With the globalization of the economy,maritime trade has surged,posing challenges in the supervision of marine vessel activities.An automatic identification system(AIS)is an effective means of shipping traffic service...With the globalization of the economy,maritime trade has surged,posing challenges in the supervision of marine vessel activities.An automatic identification system(AIS)is an effective means of shipping traffic service,but many uncertainties exist regarding its data quality.In this study,the AIS data from Haiyang(HY)series of satellites were used to assess the data quality,analyze the global ship trajectory distribution and update frequencies from 2019 to 2023.Through the analysis of maritime mobile service identity numbers,we identified 340185 unique vessels,80.1%of which adhered to the International Telecommunication Union standards.Approximately 49.7%of ships exhibit significant data gaps,and 1.1%show inconsistencies in their AIS data sources.In the central Pacific Ocean at low latitudes and along the coast of South America(30°-60°S),a heightened incidence of abnormal trajectories of ships has been consistently observed,particularly in areas associated with fishing activities.According to the spatial distribution of ship trajectories,AIS data exhibit numerous deficiencies,particularly in high-traffic regions such as the East China Sea and South China Sea.In contrast,ship trajectories in the polar regions,characterized by high latitudes,are relatively comprehensive.With the increased number of HY satellites equipped with AIS receivers,the quantity of trajectory points displays a growing trend,leading to increasingly complete trajectories.This trend highlights the significant potential of using AIS data acquired from HY satellites to increase the accuracy of vessel tracking.展开更多
With the rapid development of the global economy, maritime transportation has become much more convenient due to large capacities and low freight. However, this means the sea lanes are becoming more and more crowded,l...With the rapid development of the global economy, maritime transportation has become much more convenient due to large capacities and low freight. However, this means the sea lanes are becoming more and more crowded,leading to high probabilities of marine accidents in complex maritime environments. According to relevant historical statistics, a large number of accidents have happened in water areas that lack high precision navigation data, which can be utilized to enhance navigation safety. The purpose of this work was to carry out ship route planning automatically, by mining historical big automatic identification system(AIS) data. It is well-known that experiential navigation information hidden in maritime big data could be automatically extracted using advanced data mining techniques;assisting in the generation of safe and reliable ship planning routes for complex maritime environments. In this paper, a novel method is proposed to construct a big data-driven framework for generating ship planning routes automatically, under varying navigation conditions. The method performs density-based spatial clustering of applications with noise first on a large number of ship trajectories to form different trajectory vector clusters. Then, it iteratively calculates its centerline in the trajectory vector cluster, and constructs the waterway network from the node-arc topology relationship among these centerlines. The generation of shipping route could be based on the waterway network and conducted by rasterizing the marine environment risks for the sea area not covered by the waterway network. Numerous experiments have been conducted on different AIS data sets in different water areas, and the experimental results have demonstrated the effectiveness of the framework of the ship route planning proposed in this paper.展开更多
Predicting the future trajectories of multiple agents is essential for various applications in real life,such as surveillance systems,autonomous driving,and social robots.The trajectory prediction task is influenced b...Predicting the future trajectories of multiple agents is essential for various applications in real life,such as surveillance systems,autonomous driving,and social robots.The trajectory prediction task is influenced by many factors,including the individual historical trajectory,interactions between agents,and the fuzzy nature of the observed agents’motion.While existing methods have made great progress on the topic of trajectory prediction,they treat all the information uniformly,which limits the effectiveness of information utilization.To this end,in this paper,we propose and utilize a model-agnostic framework to regard all the information in a two-level hierarchical view.Particularly,the first-level view is the inter-trajectory view.In this level,we observe that the difficulty in predicting different trajectory samples varies.We define trajectory difficulty and train the proposed framework in an“easy-to-hard”schema.The second-level view is the intra-trajectory level.We find the influencing factors for a particular trajectory can be divided into two parts.The first part is global features,which keep stable within a trajectory,i.e.,the expected destination.The second part is local features,which change over time,i.e.,the current position.We believe that the two types of information should be handled in different ways.The hierarchical view is beneficial to take full advantage of the information in a fine-grained way.Experimental results validate the effectiveness of the proposed model-agnostic framework.展开更多
船舶行为特征挖掘与预测是水上智能交通系统的重要研究内容,也是交通运输工程领域的关键科学问题。为系统研究基于船舶自动识别系统(Automatic Identification System,AIS)数据的船舶行为特征挖掘与预测的研究现状与发展趋势,本文首先针...船舶行为特征挖掘与预测是水上智能交通系统的重要研究内容,也是交通运输工程领域的关键科学问题。为系统研究基于船舶自动识别系统(Automatic Identification System,AIS)数据的船舶行为特征挖掘与预测的研究现状与发展趋势,本文首先针对Web of Science(WOS)和中国知网(China National Knowledge Infrastructure,CNKI)收录的文献,用知识图谱分析软件VOSviewer对文献关键词进行处理,从文献计量学的角度生成高频关键词的聚类图谱和趋势演化。然后对基于AIS数据的水上交通要素挖掘、船舶行为聚类和船舶行为预测3个主题的研究内容、方法、存在问题进行了系统分析和展望,研究结果表明:①在基于AIS的水上交通要素挖掘方面,主要集中在对AIS数据中表征船舶行为空间特征和交通流的时间特征单独挖掘分析,缺乏对AIS数据的时间、空间以及环境因素特征的关联挖掘,对于如何进行交通要素的关联融合挖掘研究还有待深入探索;②在船舶行为聚类方面,研究主要是运用无监督聚类方法研究船舶航迹点和航迹段聚类,得到船舶航行行为模式的时空分布和船舶操纵意图辨识模型,然而融合多维特征的船舶轨迹的相似性计算方法、聚类参数的自适应选取以及船舶行为的语义特征建模有待进一步研究;③在船舶行为预测方面,主要集中在基于动力学方程、传统智能算法和深度循环神经网络的船舶行为预测研究,考虑船舶行为的随机性、多样性和耦合性的特点,运用混合神经网络模型以及神经网络与向量机、注意力机制相结合的模型实现多维的船舶航行行为特征的实时预测将是新的研究方向。最后提出了基于语义模型的船舶行为特征挖掘、基于深度卷积神经网络的船舶行为的预测和基于知识图谱的船舶行为特征挖掘和预测结果可视化等有待进一步研究的方向。展开更多
基金The National Key R&D Program of China under contract Nos 2021YFC2803305 and 2024YFC2816301the Fundamental Research Funds for the Central Universities of China under contract No.2042022dx0001.
文摘With the globalization of the economy,maritime trade has surged,posing challenges in the supervision of marine vessel activities.An automatic identification system(AIS)is an effective means of shipping traffic service,but many uncertainties exist regarding its data quality.In this study,the AIS data from Haiyang(HY)series of satellites were used to assess the data quality,analyze the global ship trajectory distribution and update frequencies from 2019 to 2023.Through the analysis of maritime mobile service identity numbers,we identified 340185 unique vessels,80.1%of which adhered to the International Telecommunication Union standards.Approximately 49.7%of ships exhibit significant data gaps,and 1.1%show inconsistencies in their AIS data sources.In the central Pacific Ocean at low latitudes and along the coast of South America(30°-60°S),a heightened incidence of abnormal trajectories of ships has been consistently observed,particularly in areas associated with fishing activities.According to the spatial distribution of ship trajectories,AIS data exhibit numerous deficiencies,particularly in high-traffic regions such as the East China Sea and South China Sea.In contrast,ship trajectories in the polar regions,characterized by high latitudes,are relatively comprehensive.With the increased number of HY satellites equipped with AIS receivers,the quantity of trajectory points displays a growing trend,leading to increasingly complete trajectories.This trend highlights the significant potential of using AIS data acquired from HY satellites to increase the accuracy of vessel tracking.
文摘With the rapid development of the global economy, maritime transportation has become much more convenient due to large capacities and low freight. However, this means the sea lanes are becoming more and more crowded,leading to high probabilities of marine accidents in complex maritime environments. According to relevant historical statistics, a large number of accidents have happened in water areas that lack high precision navigation data, which can be utilized to enhance navigation safety. The purpose of this work was to carry out ship route planning automatically, by mining historical big automatic identification system(AIS) data. It is well-known that experiential navigation information hidden in maritime big data could be automatically extracted using advanced data mining techniques;assisting in the generation of safe and reliable ship planning routes for complex maritime environments. In this paper, a novel method is proposed to construct a big data-driven framework for generating ship planning routes automatically, under varying navigation conditions. The method performs density-based spatial clustering of applications with noise first on a large number of ship trajectories to form different trajectory vector clusters. Then, it iteratively calculates its centerline in the trajectory vector cluster, and constructs the waterway network from the node-arc topology relationship among these centerlines. The generation of shipping route could be based on the waterway network and conducted by rasterizing the marine environment risks for the sea area not covered by the waterway network. Numerous experiments have been conducted on different AIS data sets in different water areas, and the experimental results have demonstrated the effectiveness of the framework of the ship route planning proposed in this paper.
基金supported by the Youth Innovation Promotion Association of Chinese Academy of Sciences under Grant No.2023112the National Natural Science Foundation of China under Grant No.62206266Zhao Zhang is supported by the China Postdoctoral Science Foundation under Grant No.2021M703273.
文摘Predicting the future trajectories of multiple agents is essential for various applications in real life,such as surveillance systems,autonomous driving,and social robots.The trajectory prediction task is influenced by many factors,including the individual historical trajectory,interactions between agents,and the fuzzy nature of the observed agents’motion.While existing methods have made great progress on the topic of trajectory prediction,they treat all the information uniformly,which limits the effectiveness of information utilization.To this end,in this paper,we propose and utilize a model-agnostic framework to regard all the information in a two-level hierarchical view.Particularly,the first-level view is the inter-trajectory view.In this level,we observe that the difficulty in predicting different trajectory samples varies.We define trajectory difficulty and train the proposed framework in an“easy-to-hard”schema.The second-level view is the intra-trajectory level.We find the influencing factors for a particular trajectory can be divided into two parts.The first part is global features,which keep stable within a trajectory,i.e.,the expected destination.The second part is local features,which change over time,i.e.,the current position.We believe that the two types of information should be handled in different ways.The hierarchical view is beneficial to take full advantage of the information in a fine-grained way.Experimental results validate the effectiveness of the proposed model-agnostic framework.
文摘船舶行为特征挖掘与预测是水上智能交通系统的重要研究内容,也是交通运输工程领域的关键科学问题。为系统研究基于船舶自动识别系统(Automatic Identification System,AIS)数据的船舶行为特征挖掘与预测的研究现状与发展趋势,本文首先针对Web of Science(WOS)和中国知网(China National Knowledge Infrastructure,CNKI)收录的文献,用知识图谱分析软件VOSviewer对文献关键词进行处理,从文献计量学的角度生成高频关键词的聚类图谱和趋势演化。然后对基于AIS数据的水上交通要素挖掘、船舶行为聚类和船舶行为预测3个主题的研究内容、方法、存在问题进行了系统分析和展望,研究结果表明:①在基于AIS的水上交通要素挖掘方面,主要集中在对AIS数据中表征船舶行为空间特征和交通流的时间特征单独挖掘分析,缺乏对AIS数据的时间、空间以及环境因素特征的关联挖掘,对于如何进行交通要素的关联融合挖掘研究还有待深入探索;②在船舶行为聚类方面,研究主要是运用无监督聚类方法研究船舶航迹点和航迹段聚类,得到船舶航行行为模式的时空分布和船舶操纵意图辨识模型,然而融合多维特征的船舶轨迹的相似性计算方法、聚类参数的自适应选取以及船舶行为的语义特征建模有待进一步研究;③在船舶行为预测方面,主要集中在基于动力学方程、传统智能算法和深度循环神经网络的船舶行为预测研究,考虑船舶行为的随机性、多样性和耦合性的特点,运用混合神经网络模型以及神经网络与向量机、注意力机制相结合的模型实现多维的船舶航行行为特征的实时预测将是新的研究方向。最后提出了基于语义模型的船舶行为特征挖掘、基于深度卷积神经网络的船舶行为的预测和基于知识图谱的船舶行为特征挖掘和预测结果可视化等有待进一步研究的方向。
