计算机应用 ›› 2015, Vol. 35 ›› Issue (11): 3106-3111.DOI: 10.11772/j.issn.1001-9081.2015.11.3106

• 2015年全国开放式分布与并行计算学术年会(DPCS 2015)论文 • 上一篇    下一篇

河网中具有时空关系的异常事件在线检测

毛莺池1, 接青1, 陈豪2,3   

  1. 1. 河海大学 计算机与信息学院, 南京 211100;
    2. 河海大学 水利水电学院, 南京 210098;
    3. 华能澜沧江水电股份有限公司, 昆明 650214
  • 收稿日期:2015-06-17 修回日期:2015-07-28 发布日期:2015-11-13
  • 通讯作者: 毛莺池(1976-),女,上海人,副教授,博士,CCF会员,主要研究方向:分布式计算、并行处理、分布式数据管理.
  • 作者简介:接青(1989-),女,山东烟台人,硕士研究生,主要研究方向:分布式计算、并行处理、数据管理; 陈豪(1982-),男,上海人,高级工程师,博士研究生,主要研究方向:水工结构安全监测.
  • 基金资助:
    国家自然科学基金资助项目(61272543);国家科技支撑计划项目(2013BAB06B04);中央高校基本科研业务费专项资金资助项目(2015B22214)中国华能集团公司总部科技项目(HNKJ13-H17-04);云南省科技计划项目(2014GA007).

Online abnormal event detection with spatio-temporal relationship in river networks

MAO Yingchi1, JIE Qing1, CHEN Hao2,3   

  1. 1. College of Computer and Information, Hohai University, Nanjing Jiangsu 211100, China;
    2. College of Water Conservancy and Hydropower Engineering, Hohai University, Nanjing Jiangsu 210098, China;
    3. Huaneng Lancang River Hydropower Company Limited, Kunming Yunnan 650214, China
  • Received:2015-06-17 Revised:2015-07-28 Published:2015-11-13

摘要: 当网络异常事件发生时,传感器节点间的时空相关性往往非常明显.而现有方法通常将时间和空间数据性质分开考虑,提出一种分散的基于概率图模型的时空异常事件检测算法.该算法首先利用连通支配集算法(CDS)选择部分传感器节点监测,避免监测所有的传感器节点;然后通过马尔可夫链(MC)预测时间异常事件;最后用贝叶斯网络(BN)推测空间异常事件是否出现,结合时空事件来预测异常事件是否会发生.与简单阈值算法和基于贝叶斯网络算法对比,实验结果表明该算法有高检测精度、低延迟率, 能大幅降低通信开销,提高响应速度.

关键词: 异常事件检测, 马尔可夫链, 贝叶斯网络, 时空事件, 连通支配集

Abstract: When the network abnormal event occurs, the spatial-temporal correlation of the sensor nodes is very obvious. While existing methods generally separate time and space data properties, a decentralized algorithm of spatial-temporal abnormal detection based on Probabilistic Graphical Model (PGM) was proposed. Firstly the Connected Dominating Set (CDS) algorithm was used to select part of the sensor nodes to avoid monitoring all the sensor nodes, and then Markov Chain (MC) was used to predict time exception event, at last Bayesian Network (BN) was utilized in modelling the spatial dependency of sensors, combining spatio-temporal events to predict whether the abnormal events would or would not occur. Compared with the simple threshold algorithm and BN algorithm, the experimental results demonstrate that the proposed algorithm has higher detection precision, and low delay rate, greatly reducing the communication overhead and improving the response speed.

Key words: abnormal event detection, Markov chain, Bayesian Network (BN), spatial-temporal event, Connected Dominating Set (CDS)

中图分类号: