Institution profile

University of Hyogo

Academic institutionasia · jp
Official website
Research library22linked papers
Opportunities0open roles
Selected work

Representative Papers

SecondOpinion: Anatomy-Aware Gated Reasoning for Efficient Medical Image Analysis

Aug 03, 2026

This work addresses the inefficiency of conventional medical image analysis models that uniformly process all cases regardless of complexity. The authors propose SecondOpinion, a dual-stream framework wherein a primary stream rapidly handles all inputs, while an anatomically guided auxiliary stream is activated only when a learnable gating mechanism—GateKeeper—deems the initial prediction unreliable. Crucially, the gate is explicitly trained as a binary correctness classifier, enabling on-demand invocation of anatomical reasoning. Results on chest X-ray and pelvic fracture datasets demonstrate that the model matches or exceeds state-of-the-art performance, with auxiliary stream activation rates ranging from 9.23% to 45.71%, closely aligned with task difficulty. This approach significantly enhances computational efficiency and task adaptability.

0 citationsRead paper

Shepherding UAV Swarm with Action Prediction Based on Movement Constraints

Apr 18, 2026

Existing sheepdog-inspired drone swarm control methods often neglect realistic motion constraints and lack predictive capabilities for collective behavior, leading to suboptimal efficiency and safety in real-world deployment. This work proposes a three-dimensional herding control law that integrates explicit motion constraints with short-term behavioral prediction. The approach employs a guiding drone that leverages an internal model to forecast swarm evolution and combines Dynamic Window Approach (DWA) to generate kinematically feasible guidance actions respecting velocity and acceleration limits. Guidance performance is further refined through a multi-criteria evaluation incorporating target convergence speed, relative positioning strategy, and safety margins. By explicitly embedding motion constraints and predictive behavior modeling into the sheepdog framework—addressing a gap in prior work—the method significantly enhances the efficiency and robustness of large-scale drone swarm guidance under physical limitations, as demonstrated in simulations.

0 citationsRead paper

A Deep Reinforcement Learning Framework for Closed-loop Guidance of Fish Schools via Virtual Agents

Mar 30, 2026

This study addresses the challenge of simultaneously achieving directional control and maintaining social cohesion when guiding fish schools in closed-loop systems. The authors propose a novel framework that integrates deep reinforcement learning with real biological interactions: a proximal policy optimization (PPO) algorithm trains virtual agents in simulation to optimize a composite reward function that balances guidance objectives with group coherence, enabling online closed-loop guidance in experiments with red-nosed tetras (*Hemigrammus rhodostomus*). This work represents the first application of deep reinforcement learning to the physical steering of live fish groups and systematically evaluates the influence of visual stimulus parameters. Experimental results demonstrate that, in groups of five fish, a white background and larger stimulus size significantly enhance guidance efficiency; however, performance markedly declines when group size increases to eight individuals.

0 citationsRead paper
Recent publications

Latest Papers

SecondOpinion: Anatomy-Aware Gated Reasoning for Efficient Medical Image Analysis

Aug 03, 2026

This work addresses the inefficiency of conventional medical image analysis models that uniformly process all cases regardless of complexity. The authors propose SecondOpinion, a dual-stream framework wherein a primary stream rapidly handles all inputs, while an anatomically guided auxiliary stream is activated only when a learnable gating mechanism—GateKeeper—deems the initial prediction unreliable. Crucially, the gate is explicitly trained as a binary correctness classifier, enabling on-demand invocation of anatomical reasoning. Results on chest X-ray and pelvic fracture datasets demonstrate that the model matches or exceeds state-of-the-art performance, with auxiliary stream activation rates ranging from 9.23% to 45.71%, closely aligned with task difficulty. This approach significantly enhances computational efficiency and task adaptability.

0 citationsRead paper

Shepherding UAV Swarm with Action Prediction Based on Movement Constraints

Apr 18, 2026

Existing sheepdog-inspired drone swarm control methods often neglect realistic motion constraints and lack predictive capabilities for collective behavior, leading to suboptimal efficiency and safety in real-world deployment. This work proposes a three-dimensional herding control law that integrates explicit motion constraints with short-term behavioral prediction. The approach employs a guiding drone that leverages an internal model to forecast swarm evolution and combines Dynamic Window Approach (DWA) to generate kinematically feasible guidance actions respecting velocity and acceleration limits. Guidance performance is further refined through a multi-criteria evaluation incorporating target convergence speed, relative positioning strategy, and safety margins. By explicitly embedding motion constraints and predictive behavior modeling into the sheepdog framework—addressing a gap in prior work—the method significantly enhances the efficiency and robustness of large-scale drone swarm guidance under physical limitations, as demonstrated in simulations.

0 citationsRead paper

A Deep Reinforcement Learning Framework for Closed-loop Guidance of Fish Schools via Virtual Agents

Mar 30, 2026

This study addresses the challenge of simultaneously achieving directional control and maintaining social cohesion when guiding fish schools in closed-loop systems. The authors propose a novel framework that integrates deep reinforcement learning with real biological interactions: a proximal policy optimization (PPO) algorithm trains virtual agents in simulation to optimize a composite reward function that balances guidance objectives with group coherence, enabling online closed-loop guidance in experiments with red-nosed tetras (*Hemigrammus rhodostomus*). This work represents the first application of deep reinforcement learning to the physical steering of live fish groups and systematically evaluates the influence of visual stimulus parameters. Experimental results demonstrate that, in groups of five fish, a white background and larger stimulus size significantly enhance guidance efficiency; however, performance markedly declines when group size increases to eight individuals.

0 citationsRead paper