-
摘要: 针对船舶自动识别系统(AIS)报文中的异常动态信息, 提出一种基于概率推理的包括先验知识提取、证据建模、证据合成与权重系数优化4个步骤的识别方法, 运用似然度建模方法将经过人工识别的AIS数据中的速度、航向角和轨迹位置信息转化为0~1之间的证据信度, 并用证据推理(ER)规则合成, 以验证过的AIS数据作为输入, 采用非线性优化方法修正证据权重系数, 利用武汉天兴洲大桥水域轮渡与武桥水域货船的AIS数据进行验证试验。试验结果表明: 在优化权重系数下武汉天兴洲大桥水域轮渡的正确数据、错误数据、总体数据识别准确率分别为91.67%、97.62%、92.63%;以总体偏差最小为目标时, 武桥水域货船的正确数据、错误数据、总体数据识别准确率分别为91.79%、89.87%、91.65%;以正确数据偏差最小为目标时, 武桥水域货船的正确数据、错误数据、总体数据识别准确率分别为93.18%、49.95%、90.03%。可见, 基于ER规则的AIS动态信息甄别方法能针对不同的优化目标灵活调整证据权重系数, 具有接近人工水平的识别准确率。Abstract: Aiming at the abnormal dynamic information in ship automatic identification system(AIS)messages, a recognition approach based on probabilistic inference with four steps including prior knowledge extraction, evidence modeling, evidence combination and weight coefficient optimization was proposed.Likelihood modeling approach was used to transform artificially identified velocity, course angle and track position information included in AIS data to evidence reliability between 0 and 1 that was composed by evidential reasoning(ER)rule.The verified AIS data was regarded as the input, and nonlinear optimization approach was used to modify the weight coefficient of evidence.The AIS data of ferry in Wuhan Tianxingzhou Bridge waters and the cargo ships in Wuqiao waters were used to carry out verification test.Test result shows that the recognition accuracies of correct data, incorrect data and total data for ferry in WuhanTianxingzhou Bridge waters under optimized weight coefficients are 91.67%, 97.62% and 92.63% respectively.When the minimum total deviation is goal, the recognition accuracies of correct data, incorrect data and total data for cargo ships in Wuqiao waters are 91.79%, 89.87% and 91.65% respectively.When the minimum deviation of correct data is goal, the recognition accuracies of correct data, incorrect data and total data for cargo ships in Wuqiao waters are 93.18%, 49.95% and 90.03% respectively.Obviously, the discriminating method of AIS dynamic information based on ER rule can flexibly adjust the weight coefficient of evidence with different optimized goals, and has the accuracy close to the artificial level.
-
表 1 样本的频次分布与样本总数
Table 1. Frequency distribution of samples and sample total numbers
表 2 样本的似然度分布
Table 2. Likelihood distribution of sample
表 3 一条轮渡AIS信息
Table 3. An AIS information of ferry
表 4 汇总结果
Table 4. Summary result
表 5 初始权重系数下轮渡数据样本的识别结果
Table 5. Recognition results of ferry data samples with initial weight coefficient
表 6 总体偏差最小时轮渡数据样本的识别结果
Table 6. Recognition results of ferry data samples with minimum total deviation
表 7 单一偏差最小时轮渡数据样本的识别结果
Table 7. Recognition results of ferry data samples with minimum single deviation
表 8 优化权重系数下轮渡数据样本的识别结果
Table 8. Recognition results of ferry data samples with optimized weight coefficient
表 9 总体偏差最小时货船AIS数据的识别结果
Table 9. Recognition results of AIS data for cargo ships with minimum total deviation
表 10 0单一偏差最小时货船AIS数据的识别结果
Table 10. Recognition results of AIS data for cargo ships with minimum single deviation
-
[1] 孙星, 吴勇, 初秀民. 船-标-岸协同下智能长江航运及其发展展望[J]. 交通信息与安全, 2010, 28(6): 48-52, 56. doi: 10.3963/j.ISSN1674-4861.2010.06.014SUN Xing, WU Yong, CHU Xiu-min. Intelligent Yangtze River shipping and its prospects based on coordination of shipmark-bank[J]. Journal of Transport Information and Safety, 2010, 28(6): 48-52, 56. (in Chinese). doi: 10.3963/j.ISSN1674-4861.2010.06.014 [2] 严新平, 马枫, 初秀民, 等. 长江船舶交通流实时采集关键技术研究[J]. 中国航海, 2010, 33(2): 40-45. doi: 10.3969/j.issn.1000-4653.2010.02.010YAN Xin-ping, MA Feng, CHU Xiu-min, et al. Key technology of collecting traffic flow on the Yangtze River in real-time[J]. Navigation of China, 2010, 33(2): 40-45. (in Chinese). doi: 10.3969/j.issn.1000-4653.2010.02.010 [3] PALLOTTA G, VESPE M, BRYAN K. Vessel pattern knowledge discovery from AIS data: a framework for anomaly detection and route prediction[J]. Entropy, 2013, 15(6): 2218-2245. [4] MASCARO S, KORB B K, NICHOLSON A E. Learning abnormal vessel behaviour from AIS data with Bayesian networks at two time scales[J]. Tracks A: Journal of Artists Writings, 2010(8): 1-34. [5] TALAVERA A, AGUASCA R, GALVÁN B, et al. Application of Dempster-Shafer theory for the quantification and propagation of the uncertainty caused by the use of AISdata[J]. Reliability Engineering and System Safety, 2013, 111: 95-105. doi: 10.1016/j.ress.2012.10.007 [6] AARSÆTHER K G, MOAN T. Computer vision and ship traffic analysis: inferring maneuver patterns from the automatic identification system[J]. TransNav: International Journal on Marine Navigation and Safety of Sea Transportation, 2010, 4(3): 303-308. [7] BALDAUF M, BENEDICT K, MOTZ F. Aspects of technical reliability of navigation systems and human element in case of collision avoidance[C]//RIN. Proceedings of the Navigation Conference and Exhibition 2008. London: RIN, 2008: 1-11. [8] 朱飞祥, 张英俊, 高宗江. 基于数据挖掘的船舶行为研究[J]. 中国航海, 2012, 35(2): 50-54. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGHH201202012.htmZHU Fei-xiang, ZHANG Ying-jun, GAO Zong-jiang. Research on ship behaviors based on data mining[J]. Navigation of China, 2012, 35(2): 50-54. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-ZGHH201202012.htm [9] 马枫, 初秀民, 严新平. AIS基站短消息特性[J]. 交通运输工程学报, 2012, 12(6): 111-118. http://transport.chd.edu.cn/article/id/201206017MA Feng, CHU Xiu-min, YAN Xin-ping. Short message characteristics of AIS base stations[J]. Journal of Traffic and Transportation Engineering, 2012, 12(6): 111-118. (in Chinese). http://transport.chd.edu.cn/article/id/201206017 [10] 马枫, 严新平, 初秀民, 等. 船舶自动识别系统信号失效与场强的相关性[J]. 大连海事大学学报, 2011, 37(3): 111-114. https://www.cnki.com.cn/Article/CJFDTOTAL-DLHS201103030.htmMA Feng, YAN Xin-ping, CHU Xiu-min, et al. Correlation between signal failure and field strength in automatic identify system[J]. Journal of Dalian Maritime University, 2011, 37(3): 111-114. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-DLHS201103030.htm [11] MA Feng, CHU Xiu-min, YAN Xin-ping, et al. Error distinguish of AIS based on evidence combination[J]. Journal of Theoretical and Applied Information Technology, 2012, 45(1): 83-90. [12] MA Feng, CHU Xiu-min, LIU Chen-guang. The error distinguishing of automatic identification system based on improved evidence similarity[C]//IEEE. 2nd International Conference on Transportation Information and Safety. New York: IEEE, 2013: 715-722. [13] ZHANG Wen-juan, WU Qing, SANG Ling-zhi, et al. Denoising method of inland AIS information based on vessel track[C]//IEEE. 11th International Symposium on Distributed Computing and Applications to Business, Engineering and Science. New York: IEEE, 2012: 358-361. [14] SANG Ling-zhi, WALL A, MAO Zhe, et al. A novel method for restoring the trajectory of the inland waterway ship by using AIS data[J]. Ocean Engineering, 2015, 110: 183-194. [15] ZHANG Yue-wen, CUI Wen-bin, WU Gui-tao, et al. Ashipboard remote surveillance system improved by BP neural networks[J]. Navigation of China, 2009, 32(2): 14-19. [16] LAINIOTIS D G, PLATANIOTIS K N, MENON D, et al. Neural network application to ship position estimation[C]//IEEE. OCEANS Conference 1993. New York: IEEE, 1993: 384-389. [17] XIAO Fang-liang, LIGTERINGEN H, VAN GULIJK C, et al. Comparison study on AIS data of ship traffic behavior[J]. Ocean Engineering, 2015, 95: 84-93. [18] RISTIC B, LA SCALA B, MORELANDE M, et al. Statistical analysis of motion patterns in AIS data: anomaly detection and motion prediction[C]//IEEE. 2008 11th International Conference on Information Fusion. New York: IEEE, 2008: 1-7. [19] BATTISTELLO G, ULMKE M, PAPI F, et al. Assessment of vessel route information use in Bayesian non-linear filtering[C]//IEEE. 2012 15th International Conference on Information Fusion. New York: IEEE, 2012: 447-454. [20] MASCARO S, NICHOLSO A, KORB K. Anomaly detection in vessel tracks using Bayesian networks[J]. International Journal of Approximate Reasoning, 2014, 55(1): 84-98. [21] 马枫. 内河AIS通讯链路可靠性分析与技术研究[D]. 武汉: 武汉理工大学, 2012.MA Feng. Research on the reliability and technology of AISfor inland waterway[D]. Wuhan: Wuhan University of Technology, 2012. (in Chinese). [22] YAGER R R. On the aggregation of prioritized belief structures[J]. IEEE Transactions on Systems, Man, and Cybernetics Part A: Systems and Humans, 1996, 26(6): 708-717. [23] YANG Jian-bo, XU Dong-ling. Evidential reasoning rule for evidence combination[J]. Artificial Intelligence, 2013, 205: 1-29. [24] YANG Jian-bo, XU Dong-ling. A study on generalising Bayesian inference to evidential reasoning[C]//CUZZOLINF. Proceedings of the Third International Conference on Belief Functions. New York: Springer International Publishing, 2014: 180-189. [25] LIU Xing-long, HE Wei, CHU Xiu-min, et al. A multi-source information fusion method for error AIS targets identification[J]. The Open Electrical and Electronic Engineering Journal, 2014, 8: 729-737.