计算机科学 ›› 2021, Vol. 48 ›› Issue (9): 59-67.doi: 10.11896/jsjkx.210100014
所属专题： 智能数据治理技术与系统
宋嘉庚, 张扶桑, 金蓓弘, 窦竹梅
SONG Jia-geng, ZHANG Fu-sang, JIN Bei-hong, DOU Zhu-mei
摘要： 随着全球定位系统和雷达技术的发展,越来越多的轨迹数据可以被收集到,其中,飞机、轮船、候鸟等对象产生的轨迹复杂多变,自由度较大。为了帮助识别飞行对象的行为和意图,航迹类型识别具有重要作用。文中提出了一种基于频繁航路模式的航迹分类方法。该方法包含一个频繁航路提取算法和一个卷积神经网络模型。算法首先对轨迹进行压缩,获得关键点;接着通过寻找轨迹自相交点提取闭合航路,然后寻找闭合航路中的频繁航路模式作为模型的分类依据;最后通过图像处理完成航迹类型的识别。文中利用FlightRadar24网站公开的真实航迹数据和模拟数据进行了大量的实验,结果表明,所提方法能有效识别复杂轨迹类型,与不经过轨迹提取的LeNet-5 CNN分类模型相比,所提方法性能更优,在轨迹分类上实现了95%以上的平均准确率。
中图分类号:
| [1]ZHENG Y,CAPRA L,WOLFSON O,et al.Urban computing:concepts,methodologies,and applications[J].ACM Transactions on Intelligent Systems and Technology (TIST),2014,5(3):1-55. [2]YUAN N J,ZHENG Y,XIE X.Discovering functional zones in a city using human movements and points of interest[M]//Spatial Analysis and Location Modeling in Urban and Regional Systems.Berlin,Heidelberg:Springer,2018:33-62. [3]CUI G.Personalized Travel Route Recommendation Based onGPS Trajectories[J].International Journal of Digital Earth,2018,11(12):1-24. [4]YI X,DUAN Z,LI T,et al.Citytraffic:Modeling citywide traffic via neural memorization and generalization approach[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management.2019:2665-2671. [5]PAN Z,LIANG Y,WANG W,et al.Urban traffic prediction from spatio-temporal data using deep meta learning[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2019:1720-1730. [6]ZHENG Y.Location-based social networks:Users[M]//Computing with Spatial Trajectories.New York,NY:Springer,2011:243-276. [7]SU H,LIU S,ZHENG B,et al.A survey of trajectory distance measures and performance evaluation[J].The VLDB Journal,2020,29(1):3-32. [8]PELEKIS N,KOPANAKIS I,MARKETOS G,et al.Similarity search in trajectory databases[C]//14th International Sympo-sium on Temporal Representation and Reasoning (TIME'07).IEEE,2007:129-140. [9]MONREALE A,PINELLI F,TRASARTI R,et al.WhereNext:A location predictor on trajectory pattern mining[C]//Procee-dings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.Paris,France:ACM,2009. [10]ZHENG Y,ZHANG L,MA Z,et al.Recommending friends and locations based on individual location history[J].ACM Transactions on the Web (TWEB),2011,5(1):1-44. [11]GIANNOTTI F,NANNI M,PINELLI F,et al.Trajectory pattern mining[C]//Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2007:330-339. [12]YE Y,ZHENG Y,CHEN Y,et al.Mining individual life pattern based on location history[C]//2009 tenth International Confe-rence on Mobile Data Management:Systems,Services and Middleware.IEEE,2009:1-10. [13]PEI J,HAN J W,MORTAZAVI-ASL B,et al.PrefixSpan:mi-ning sequential patterns efficiently by prefix-projected pattern growth[C]//17th International Conference on Data Enginee-ring.2001:215-224. [14]TSAI C Y,LIOU J J H,CHEN C J,et al.Generating touring path suggestions using time-interval sequential pattern mining[J].Expert Systems with Applications,2012,39(3):3593-3602. [15]LI Z,DING B,HAN J,et al.Mining periodic behaviors for mo-ving objects[C]//Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2010:1099-1108. [16]ZHENG K,ZHENG Y,YUAN N J,et al.On discovery of ga-thering patterns from trajectories[C]//2013 IEEE 29th International Conference on Data Engineering (ICDE).IEEE,2013:242-253. [17]YAO D,ZHANG C,ZHU Z,et al.Learning deep representation for trajectory clustering[J].Expert Systems,2018,35(2):e12252. [18]ZHENG Y,ZHANG L,XIE X,et al.Mining interesting loca-tions and travel sequences from GPS trajectories[C]//Procee-dings of the 18th International Conference on World Wide Web.2009:791-800. [19]ZHENG Y,XIE X.Learning travel recommendations from user-generated GPS traces[J].ACM Transactions on Intelligent Systems and Technology (TIST),2011,2(1):1-29. [20]ENDO Y,TODA H,NISHIDA K,et al.Classifying spatial tra-jectories using representation learning[J].International Journal of Data Science and Analytics,2016,2(3/4):107-117. [21]JIANG X,DE SOUZA E N,PESARANGHADER A,et al.Tra-jectory Net:An embedded gps trajectory representation for point-based classification using recurrent neural networks[J].arXiv:1705.02636,2017. [22]ANNONI R,FORSTER C H Q.Analysis of aircraft trajectories using fourier descriptors and kernel density estimation[C]//2012 15th International IEEE Conference on Intelligent Transportation Systems.IEEE,2012:1441-1446. [23]SONG Y,CHENG P,MU C.An improved trajectory prediction algorithm based on trajectory data mining for air traffic management[C]//2012 IEEE International Conference on Information and Automation.IEEE,2012:981-986. [24]LIU S S,MA S X,MENG X,et al.Prediction Model of ShipTrajectory Based on CNN and Bi-LSTM[J].Journal of Chongqing University of Technology( Natural Science),2020,34(12):196-205. [25]LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based lear-ning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324. |
| [1] | 吴成凤, 蔡莉, 李劲, 梁宇. 基于多源位置数据的居民出行频繁模式挖掘 Frequent Pattern Mining of Residents’ Travel Based on Multi-source Location Data 计算机科学, 2021, 48(7): 155-163. https://doi.org/10.11896/jsjkx.200800072 |
| [2] | 崔彤彤, 王桂玲, 高晶. 基于1DCNN-LSTM的船舶轨迹分类方法 Ship Trajectory Classification Method Based on 1DCNN-LSTM 计算机科学, 2020, 47(9): 175-184. https://doi.org/10.11896/jsjkx.191000162 |
| [3] | 陆鑫赟, 王兴芬. 基于领域关联冗余的教务数据关联规则挖掘 Educational Administration Data Mining of Association Rules Based on Domain Association Redundancy 计算机科学, 2019, 46(6A): 427-430. |
| [4] | 张洪泽, 洪征, 王辰, 冯文博, 吴礼发. 基于闭合序列模式挖掘的未知协议格式推断方法 Closed Sequential Patterns Mining Based Unknown Protocol Format Inference Method 计算机科学, 2019, 46(6): 80-89. https://doi.org/10.11896/j.issn.1002-137X.2019.06.011 |
| [5] | 孙文平, 常亮, 宾辰忠, 古天龙, 孙彦鹏. 基于知识图谱和频繁序列挖掘的旅游路线推荐 Travel Route Recommendation Based on Knowledge Graph and Frequent Sequence Mining 计算机科学, 2019, 46(2): 56-61. https://doi.org/10.11896/j.issn.1002-137X.2019.02.009 |
| [6] | 荣俸萍,方勇,左政,刘亮. MACSPMD:基于恶意API调用序列模式挖掘的恶意代码检测 MACSPMD:Malicious API Call Sequential Pattern Mining Based Malware Detection 计算机科学, 2018, 45(5): 131-138. https://doi.org/10.11896/j.issn.1002-137X.2018.05.022 |
| [7] | 魏芹双,武优西,刘靖宇,朱怀忠. 基于密度约束和间隙约束的对比模式挖掘 Distinguishing Sequence Patterns Mining Based on Density and Gap Constraints 计算机科学, 2018, 45(4): 252-256. https://doi.org/10.11896/j.issn.1002-137X.2018.04.042 |
| [8] | 张光兰, 杨秋辉, 程雪梅, 姜科, 王帅, 谭武坤. 序列模式挖掘在通信网络告警预测中的应用 Application of Sequence Pattern Mining in Communication Network Alarm Prediction 计算机科学, 2018, 45(11A): 535-538. |
| [9] | 王树怡,董东. 基于聚类和偏序序列的API用法模式挖掘 Mining of API Usage Pattern Based on Clustering and Partial Order Sequences 计算机科学, 2017, 44(Z6): 486-490. https://doi.org/10.11896/j.issn.1002-137X.2017.6A.108 |
| [10] | 宁卓,邵达成,陈勇,孙知信. 基于签名与数据流模式挖掘的Android恶意软件检测系统 Android Static Analysis System Based on Signature and Data Flow Pattern Mining 计算机科学, 2017, 44(Z11): 317-321. https://doi.org/10.11896/j.issn.1002-137X.2017.11A.067 |
| [11] | 崔展齐,牟永敏,张志华,王伟光. 基于函数调用序列模式挖掘的程序缺陷检测 Defects Detection Based on Mining Function Call Sequence Patterns 计算机科学, 2017, 44(11): 226-231. https://doi.org/10.11896/j.issn.1002-137X.2017.11.034 |
| [12] | 丁剑,韩萌,李娟. 概念漂移数据流挖掘算法综述 Review of Concept Drift Data Streams Mining Techniques 计算机科学, 2016, 43(12): 24-29. https://doi.org/10.11896/j.issn.1002-137X.2016.12.004 |
| [13] | 姬浩博,王俊红. 一种改进的PrefixSpan算法及其在Web用户行为模式挖掘中的应用 Research on Improved PrefixSpan Algorithm and its Application in Web User Behavior Patterns Mining 计算机科学, 2016, 43(1): 25-29. https://doi.org/10.11896/j.issn.1002-137X.2016.01.006 |
| [14] | 周剑云,王丽珍,杨增芳. 基于加权欧氏距离的空间Co-location模式挖掘算法研究 Algorithm of Mining Spatial Co-location Patterns Based on Weighted Euclidean Distance 计算机科学, 2014, 41(Z6): 425-428. |
| [15] | 温佛生,肖清,王丽珍,孔兵. 一种模糊对象的极大co-location模式挖掘算法 Algorithm of Mining Maximal Co-location Patterns for Fuzzy Objects 计算机科学, 2014, 41(1): 138-145. |
|
||
首页