Maritime traffic partitioning: An adaptive semi-supervised spectral regularization approach for leveraging multi-graph evolutionary traffic interactions

Transportation Research Part C Emerging Technologies, Год журнала: 2024, Номер 164, С. 104670 - 104670

Опубликована: Май 27, 2024

Maritime situational awareness (MSA) has long been a critical focus within the domain of maritime traffic surveillance and management. The increasing complexities ship traffic, originating from sophisticated multi-attribute interactions among multiple ships, coupled with continuous evolution dynamics, pose significant challenges in attaining accurate MSA, particularly complex port waters. This study is dedicated to establishing an advanced methodology for partitioning aimed at enhancing pattern interpretability strengthening anti-collision risk Specifically, three interaction measure metrics, including conflict criticality, spatial distance, approaching rate, are initially introduced quantify different aspects spatiotemporal ships. Subsequently, semi-supervised spectral regularization framework devised adeptly accommodate both information prior knowledge derived historic structures. facilitates segmentation regional into clusters, wherein ships same cluster exhibit high temporal stability, connectivity, compactness, convergent motion. Meanwhile, adaptive hyperparameter selection model engineered seek optimal outcomes across diverse scenarios, while also incorporating user preferences specific indicators. Comprehensive experiments using AIS data Ningbo-Zhoushan Port undertaken thoroughly assess models' efficacy. Research findings case analyses comparisons distinctly showcase capability proposed approach successfully deconstruct complexity, capture high-risk zones, strengthen strategic safety measures. Consequently, holds promise advancing intelligence systems facilitating automation

Язык: Английский

---

Time-evolving graph-based approach for multi-ship encounter analysis: Insights into ship behavior across different scenario complexity levels

Transportation Research Part A Policy and Practice, Год журнала: 2025, Номер 194, С. 104427 - 104427

Опубликована: Фев. 27, 2025

Язык: Английский

---

An efficient model for small object detection in the maritime environment

Applied Ocean Research, Год журнала: 2024, Номер 152, С. 104194 - 104194

Опубликована: Авг. 27, 2024

Язык: Английский

---

Incorporation of adaptive compression into a GPU parallel computing framework for analyzing large-scale vessel trajectories

Transportation Research Part C Emerging Technologies, Год журнала: 2024, Номер 163, С. 104648 - 104648

Опубликована: Май 9, 2024

Automatic Identification System (AIS) offers a wealth of vessel navigation data, which underpins research in maritime data mining, situational awareness, and knowledge discovery within the realm intelligent transportation systems. The flourishing marine industry has prompted AIS satellites base stations to generate massive amounts trajectory escalating both storage calculation costs. conventional Douglas-Peucker (DP) algorithm used for compression sets uniform threshold, hampers effective compression. Additionally, compressing accelerating computation large datasets poses significant challenge real-world applications. To address these limitations, this paper aims develop new Graphics Processing Unit (GPU) parallel computing framework that enables acceleration optimal threshold each automatically big mining. It achieves by incorporating Adaptive DP with Speed Course (ADPSC) algorithm, utilizes dynamic characteristics different vessels. can effectively solve associated computational time cost concern when using ADPSC compress vast real world. proposes novel evaluation metric assessing efficacy based on Dynamic Time Warping (DTW) method. Comprehensive experiments encompass from three representative areas: Tianjin Port, Chengshan Jiao Promontory, Caofeidian Port. experimental results demonstrate 1) newly developed method outperforms terms compression, 2) designed GPU significantly shorten extensive datasets. GPU-accelerated methodology not only minimizes transmission costs manned unmanned vessels but also enhances processing speed, supporting real-time decision-making. From theoretical perspective, it provides key puzzle realizing anti-collision ships, particularly complex waters. hence makes contributions safety autonomous shipping era.

Язык: Английский

---

COLERGs-constrained safe reinforcement learning for realising MASS's risk-informed collision avoidance decision making

Knowledge-Based Systems, Год журнала: 2024, Номер 300, С. 112205 - 112205

Опубликована: Июль 16, 2024

Язык: Английский

---

Analyzing risk influencing factors of ship collision accidents: A data-driven Bayesian network model integrating physical knowledge

Ocean & Coastal Management, Год журнала: 2024, Номер 256, С. 107311 - 107311

Опубликована: Июль 30, 2024

Язык: Английский

---

Bi-directional information fusion-driven deep network for ship trajectory prediction in intelligent transportation systems

Transportation Research Part E Logistics and Transportation Review, Год журнала: 2024, Номер 192, С. 103770 - 103770

Опубликована: Сен. 20, 2024

Язык: Английский

---

A game-based decision-making method for multi-ship collaborative collision avoidance reflecting risk attitudes in open waters

Ocean & Coastal Management, Год журнала: 2024, Номер 259, С. 107450 - 107450

Опубликована: Окт. 23, 2024

Язык: Английский

---

A Dynamic Trajectory Temporal Density Model for Analyzing Maritime Traffic Patterns

Journal of Marine Science and Engineering, Год журнала: 2025, Номер 13(2), С. 381 - 381

Опубликована: Фев. 19, 2025

This study investigates the spatiotemporal density aggregation and pattern distribution of vessel traffic amidst bustling maritime logistics scenarios. Firstly, a relatively new segmentation reconstruction method is proposed for ship AIS trajectories to address trajectory disruptions caused by berthing, anchorage, other factors. Subsequently, filtering algorithm utilizing time window panning introduced mitigate position jumps deviation errors in points, ensuring that dynamic adheres correlations motion. Secondly, establish geographical spatial mapping trajectories, gridding applied areas. By associating space activities with temporal attributes model constructed. Finally, case conducted evaluate effectiveness applicability identifying patterns states. The results show can identify after application compression algorithms, providing novel approach studying era big data.

Язык: Английский

---

Collision avoidance method for unmanned ships using a modified APF algorithm

Frontiers in Marine Science, Год журнала: 2025, Номер 12

Опубликована: Фев. 27, 2025

The Artificial Potential Field (APF) algorithm has been widely used for collision avoidance on unmanned ships. However, traditional APF methods have several defects that need to be addressed. To ensure safe navigation with good seamanship and full compliance the Convention International Regulations Preventing Collisions at Sea, 1972 (COLREGS), this study proposes a dynamic method based algorithm. proposed incorporates ship domain priority judgment encounter situation, allowing perform operations in accordance actual operational requirements. address path interference unreachable target issues, new attractive potential field function is introduced, dividing of point into multiple segments simultaneously. Additionally, repulsive force own reduced when close point. results show effectively resolves oscillation problems by integrating partial ideas from Dynamic Window Approach (DWA). In comparison algorithms, overall smoothing degree was improved 71.8%, verifying effectiveness superiority

Язык: Английский

---