1. 研究目的与意义（文献综述）
于是可以说灾祸可能成为技术进步的阻碍。
随着监控技术进步和对保护国家安全的迫切需要，用于监测移动物体如船舶、飞机和车辆等异常行为的自动化解决方案成为一个重要的问题[1] 。
2. 研究的基本内容与方案
2.1基本内容与目标：1） 通过增加船舶航行非空间属性，改进dbscan算法，使之更适合于建立船舶航行正常轨迹模型；2） 基于领域知识和阅读相关文献，掌握相关理论知识，设计船舶航行异常轨迹检测算法；3） 实现所设计的算法，并利用测试数据予以验证。2.2技术方案及措施：1) 开发环境visual studio2) 功能设计
图1 系统功能设计
3. 研究计划与安排
1) 2016/1/11—2016/1/22：查阅参考文献，明确选题；2) 2016/1/23—2016/3/7：进一步阅读文献，并分析和总结；确定技术路线，完成并提交开题报告；3) 2016/3/8—2016/4/26：需求分析，算法或系统设计，分析、比较或实现等；4) 2016/4/27—2016/5/27：撰写论文初稿；修改论文，定稿并提交论文评审； 5) 2016/5/28—2016/6/7：准备论文答辩。
4. 参考文献（12篇以上）
[1] David J. Hilla, Barbara S. Minsker. Anomaly detection in streaming environmental sensor data_ A data-driven modeling approach[J]. Environmental Modelling Software, 2010.9, 25(9): 1014–1022[2] Po-Ruey Lei. Exploring Trajectory Behavior Model for Anomaly detection in maritime moving objects[J], National Science Council, 2013,9(13): 271[3] A. Holst, B. Bjurling, J. Ekman, . Rudstrm. A Joint Statistical and Symbolic anomaly detection system[J]. Increasing Performance in Maritime Surveillance, 2011: 1920-1926[4] Olov Rosén, Alexander Medvedev. An On-line Algorithm For Anomaly Detection in Trajectory Data[P].America: 2012 American Control Conference, 2012[5] Dini Oktarina Dwi Handayani, Asadullah Shah, Wahju Sediono. Anomaly Detection in Vessel Tracking Using Support Vector Machines[J]. 2013 International Conference on Advanced Computer Science Applications and Technologies,2013,6(13): 213-217[6] Steven Mascaro, Ann E. Nicholsob, Kevin B. Korb. Anomaly detection in vessel tracks using Bayesian networks[J]. International Journal of Approximate Reasoning, 2014, 1(55): 84–98[7] Vladimir Avram, Uwe Glasser, Hamed Yaghoubi Shahir. Anomaly Detection in Spatiotemporal Data in the Maritime Domain[J]. ISI 2012 , 2012, 4(12):147-149[8] Zhiruo Zhao, Kishan G. Mehrotra, Chilukuri K. Mohan. Ensemble Algorithms for Unsupervised anomaly detection[C]. Switzerland: Springer International Publishing, 2015: 514-525[9] Hamed Yaghoubi Shahir, Uwe Glasser, Narek Nalbandyan, Hans When. Maritime Situation Analysis_A Multi-vessel Interaction and Anomaly Detection Framework[C]. Canada: 2014 IEEE Joint Intelligence and Security Informatics Conference, 2014: 192-199[10] Xiaobin Tan, Hongsheng Xi. Hidden semi-Markov model for anomaly detection[J]. Applied Mathematics and Computation, 2(205), 2008: 562–567[11] Bo Liu, Erico N. de Souza, Stan Matwin, Cassey Hilliard. Ship Movement Anomaly Detection Using Specialized Distance Measures[C], Washington DC: 18th International Conference on Information Fusion, 2015: 1113-1120[12] Bo Liu, Erico N. de Souza, Stan Matwin, Marcin Sydow. Knowledge-based Clustering of Ship Trajectories Using Density-based Approach[J]. 2014 IEEE International Conference on Big Data, 2014, 1(14): 603-608[13] Xiaoguang Wang, Xuan Liu, Bo Liu, Erico N. de Souza, Stan Matwin. Ship Movement Anomaly Detection Using Specialized Distance Measures[C], Washington DC: 2014 IEEE International Conference on Big Data, 2014: 25-30[14] 刘良旭, 乔少杰, 刘宾, 乐嘉锦, 唐常杰. 基于R_Tree的高效异常轨迹检测算法[J]. Journal of Software, 2009, 20(9): 2426-2435[15] Na Luo, Fuyu Yuan, Wanli Zuo, Fengling He, Zhiguo Zhou. Improved Unsupervised Anomaly Detection Algorithm[C], Berlin: Springer-Verlag Berlin Heidelberg , 2008:532–539[16] 吴贞珍, 黄建华. DBSCAN聚类算法在异常检测中的应用[J], 计算机安全, 2007, 8: 43-45[17] 杨洁.基于历史轨迹的位置预测方法研究[D].杭州:杭州电子科技大学,2015:1-57
课题毕业论文、开题报告、任务书、外文翻译、程序设计、图纸设计等资料可联系客服协助查找。
