Jimei University

A Review of Ship Path Planning for Autonomous Navigation: From Model-Driven Methods to Deep Reinforcement Learning

Ship path planning is a central challenge in autonomous navigation for unmanned surface vehicles and maritime autonomous surface ships. It is not simply a shortest-path problem, but a constrained sequential decision process that must reconcile collision risk, route efficiency, CO...

Numerical Study on Hydrodynamic Characteristics of a Supercavitating Vehicle During Booster Separation

The application of a staged booster system can significantly extend the operational range of a supercavitating vehicle. Booster separation from the main body within the supercavity, followed by its downstream movement and exit from the cavity, constitutes a key process in the rea...

Wintertime organic carbon export provides a potential food source for zooplankton in the High Arctic

Abstract Pulsed particulate organic carbon export plays a vital role in sustaining Arctic marine ecosystems and the biological pump. Wintertime particulate organic carbon export in ice-covered Arctic waters is generally considered negligible due to light-limited local primary pro...

Study on Microstructure and Wear Resistance Service Characteristics of AlCrN-Coated Relay Injection Mold

To address the problem of the short service life of relay injection molds caused by erosion of high-temperature glass fibers, AlCrN coatings were deposited on the surface of ELMAX mold steel using multi-arc ion plating technology. The surface morphology, cross-sectional morpholog...

Optimizing one-dimensional bin packing for conveyor belt logistics via pointer-network-based A2C and heuristics

The one-dimensional Bin Packing Problem (1D-BPP) poses significant challenges in logistics, particularly for optimizing item packing sequences in warehouse conveyor belt systems. This paper proposes a Deep Reinforcement Learning (DRL) approach using Advantage Actor-Critic (A2C) i...

Artificial intelligence driven personalized adaptive training system for individual differences in competitive sports

The current competitive sports training system generally neglects individual differences, leading to significant inter-individual variations in training effects. To address this issue, this study developed an AI-based personalized adaptive training scheme system. A 12-week interv...

Mirror‑Induced Field Compression Drives Tunable Strong Exciton–Plasmon Polaritons in WS 2 /h‐BN/Au Heterostructures

ABSTRACT Deep‑subwavelength confinement and strong coupling at visible frequencies are central to scalable nanophotonic and quantum technologies. While transition metal dichalcogenides are promising candidates for such confinement, achieving tunable strong coupling often relies o...