Papers - OHE Kaoru
-
Broadening Access-to Creative Experience with MR 3D Painting Reviewed
Ishimaru T., Oshikawa Y., Nokura S., Ikeda S., Aoki K., Ohe K., Takei A., Kawamura R., Sakamoto M.
Proceedings of International Conference on Artificial Life and Robotics 421 - 425 2026
Publishing type：Research paper (scientific journal) Publisher：Proceedings of International Conference on Artificial Life and Robotics
Access to arts experiences varies by income and locality, creating an experience divide. We present a low-barrier mixed-reality (MR) 3D-painting system on Meta Quest 3 that renders strokes in the user's surrounding space in passthrough MR. We conducted two complementary studies: an in-the-wild festival study with local children (MR 3D free creation) and a controlled study with university students enabling within-participant comparisons across free 2D drawing, free 3D drawing (with depth), and prompted 3D drawing. After each condition, participants rated immersion, accomplishment, perceived creativity, self-efficacy, intention to continue, and usability (plus two free-creation items) on 5-point Likert scales, and collaboration was assessed in paired tasks. We report condition-wise medians and within-participant median differences. Results suggest that MR can deliver meaningful creative experiences with minimal setup in everyday spaces and inform how task framing supports depth-oriented 3D creation.
-
Ohe K., Yamaguchi Y., Oshima T.
Proceedings of International Conference on Artificial Life and Robotics 462 - 465 2026
Publishing type：Research paper (scientific journal) Publisher：Proceedings of International Conference on Artificial Life and Robotics
Sericin is an underutilized biomass of hydrophilic protein removal during the refining process of silk yarn. Processing abundant functional groups such as hydroxyl, carboxyl, amide, and amino groups, sericin exhibits affinity for metal ions, making it a promising biosorbent. This study investigated the adsorption behavior of metal ions using sericin and glutaraldehyde-crosslinked sericin(Glu-sericin). Glu-sericin selectively adsorbed precious metals over Cu(II) in 0.01 M HCl. In contrast, sericin showed a red color change after Au(III) adsorption from 0.01 M and 0.1 M HCl, indicating the reduction of Au(III) to Au(0). These results show that sericin non-crosslinked treatment, both adsorption and reduction functions, making it a unique biomass material for gold recovery.
-
Proposal of a Muscle Training Method using EMG Visualization via Machine Learning Reviewed
Oshikawa Y., Ishimaru T., Nokura S., Ikeda S., Aoki K., Ohe K., Takei A., Kawamura R., Sakamoto M.
Proceedings of International Conference on Artificial Life and Robotics 426 - 429 2026
Publishing type：Research paper (scientific journal) Publisher：Proceedings of International Conference on Artificial Life and Robotics
Strength training is essential for maintaining health and building an attractive physique, yet many people struggle to stick with it. One reason for this is that they fail to feel the effects of strength training. To maximize the effects of strength training, mastering proper form is essential. Therefore, I embarked on this research to reduce the number of people who quit strength training by visualizing muscle load in real time during workouts.We are developing a system that uses machine learning to visualize muscle load from user form, enabling muscle load visualization without requiring electromyography. At present, it is possible to estimate muscle load, but the accuracy of this estimation is low. Therefore, we are currently experimenting to improve the accuracy of muscle load estimation.
-
Unsupervised Defect Detection for Automatic Shiitake Sorting Reviewed
Nokura S., Kimura L., Ishimaru T., Oshikawa Y., Ikeda S., Aoki K., Ohe K., Takei A., Kawamura R., Sakamoto M., Sugimoto K.
Proceedings of International Conference on Artificial Life and Robotics 430 - 433 2026
Publishing type：Research paper (scientific journal) Publisher：Proceedings of International Conference on Artificial Life and Robotics
Automated shiitake sorting faces severe data imbalance (1,731 good vs. 241 defective images) and annotation difficulties. We compared data augmentation and unsupervised detection. First, augmenting scarce defective data with GANs failed; models either lost subtle defect features (e.g., discoloration) during pre-processing or overfit to augmentation patterns, proving label-less augmentation difficult. We then shifted to unsupervised anomaly detection (VAE+OC-SVM) trained only on good data. This model achieved perfect Recall (100%) for the defective class, identifying all bad items without a single miss. This Recall 100% capability demonstrates its high practical utility as a primary screening tool for quality control, particularly where preventing defective product leakage is prioritized (albeit with low precision). This approach highlights a path for automated sorting in data-scarce agricultural settings and suggests high transferability to other products (e.g., tomato, potato) with similar data constraints.
-
Adsorption Equilibrium of Selenium Oxyanions Using FeY Mixed Oxides Reviewed
Ohe Kaoru, Wakamatsu Amu, Oshima Tatsuya
人工生命とロボットに関する国際会議予稿集 30 645 - 648 2025.2
Authorship：Lead author Language：English Publishing type：Research paper (scientific journal) Publisher：株式会社ALife Robotics
Selenium oxyanions (Se(IV) and Se(VI)) in wastewater are of concern as serious pollutants due to their easy bioaccumulation and toxicity to living organisms. In this study, mixed oxides with various Y/Fe molar composition ratios (x=0.5, 1, 2) were investigated in the adsorption properties of selenium oxyanions, and were studied their adsorption mechanism. The experimental data best fits the Langmuir adsorption model, which is characteristic of monolayer adsorption (r2 >0.991). The maximum adsorption capacity (qmax) of Se(IV) and Se(VI) increased in the order of FeY2 > FeY1 > FeY0.5 and of Fe2 > FeY1, respectively. It was suggested that FeY2 adsorbed Se(IV) by formation of inner-sphere complexes and outer-sphere complexes, and adsorbed Se(VI) by outer-sphere complexes.
-
Simplification of Rip Current Detection by Image Averaging Based on the Number of Wave Breaks Reviewed
Hamasuna Ota, Kimura Leona, Ikeda Satoshi, Ohe Kaoru, Aoki Kenji, Takei Amane, Kudo Akihiro, Sakamoto Makoto
人工生命とロボットに関する国際会議予稿集 30 609 - 612 2025.2
Language：English Publishing type：Research paper (scientific journal) Publisher：株式会社ALife 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.
-
Ide Masatomo, Beppu Masatoshi, Ikeda Satoshi, Ohe Kaoru, Aoki Kenji, Takei Amane, Kudo Akihiro, Sakamoto Makoto
人工生命とロボットに関する国際会議予稿集 30 628 - 631 2025.2
Language：English Publishing type：Research paper (scientific journal) Publisher：株式会社ALife 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 Masatoshi, Ide Masatomo, Ohe Kaoru, Ikeda Satoshi, Aoki Kenji, Takei Amane, Kudo Akihiro, Sakamoto Makoto
人工生命とロボットに関する国際会議予稿集 30 618 - 622 2025.2
Language：English Publishing type：Research paper (scientific journal) Publisher：株式会社ALife 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.
-
Automated Classification of High-Grade Dried Shiitake Mushrooms Using Machine Learning Reviewed
Kimura Leona, Hamasuna Ota, Ohe Kaoru, Ikeda Satoshi, Aoki Kenji, Takei Amane, Kudo Akihiro, Sugimoto Kazuhide, Sakamoto Makoto
人工生命とロボットに関する国際会議予稿集 30 613 - 617 2025.2
Language：English Publishing type：Research paper (scientific journal) Publisher：株式会社ALife Robotics
This study aims to automate shiitake mushroom sorting using an anomaly detection system with Autoencoders (AE) trained on acceptable product data. Initial experiments using CNN approaches highlighted challenges in achieving high accuracy for acceptable product classification, necessitating improvement. The AE-based approach showed progress in detecting defective products via data cleansing, augmentation, and training optimization. However, misclassification of acceptable products with features like darker areas or complex textures remains an issue. This presentation outlines current findings and strategies, including data expansion and model improvements, to address these challenges.
-
Depiction of 3DCG Hula Dancers for Hula Costume Design CAD Development Reviewed
Kimura L., Beppu M., Ikeda S., Ohe K., Sakamoto M.
Lecture Notes in Electrical Engineering 1321 LNEE 233 - 242 2025.2
Language：English Publishing type：Research paper (international conference proceedings) Publisher：Lecture Notes in Electrical Engineering
Hula costumes are often handmade and expensive, so this study aims to develop a computer-aided design (CAD) system using 3DCG to visualize the final costume. The tool includes four functions: 1) generating a 3DCG body model based on 11 body measurements, 2) intuitively changing paw skirt (hereinafter referred to as skirt) colors, 3) changing skirt patterns with a button click, and 4) recommending and simulating skirt lengths based on body measurements. This helps users find their preferred skirt. Additionally, it allows selecting the color and pattern of practice T-shirts and the background.
-
Ohe K., Furukawa M., Oshima T.
Lecture Notes in Electrical Engineering 1321 LNEE 34 - 43 2025.2
Authorship：Lead author Language：English Publishing type：Research paper (international conference proceedings) Publisher：Lecture Notes in Electrical Engineering
Arsenic and selenium are toxic semimetals, and removal of these semimetals from environmental water is a global problem to be solved. This study modified chitosan nanofiber using xylose (XY), which has multiple hydroxyl groups with high affinity to semimetals as ligands to enhance semimetals adsorption. Adsorption properties of semimetals by cross-linked chitosan nanofiber derivative (CNF-XY) were compared with cross-linked chitosan nanofiber (CNF) and commercially synthesized and commercially available N-methylglucamine-type chelating resins (CRB05, GRY-HW). Se(IV) and Se(VI) adsorption by CNF-XY and CNF was 2.8 to 8.8 times faster than that by commercial resins, and the maximum adsorption capacity was 2.3 to 10 times larger than that by commercial resins. The adsorption kinetics of arsenic and selenium were analyzed using pseudo-first-order, pseudo-second-order, and Weber-Morris intraparticle diffusion models. The adsorption of As(III) and As(V) by CNF-XY was faster than those by commercial resins. The adsorption of As(III) and As(V) by CNF-XY fit the pseudo-second-order kinetic model but did not pass the origin, suggesting that intraparticle diffusion is responsible for As(III), As(V) adsorption was not the only rate-limiting step controlling As(III), As(V) adsorption, indicating some control by boundary membrane diffusion, suggesting that multiple processes were affected by adsorption. Se(IV) and Se(VI) adsorption onto CNF-XY and CNF are predominant by the pseudo-first-order adsorption mechanism.
-
A Study on Improvement of Operation Accuracy by Viewpoint Switching in VR Reviewed
Beppu M., Kimura L., Ohe K., Ikeda S., Sakamoto M.
Lecture Notes in Electrical Engineering 1321 LNEE 243 - 253 2025.2
Language：English Publishing type：Research paper (scientific journal) Publisher：Lecture Notes in Electrical Engineering
In recent years, VR technology is expected to be utilized in various situations such as disaster relief. Drones operated from a VR perspective are expected to play an active role in disaster relief and disaster damage assessment. However, among them, there are only a few examples of studies that focused on the user’s viewpoint during the VR experience and studied the effects of the change in viewpoint. Therefore, in this study we focus on the user’s viewpoint during the VR experience. Three VR games with the same content but different viewpoints (first-person, third person, and viewpoint switching) were created, and the effects of the different viewpoints on the VR experience were examined by comparing their completion times and responses to a questionnaire after the VR experience.
-
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 The 2025 International Conference on Artificial Life and Robotics (ICAROB2025), J:COM HorutoHall, Oita, Japan. 609 - 612 2025.2
Language：English Publishing type：Research paper (international conference proceedings) 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.
-
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.
Proceeding of The 2025 International Conference on Artificial Life and Robotics (ICAROB2025), J:COM HorutoHall, Oita, Japan 618 - 622 2025.2
Language：English 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.
-
Ide M., Beppu M., Ikeda S., Ohe K., Aoki K., Takei A., Kudo A., Sakamoto M.
Proceeding of The 2025 International Conference on Artificial Life and Robotics (ICAROB2025), J:COM HorutoHall, Oita, Japan 628 - 631 2025.2
Language：English 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.
-
Automated Classification of High-Grade Dried Shiitake Mushrooms Using Machine Learning Reviewed
Kimura L., Hamasuna O., Ohe K., Ikeda S., Aoki K., Takei A., Kudo A., Sugimoto K., Sakamoto M.
Proceeding of The 2025 International Conference on Artificial Life and Robotics (ICAROB2025), J:COM HorutoHall, Oita, Japan 613 - 617 2025.2
Language：English Publishing type：Research paper (international conference proceedings) Publisher：Proceedings of International Conference on Artificial Life and Robotics
This study aims to automate shiitake mushroom sorting using an anomaly detection system with Autoencoders (AE) trained on acceptable product data. Initial experiments using CNN approaches highlighted challenges in achieving high accuracy for acceptable product classification, necessitating improvement. The AE-based approach showed progress in detecting defective products via data cleansing, augmentation, and training optimization. However, misclassification of acceptable products with features like darker areas or complex textures remains an issue. This presentation outlines current findings and strategies, including data expansion and model improvements, to address these challenges.
-
Adsorption Equilibrium of Selenium Oxyanions Using FeY Mixed Oxides Reviewed
Ohe K., Wakamatsu A., Oshima T.
Proceeding of The 2025 International Conference on Artificial Life and Robotics (ICAROB2025), J:COM HorutoHall, Oita, Japan 645 - 648 2025.2
Authorship：Lead author Language：English Publishing type：Research paper (international conference proceedings) Publisher：Proceedings of International Conference on Artificial Life and Robotics
Selenium oxyanions (Se(IV) and Se(VI)) in wastewater are of concern as serious pollutants due to their easy bioaccumulation and toxicity to living organisms. In this study, mixed oxides with various Y/Fe molar composition ratios (x=0.5, 1, 2) were investigated in the adsorption properties of selenium oxyanions, and were studied their adsorption mechanism. The experimental data best fits the Langmuir adsorption model, which is characteristic of monolayer adsorption (r2 >0.991). The maximum adsorption capacity (qmax) of Se(IV) and Se(VI) increased in the order of FeY2 > FeY1 > FeY0.5 and of Fe2 > FeY1, respectively. It was suggested that FeY2 adsorbed Se(IV) by formation of inner-sphere complexes and outer-sphere complexes, and adsorbed Se(VI) by outer-sphere complexes.
-
Oshima T., Kadogawa Y., Shiraishi K., Ohe K., Nishihama S., Yoshizuka K.
Solvent Extraction and Ion Exchange 43 ( 1 ) 79 - 93 2024.12
Language：English Publishing type：Research paper (scientific journal) Publisher：Solvent Extraction and Ion Exchange
Lithium is essential for the production of lithium-ion batteries, and the demand is expected to further increase. λ-MnO2 adsorbent exhibits superior selectivity of Li(I) adsorption against other alkali and alkali earth ions. In this study, the Li(I) adsorption on λ-MnO2 adsorbent granulated with alumina binder in batch and column operations, in particular, effect of acid treatment on the adsorbent was investigated. From the analysis of the adsorption isotherm by Langmuir’s model, and the maximum adsorption was calculated to be 1.64 mmol/g. The granulated adsorbent before and after excessive acid treatment was analyzed by XPS. Based on the change at the narrow spectrum attributed to the 2p orbital, decrease of Mn(II) due to the dissolution of adsorption body was suggested. The adsorption and desorption kinetics of Li(I) on the sieved granulated adsorbents were compared. The kinetics of both adsorption and desorption were explained by intraparticle diffusion equations, and the adsorbent with smaller particle size showed faster adsorption. As the rate of disproportionation reaction for the adsorbent resulting in the elution of small amount of manganese is competitive with desorption rate of Li(I) based on ion exchange, kinetic control of manganese elution in the desorption process seems to be difficult. These results should be informative for the operation of Li(I) recovery using the granulated λ-MnO2 adsorbent.
-
Automatic Selection of High-Quality Dried Shiitake Mushrooms using Machine Learning Reviewed
Ohe Kaoru, Hamasuna Ota, Takemura Kakeru, Hasebe Kodai, Hamakawa Fumito, Biki Bidesh Biswas, Ikeda Satoshi, Takei Amane, Sakamoto Makoto, Sugimoto Kazuhide
Journal of Robotics, Networking and Artificial Life 10 ( 3 ) 257 - 260 2024.9
Authorship：Lead author Language：English Publishing type：Research paper (scientific journal) Publisher：ALife Robotics Corporation Ltd.
Miyazaki Prefecture is blessed with a rich natural environment, where many mushrooms have grown wild since ancient times, and the production of dried shiitake mushrooms ranks second in Japan after Oita Prefecture. Our partner, Sugimoto Co., Ltd., is a long-established company founded in 1970, and sometimes it is necessary to sort over 1 ton. Sorting is still done manually, making it very difficult for employees to sort. The purpose of this study is to determine the quality of shiitake mushrooms using deep learning and video image processing.
-
Ohe Kaoru, Tabuchi Ryosuke, Oshima Tatsuya
Journal of Robotics, Networking and Artificial Life 10 ( 4 ) 294 - 298 2024.9
Authorship：Lead author, Corresponding author Language：English Publishing type：Research paper (scientific journal) Publisher：ALife Robotics Corporation Ltd.
Development of adsorbents for selenium and arsenic, which are particularly toxic, is urgently needed. arsenic was prepared for adsorption and removal. The experimental data of adsorption isotherms of As and Se oxyanions by NiZn adsorbents were well fitted to the Langmuir adsorption model, which is characteristic of monolayer adsorption, with a coefficient of determination of R2>0.94. The maximum adsorption (qmax) of Se(IV) by NiZn-Cl and NiZn-NO3 was similar to that of NiZn-AcO, and no difference in adsorption due to interlayer ions was indicated. On the other hand, NiZn-Cl had the highest qmax for Se(VI) and As(V). qmax for As(V) by NiZn-Cl was about twice that of NiZn-AcO, As(V) and Se(VI) adsorption performance was greatly improved.