Koji Miyoshi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Koji Miyoshi has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
Yasuhiro Kuwahara
Hokkaido Research Organization, Fisheries Research Department, Mariculture Fisheries Research Institute, Muroran, Japan
4 shared publicationsChitose Yamazaki
Fisheries Research Department, Abashiri Fisheries Research Institute, Hokkaido Research Organization, Abashiri, Japan
2 shared publications- Koichiro Enomoto
The University of Shiga Prefecture, 2500 Hassaka-cho, Hikone, Shiga 522-8533, Japan
2 shared publications - Masashi Toda
Kumamoto University, Kumamoto, Japan
2 shared publications Shinya Hirao
Fisheries Research Department, Abashiri Fisheries Research Institute, Hokkaido Research Organization, Abashiri, Japan
2 shared publicationsSusumu Chiba
Faculty of Bioindustry, Tokyo University of Agriculture
2 shared publications
Latest Publications
- 8 October 2026
- Published by Springer Nature in Fisheries Science
- p. 1-11
Screening of antiparasitic agents against fish ectoparasite Argulus coregoni using deep-learning-based motility analysis
- 8 October 2026
- Published by Springer Nature in Fisheries Science
- p. 1-11
Screening of antiparasitic agents against fish ectoparasite Argulus coregoni using deep-learning-based motility analysis
- Open Access
- 15 September 2026
- Published by Japanese Society of Fisheries Science in NIPPON SUISAN GAKKAISHI
- Vol. 92 (5) , 317-327
Quantifying predation impact on the bottom-cultured scallop Mizuhopecten yessoensis by sea stars Asterias amurensis and Distolasterias nipon, and species-specific management strategies
階層ベイズモデルによって様々な飼育試験結果を統合解析し,マヒトデおよびニッポンヒトデによるホタテガイの捕食被害を定量化した。その結果,マヒトデの捕食はホタテガイのサイズに,ニッポンヒトデは密度に強く依存し,捕食戦略が異なることが明らかになった。実際の漁場におけるシミュレーションでは,総捕食被害の約60%が放流後1年目に集中した。放流ホタテガイの生存率を90%以上に維持するには,マヒトデ密度を0.012個体/m2以下,ニッポンヒトデ密度を0.005個体/m2以下に抑制する必要があると算出された。
- 15 September 2026
- Published by Japanese Society of Fisheries Science in NIPPON SUISAN GAKKAISHI
- Vol. 92 (5) , 317-327
Open AccessQuantifying predation impact on the bottom-cultured scallop Mizuhopecten yessoensis by sea stars Asterias amurensis and Distolasterias nipon, and species-specific management strategies
階層ベイズモデルによって様々な飼育試験結果を統合解析し,マヒトデおよびニッポンヒトデによるホタテガイの捕食被害を定量化した。その結果,マヒトデの捕食はホタテガイのサイズに,ニッポンヒトデは密度に強く依存し,捕食戦略が異なることが明らかになった。実際の漁場におけるシミュレーションでは,総捕食被害の約60%が放流後1年目に集中した。放流ホタテガイの生存率を90%以上に維持するには,マヒトデ密度を0.012個体/m2以下,ニッポンヒトデ密度を0.005個体/m2以下に抑制する必要があると算出された。
- Open Access
- 1 October 2025
- Published by MDPI AG in Geotechnics
- Vol. 5 (4) , 68
Experimental Verification of Anchor Tip Angles Suitable for Vibratory Penetration into Underwater Saturated Soft Soil
Currently, Japan’s fishing industry is facing a severe decline in its workforce. As a response, fishing mechanization using small underwater robots is promoted. These robots offer advantages due to their compact size, although their operating time is limited. A major source of this limited operating time is posture stabilization, which requires continuous thruster use and rapidly drains the battery. To reduce power consumption, anchoring the robot to the seabed with anchors is proposed. However, due to neutral buoyancy, the available thrust is limited, making penetration into the seabed difficult and reducing stability. To address this, we focus on composite-shaped anchors and vibration. The anchors combine a conical tip and a cylindrical shaft to achieve both penetrability and holding force. However, a trade-off exists between these functions depending on the tip angle; anchors with larger angles provide better holding capacity but lower penetrability. To overcome this limitation, vibration is applied to reduce soil resistance and facilitate anchor penetration. While vibration is known to aid penetration in saturated soft soils, the effect of tip angle under such conditions remains unclear. This study aims to clarify the optimal tip angle for achieving sufficient penetration and holding performance under vibratory conditions. Experiments in underwater saturated soft soil showed that vibration improves both penetration and holding. This effect was strong in anchors with tip angles optimized for holding force. These findings support the development of energy-efficient anchoring systems for autonomous underwater operations in soft seabed environments.
- 1 October 2025
- Published by MDPI AG in Geotechnics
- Vol. 5 (4) , 68
Open AccessExperimental Verification of Anchor Tip Angles Suitable for Vibratory Penetration into Underwater Saturated Soft Soil
Currently, Japan’s fishing industry is facing a severe decline in its workforce. As a response, fishing mechanization using small underwater robots is promoted. These robots offer advantages due to their compact size, although their operating time is limited. A major source of this limited operating time is posture stabilization, which requires continuous thruster use and rapidly drains the battery. To reduce power consumption, anchoring the robot to the seabed with anchors is proposed. However, due to neutral buoyancy, the available thrust is limited, making penetration into the seabed difficult and reducing stability. To address this, we focus on composite-shaped anchors and vibration. The anchors combine a conical tip and a cylindrical shaft to achieve both penetrability and holding force. However, a trade-off exists between these functions depending on the tip angle; anchors with larger angles provide better holding capacity but lower penetrability. To overcome this limitation, vibration is applied to reduce soil resistance and facilitate anchor penetration. While vibration is known to aid penetration in saturated soft soils, the effect of tip angle under such conditions remains unclear. This study aims to clarify the optimal tip angle for achieving sufficient penetration and holding performance under vibratory conditions. Experiments in underwater saturated soft soil showed that vibration improves both penetration and holding. This effect was strong in anchors with tip angles optimized for holding force. These findings support the development of energy-efficient anchoring systems for autonomous underwater operations in soft seabed environments.
- 24 September 2025
- Published by Springer Nature in Marine Biology
- Vol. 172 (10) , 1-17
Adaptive aggregation behavior of the scallop Mizuhopecten yessoensis in response to predation risk
- 24 September 2025
- Published by Springer Nature in Marine Biology
- Vol. 172 (10) , 1-17
Adaptive aggregation behavior of the scallop Mizuhopecten yessoensis in response to predation risk
- Open Access
- 5 July 2025
- Published by Fuji Technology Press Ltd. in International Journal of Automation Technology
- Vol. 19 (4) , 618-629
Deep Learning-Based Scallop Detection in Seabed Images Using Active Learning and Model Comparison
This study proposes a method for detecting scallops in seabed images using deep-learning based instance segmentation and active learning techniques. This method uses a mask region-based convolutional neural network (Mask R-CNN) combined with active learning to enable efficient annotation and adaptive learning in different seabed environments. A comparison with the transformer-based deformable detection transformer (Deformable DETR) model provides a detailed evaluation of the detection performance. The proposed method proves to be effective in detecting of object features while removing unnecessary background regions in noisy seabed environments. Active learning with margin sampling enhances the annotation process and creates an effective dataset from numerous seabed images. Experiments conducted on a large dataset of over 83,000 seabed images show that Mask R-CNN outperforms Deformable DETR, achieving an F-measure of 0.89 compared to 0.85. This study contributes to the field of fishery resource investigations by providing an approach for efficient learning using new data, which is crucial for maintaining accurate scallop detection systems over time.
- 5 July 2025
- Published by Fuji Technology Press Ltd. in International Journal of Automation Technology
- Vol. 19 (4) , 618-629
Open AccessDeep Learning-Based Scallop Detection in Seabed Images Using Active Learning and Model Comparison
This study proposes a method for detecting scallops in seabed images using deep-learning based instance segmentation and active learning techniques. This method uses a mask region-based convolutional neural network (Mask R-CNN) combined with active learning to enable efficient annotation and adaptive learning in different seabed environments. A comparison with the transformer-based deformable detection transformer (Deformable DETR) model provides a detailed evaluation of the detection performance. The proposed method proves to be effective in detecting of object features while removing unnecessary background regions in noisy seabed environments. Active learning with margin sampling enhances the annotation process and creates an effective dataset from numerous seabed images. Experiments conducted on a large dataset of over 83,000 seabed images show that Mask R-CNN outperforms Deformable DETR, achieving an F-measure of 0.89 compared to 0.85. This study contributes to the field of fishery resource investigations by providing an approach for efficient learning using new data, which is crucial for maintaining accurate scallop detection systems over time.
- Open Access
- 14 May 2025
- Published by Springer Nature in Research Square
Adaptive aggregation behavior of the scallop Mizuhopecten yessoensis in response to predation risk
Aggregation behavior in scallops, beyond known individual escape responses, may serve as an active defense against predators. We investigated this possibility in the scallop Mizuhopecten yessoensis facing the predatory sea star Distolasterias nipon. Using controlled tank experiments with varying scallop and predator densities, we analyzed individual spatial distribution, activity levels, and aggregation dynamics via automated video tracking and Bayesian statistical modeling. Results revealed density-dependent baseline spatial patterns (uniform spacing and aggregation at low and high densities, respectively) While predator presence and higher scallop density generally increased aggregation frequency, aggregation "maintenance" was distinctly controlled by different mechanisms: group size strongly promoted maintenance duration, whereas the number of predators destabilized aggregations. Complexity emerged at high density, where a single predator paradoxically induced uniform spacing, potentially via disturbance-driven dispersion, while two predators induced strong aggregation. A key finding supporting active strategic adjustment was a non-linear relationship between predator disturbance level and aggregation maintenance duration, peaking at moderate disturbance levels ("optimal disturbance hypothesis"). Furthermore, a separate experiment confirmed that scallops possess the ability to recognize and approach conspecifics via chemical signals under predation risk, suggesting a foundation for active aggregation mechanisms. Collectively, our findings demonstrate that scallop aggregation is not merely passive assembly but a complex and active adaptive strategy, dynamically adjusted based on assessments of conspecific density, group dynamics, and nuanced predation risk (presence, number, and disturbance levels). This study enhances our understanding of complex bivalve behavior and predator-prey interactions, offering new insights for resource management.
- 14 May 2025
- Published by Springer Nature in Research Square
Open AccessAdaptive aggregation behavior of the scallop Mizuhopecten yessoensis in response to predation risk
Aggregation behavior in scallops, beyond known individual escape responses, may serve as an active defense against predators. We investigated this possibility in the scallop Mizuhopecten yessoensis facing the predatory sea star Distolasterias nipon. Using controlled tank experiments with varying scallop and predator densities, we analyzed individual spatial distribution, activity levels, and aggregation dynamics via automated video tracking and Bayesian statistical modeling. Results revealed density-dependent baseline spatial patterns (uniform spacing and aggregation at low and high densities, respectively) While predator presence and higher scallop density generally increased aggregation frequency, aggregation "maintenance" was distinctly controlled by different mechanisms: group size strongly promoted maintenance duration, whereas the number of predators destabilized aggregations. Complexity emerged at high density, where a single predator paradoxically induced uniform spacing, potentially via disturbance-driven dispersion, while two predators induced strong aggregation. A key finding supporting active strategic adjustment was a non-linear relationship between predator disturbance level and aggregation maintenance duration, peaking at moderate disturbance levels ("optimal disturbance hypothesis"). Furthermore, a separate experiment confirmed that scallops possess the ability to recognize and approach conspecifics via chemical signals under predation risk, suggesting a foundation for active aggregation mechanisms. Collectively, our findings demonstrate that scallop aggregation is not merely passive assembly but a complex and active adaptive strategy, dynamically adjusted based on assessments of conspecific density, group dynamics, and nuanced predation risk (presence, number, and disturbance levels). This study enhances our understanding of complex bivalve behavior and predator-prey interactions, offering new insights for resource management.
- Open Access
- 5 May 2025
- Published by Fuji Technology Press Ltd. in International Journal of Automation Technology
- Vol. 19 (3) , 248-257
Automatic Detection and Distribution Mapping of Epibenthos from Seabed Images
The efficient investigation of fishery resources is critical for rapidly understanding the effects of abrupt environmental changes. Seabed imagery has been used extensively for resource assessment in scallop fisheries in the Sea of Okhotsk, Hokkaido, Japan. However, the potential of these images for the broader investigation of epibenthos remains unclear. In this paper, we propose an automatic detection method for epibenthos from seabed images using deep learning, specifically Mask R-CNN and Mask2Former models. We focus on four species: Asterias amurensis, Distolasterias nipon, Halocynthia aurantium, and Patiria pectinifera. The Mask R-CNN X101-FPN 3x model show the highest overall accuracy, with a mask mAP of 77.8%, whereas Mask2Former excelled in specific species detection. The trained models are successfully used to generate epibenthic distribution maps, demonstrating the effectiveness of the proposed method for monitoring large-scale marine ecosystems. This approach significantly enhances our ability to conduct comprehensive assessments of benthic communities, thereby providing an effective tool for marine-biodiversity assessment and fishery resource management.
- 5 May 2025
- Published by Fuji Technology Press Ltd. in International Journal of Automation Technology
- Vol. 19 (3) , 248-257
Open AccessAutomatic Detection and Distribution Mapping of Epibenthos from Seabed Images
The efficient investigation of fishery resources is critical for rapidly understanding the effects of abrupt environmental changes. Seabed imagery has been used extensively for resource assessment in scallop fisheries in the Sea of Okhotsk, Hokkaido, Japan. However, the potential of these images for the broader investigation of epibenthos remains unclear. In this paper, we propose an automatic detection method for epibenthos from seabed images using deep learning, specifically Mask R-CNN and Mask2Former models. We focus on four species: Asterias amurensis, Distolasterias nipon, Halocynthia aurantium, and Patiria pectinifera. The Mask R-CNN X101-FPN 3x model show the highest overall accuracy, with a mask mAP of 77.8%, whereas Mask2Former excelled in specific species detection. The trained models are successfully used to generate epibenthic distribution maps, demonstrating the effectiveness of the proposed method for monitoring large-scale marine ecosystems. This approach significantly enhances our ability to conduct comprehensive assessments of benthic communities, thereby providing an effective tool for marine-biodiversity assessment and fishery resource management.
- Open Access
- 30 May 2019
- Published by Hindawi Limited in Aquaculture Research
- Vol. 50 (9) , 2419-2428
Interactions between predatory sea stars ( Asterias amurensis and Distolasterias nipon ) and Japanese scallops ( Mizuhopecten yessoensis ) and implications for scallop seeding in mariculture
Sea stars are a key group of species in benthic marine ecosystems and represent the primary cause of mortality for cultured scallops. In the mariculture grounds of Japanese scallops (Mizuhopecten yessoensis) in north‐eastern Japan, two sea star species, Asterias amurensis (AA) and Distolasterias nipon (DN), are serious predators. However, the predatory impact of these sea stars on scallops remains unquantified, with limited information being available on the biological characteristics of DN. We compared the predatory impact of both sea star species by evaluating their predatory behaviour (i.e. probability of predation and number of captured scallops) on scallops in laboratory experiments. Both sea star species preferred smaller scallops over large ones, with the probability of predation and the number of scallops being preyed on increasing with increasing water temperature. However, DN had a greater predation impact than AA. For instance, the probability of predation by DN was higher, with more scallops being consumed. In particular, compared to AA, DN continuously captured small scallops and fed on larger scallops. Furthermore, the predatory impact of both sea star species (particularly DN) on small scallops peaked at high temperatures. In conclusion, our results present information that could help improve the survival rate of seeded scallops in mariculture systems.
- 30 May 2019
- Published by Hindawi Limited in Aquaculture Research
- Vol. 50 (9) , 2419-2428
Open AccessInteractions between predatory sea stars ( Asterias amurensis and Distolasterias nipon ) and Japanese scallops ( Mizuhopecten yessoensis ) and implications for scallop seeding in mariculture
Sea stars are a key group of species in benthic marine ecosystems and represent the primary cause of mortality for cultured scallops. In the mariculture grounds of Japanese scallops (Mizuhopecten yessoensis) in north‐eastern Japan, two sea star species, Asterias amurensis (AA) and Distolasterias nipon (DN), are serious predators. However, the predatory impact of these sea stars on scallops remains unquantified, with limited information being available on the biological characteristics of DN. We compared the predatory impact of both sea star species by evaluating their predatory behaviour (i.e. probability of predation and number of captured scallops) on scallops in laboratory experiments. Both sea star species preferred smaller scallops over large ones, with the probability of predation and the number of scallops being preyed on increasing with increasing water temperature. However, DN had a greater predation impact than AA. For instance, the probability of predation by DN was higher, with more scallops being consumed. In particular, compared to AA, DN continuously captured small scallops and fed on larger scallops. Furthermore, the predatory impact of both sea star species (particularly DN) on small scallops peaked at high temperatures. In conclusion, our results present information that could help improve the survival rate of seeded scallops in mariculture systems.
- 18 January 2018
- Published by Springer Nature in Fisheries Science
- Vol. 84 (2) , 349-355
Tracking the Northern Pacific sea star Asterias amurensis with acoustic transmitters in the scallop mariculture field of Hokkaido, Japan
- 18 January 2018
- Published by Springer Nature in Fisheries Science
- Vol. 84 (2) , 349-355
Tracking the Northern Pacific sea star Asterias amurensis with acoustic transmitters in the scallop mariculture field of Hokkaido, Japan