AIS data route mining method based on improved density peak clustering

Mu Zhiying; Li Xiaoyu; Zheng Yufang; Guo Sensen

doi:10.11959/j.issn.2096-0271.2026048

您当前的位置：

首页 >

文章列表页 >

AIS data route mining method based on improved density peak clustering

更新时间：2026-04-22

- AIS data route mining method based on improved density peak clustering
- BIG DATA RESEARCH Pages: 1-15(2026)
- 作者机构：
  
  1.西北工业大学长三角研究院，江苏太仓 215400
  2.西北工业大学网络空间安全学院，陕西西安 710072
  3.西安电子科技大学通信工程学院，陕西西安 710071
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China(U23B2041;62074131;62272389;62372069)
- DOI：10.11959/j.issn.2096-0271.2026048
  CLC： TP391
- Received：25 August 2025，
  
  Online First：22 April 2026，
- 稿件说明：
移动端阅览
慕志颖,李晓宇,郑玉方等.基于改进密度峰值聚类的AIS数据航线挖掘方法[J].大数据,

Mu Zhiying,Li Xiaoyu,Zheng Yufang,et al.AIS data route mining method based on improved density peak clustering[J].BIG DATA RESEARCH,
慕志颖,李晓宇,郑玉方等.基于改进密度峰值聚类的AIS数据航线挖掘方法[J].大数据, DOI：10.11959/j.issn.2096-0271.2026048.

Mu Zhiying,Li Xiaoyu,Zheng Yufang,et al.AIS data route mining method based on improved density peak clustering[J].BIG DATA RESEARCH, DOI：10.11959/j.issn.2096-0271.2026048.

摘要

针对现有船舶轨迹挖掘方法特征点提取阈值确认难、轨迹相似度计算效率低下以及聚类算法处理海量AIS数据时耗时过长等问题，提出了基于改进密度峰值聚类的AIS数据航线挖掘方法。首先，针对特征点阈值难以确定的问题，设计自适应阈值特征点提取算法，通过计算航向变化率和速度变化率的动态阈值自动筛选关键轨迹点；其次，针对轨迹相似度计算效率低下的问题，引入FastDTW算法计算轨迹间相似度距离，克服了传统方法在时序性和轨迹数量关系上的局限性；最后，针对聚类算法处理海量数据耗时过长的问题，结合四叉树空间分区策略，提出改进的密度峰值聚类算法，实现自适应参数选择和多分区并行聚类。在厦门港周边海域1 020万条AIS数据上进行实验验证，结果表明该方法在处理海量AIS数据时，能够准确提取目标水域的主要航路，轨迹相似度计算与航线挖掘效率显著优于传统方法。

Abstract

To address the issues of the difficulty in determining feature point thresholds

the low computational efficiency in trajectory similarity calculation and the high time complexity of clustering algorithms when processing massive AIS data in existing ship trajectory mining methods

this paper proposes an AIS data route mining method based on improved density peak clustering. Firstly

to tackle the problem of the difficulty in determining feature point thresholds

an adaptive threshold feature point extraction algorithm is designed

which automatically screens key trajectory points by calculating dynamic thresholds of course over ground (COG) change rate and speed over ground (SOG) change rate. Secondly

to address the low computational efficiency issue

the FastDTW algorithm is introduced to calculate similarity distances among trajectories

overcoming the limitations of traditional methods in terms of temporal characteristics and

trajectory quantity relationships. Finally

to solve the problem of high complexity and long processing time when clustering algorithms handle massive data

an improved density peak clustering algorithm based on the quadtree spatial partitioning strategy is proposed

which achieves adaptive parameter selection and multi-partition parallel clustering. Experimental validation is conducted using 10.2 million AIS data from waters around Xiamen Port

and the results demonstrate that the proposed method can accurately extract main routes in target waters when processing massive AIS data

significantly outperforming traditional methods in trajectory similarity calculation and route mining efficiency.

关键词

Keywords

references

Kondratenko A A , Zhang M Y , Tavakoli S , et al . Existing technologies and scientific advancements to decarbonize shipping by retrofitting [J ] . Renewable and Sustainable Energy Reviews , 2025 , 212 : 115430 .

Lu N H , Liang M H , Zheng R T , et al . Historical AIS data-driven unsupervised automatic extraction of directional maritime traffic networks [C ] // Proceedings of the 2020 IEEE 5th International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) . Piscataway : IEEE Press , 2020 : 7 - 12 .

Wang Y M . Application of neural network in abnormal AIS data identification [C ] // Proceedings of the 2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) . Piscataway : IEEE Press , 2020 : 173 - 179 .

胡昕源 , 谢磊 , 常吉亮 , 等 . 改进QuickBundles算法在船舶轨迹聚类中的应用 [J ] . 中国航海 , 2023 , 46 ( 3 ): 145 - 152 .

Hu X Y , Xie L , Chang J L , et al . Application of improved QuickBundles algorithm in ship trajectory clustering [J ] . Navigation of China , 2023 , 46 ( 3 ): 145 - 152 .

Fujino I , Claramunt C , Boudraa A O . Extracting 4-attributes vessel courses from AIS data with PQK-means and topic model [C ] // Proceedings of the 3rd International Conference on Big Data Research . New York : ACM , 2020 : 129 - 135 .

Wang G L , Meng J L , Han Y B . Extraction of maritime road networks from large-scale AIS data [J ] . IEEE Access , 2019 , 7 : 123035 - 123048 .

Sheng P , Yin J B . Extracting shipping route patterns by trajectory clustering model based on automatic identification system data [J ] . Sustainability , 2018 , 10 ( 7 ): 2327 .

Tang C H , Wang H , Zhao J H , et al . A method for compressing AIS trajectory data based on the adaptive-threshold Douglas-Peucker algorithm [J ] . Ocean Engineering , 2021 , 232 : 109041 .

Wei Z K , Xie X L , Zhang X J . AIS trajectory simplification algorithm consi-dering ship behaviours [J ] . Ocean Engineering , 2020 , 216 : 108086 .

Fernandez Arguedas V , Pallotta G , Vespe M . Maritime traffic networks: from historical positioning data to unsupervised maritime traffic monitoring [J ] . IEEE Transactions on Intelligent Transportation Systems , 2018 , 19 ( 3 ): 722 - 732 .

Jin X Y , Yang Y , Qiu X S . Framework of frequently trajectory extraction from AIS data [C ] // Proceedings of the 7th International Conference on Computer Engineering and Network (CENet2017) . Trieste : Sissa Medialab (PoS) , 2017 : 098 .

Li H H , Liu J X , Liu R , et al . A dimensionality reduction-based multi-step clustering method for robust vessel trajectory analysis [J ] . Sensors , 2017 , 17 ( 8 ): 1792 .

Chu X M , Lei J Y , Liu X L , et al . KMEANS algorithm clustering for massive AIS data based on the spark platform [C ] // Proceedings of the 2020 5th International Conference on Control, Robotics and Cybernetics (CRC) . Pisca-taway : IEEE Press , 2020 : 36 - 39 .

Zhang Z Y , Ni G X , Xu Y G . Comparison of trajectory clustering methods based on K-means and DBSCAN [C ] // Proceedings of the 2020 IEEE International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA) . Piscataway : IEEE Press , 2020 : 557 - 561 .

Lei B . A DBSCAN based algorithm for ship spot area detection in AIS trajectory data [C ] // Proceedings of the 3rd International Conference on Mechanical, System and Control Engineering . Les Ulis : EDP Sciences , 2019 : 01008

Gao M , Shi G Y . Ship-handling behavior pattern recognition using AIS sub-trajectory clustering analysis based on the T-SNE and spectral clustering algorithms [J ] . Ocean Engineering , 2020 , 205 : 106919 .

Dobrkovic A , Iacob M E , Van Hillegersberg J . Using machine learning for unsupervised maritime waypoint discovery from streaming AIS data [C ] // Proceedings of the 15th International Confe-rence on Knowledge Technologies and Data-driven Business . New York : ACM , 2015 : 1 - 8 .

何玉林 , 杨锦 , 黄哲学 , 等 . 基于标签迭代的聚类集成算法 [J ] . 智能科学与技术学报 , 2024 , 6 ( 4 ): 466 - 479 .

He Y L , Yang J , Huang Z X , et al . Label iteration-based clustering ensemble algorithm [J ] . Chinese Journal of Intelligent Science and Technology , 2024 , 6 ( 4 ): 466 - 479 .

Filipiak D , Węcel K , Stróżyna M , et al . Extracting maritime traffic networks from AIS data using evolutionary algorithm [J ] . Business & Information Systems Engineering , 2020 , 62 ( 5 ): 435 - 450 .

Finkel R A , Bentley J L . Quad trees a data structure for retrieval on composite keys [J ] . Acta Informatica , 1974 , 4 ( 1 ): 1 - 9 .

王佳玉 , 张振宇 , 褚征 , 等 . 一种基于轨迹数据密度分区的分布式并行聚类方法 [J ] . 中国科学技术大学学报 , 2018 , 48 ( 1 ): 47 - 56 .

Wang J Y , Zhang Z Y , Chu Z , et al . A trajectory data density partition based distributed parallel clustering method [J ] . Journal of University of Science and Technology of China , 2018 , 48 ( 1 ): 47 - 56 .

杨帆 , 何正伟 , 刘力荣 . 基于Spark和小波分析的水上交通异常数据实时检测方法研究 [J ] . 陕西理工大学学报(自然科学版) , 2019 , 35 ( 1 ): 35 - 41 .

Yang F , He Z W , Liu L R . Research on real-time detection method of water traffic abnormal data based on Spark and wavelet analysis [J ] . Journal of Shaanxi University of Technology (Natural Science Edution) , 2019 , 35 ( 1 ): 35 - 41 .

肖潇 , 邵哲平 , 潘家财 , 等 . 基于AIS信息的船舶轨迹聚类模型及应用 [J ] . 中国航海 , 2015 , 38 ( 2 ): 82 - 86 .

Xiao X , Shao Z P , Pan J C , et al . Ship trajectory clustering model based on AIS data and its application [J ] . Navigation of China , 2015 , 38 ( 2 ): 82 - 86 .

郭倩 , 赵津 , 过弋 . 基于分层聚类的个性化联邦学习隐私保护框架 [J ] . 信息网络安全 , 2024 , 24 ( 8 ): 1196 - 1209 .

Guo Q , Zhao J , Guo Y . Hierarchical clustering federated learning framework for personalized privacy-preserving [J ] . Netinfo Security , 2024 , 24 ( 8 ): 1196 - 1209 .

Salvador S , Chan P . Toward accurate dynamic time warping in linear time and space [J ] . Intelligent Data Analysis , 2007 , 11 ( 5 ): 561 - 580 .

Rodriguez A , Laio A . Clustering by fast search and find of density peaks [J ] . Science , 2014 , 344 ( 6191 ): 1492 - 1496 .

钮焱 , 李星 , 李军 , 等 . 基于DTW和改进匈牙利算法的句子语义相似度研究 [J ] . 计算机与数字工程 , 2021 , 49 ( 2 ): 242 - 247 .

Niu Y , Li X , Li J , et al . Research on sentence semantic similarity based on DTW and improved Hungarian algorithm [J ] . Computer and Digital Engineering , 2021 , 49 ( 2 ): 242 - 247 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰