obtained their evaluations through questionnaires. Within the survey, we received certain evaluations in areas such as trial and error. As for future issues, the application will be improved based on the feedback received from the survey. In addition, we believe it is necessary to evaluate the long-term effects of the application by having children with physical disabilities use it.
MISC 【 display / non-display 】
-
オンデマンド授業のための高画質コンテンツの作成と評価－高等教育における試み－
青木 謙二
メディア教育研究 Vol.1, No.2, p.91-101 2005
Language：Japanese Publishing type：Article, review, commentary, editorial, etc. (bulletin of university, research institution)
Presentations 【 display / non-display 】
-
An attempt to visualize device movement information using session logs of wireless LAN
Yusei Hayashida, Kenji Aoki
2024.9.19
Event date： 2024.9.19 - 2024.9.20
Presentation type：Oral presentation (general)
-
Analysis of self-diagnosis results using the information security measures self-diagnosis system
Kenji Aoki, Makoto Sonoda, Wataru Kurogi, Masashi Miyamoto, Isamu Hatsukade
2023.12.15
Event date： 2023.12.13 - 2023.12.15
Language：Japanese Presentation type：Oral presentation (general)
-
CNNによる渦巻き錯視の認識
東郷拓弥、坂本眞人、青木謙二
2022年度 電気・情報関係学会九州支部連合大会 2022.9.17
Event date： 2022.9.16 - 2022.9.17
Language：Japanese Presentation type：Oral presentation (general)
-
コロナ禍におけるオンライン授業の実践
青木 謙二
第2９回 国公立大学情報システム研究会総会
Event date： 2021.3.5
Language：Japanese Presentation type：Oral presentation (general)
-
Recognition of the spiral illusion using a convolutional neural network International conference
Kenji Aoki, Takumi Nakayama, Makoto Sakamoto
The 26th International Symposium on Artificial Life and Robotics
Event date： 2021.1.21 - 2021.1.23
Language：English Presentation type：Oral presentation (general)