Online event detection based on the spatio-temporal analysis in the river sensor networks

Events detection with the spatio-temporal correlation is one of the most popular applications in the wireless sensor networks. In general, the existing approaches separate time and space data properties and cannot combine abnormal characteristics of the global network to make a unified spatial-temporal detection. In this paper, a decentralized algorithm based on probabilistic graphical models (PGMs) of spatial-temporal detection was proposed to detect abnormal event with spatio-temporal correlation. Firstly we utilize the connected dominating set (CDS) algorithm to select backbone nodes to avoid collecting a large amount of sensory data from all the sensor nodes. Then, adopting Markov chains to model the temporal dependency among the different sensor nodes, and Bayesian Network was applied to model the spatial dependency of sensors. Based on the analysis of the spatio-temporal data correlation, the wireless sensor network can predict the abnormal events occurrence. In the paper, the online event detection with spatio-temporal correlation is applied in the river sensor networks. The extensive experimental results demonstrated that the proposed algorithm can achieve better performance than the simple thresholds algorithm and Bayesian Network based algorithm in the terms of the detection precision, data transmission delay, scalability and response speed.

[1]  Hejun Wu,et al.  Pattern-based event detection in sensor networks , 2011, Distributed and Parallel Databases.

[2]  Shiwei Tang,et al.  Online Detecting Spreading Events with the Spatio-temporal Relationship in Water Distribution Networks , 2013, ADMA.

[3]  Samuel Karlin,et al.  A First Course on Stochastic Processes , 1968 .

[4]  D. G. Eliadesa,et al.  Contamination Event Detection in Water Distribution Systems Using a Model-based Approach , 2015 .

[5]  Yoon-Hwa Choi,et al.  Fault-Tolerant Event Detection Using Two Thresholds in Wireless Sensor Networks , 2009, 2009 15th IEEE Pacific Rim International Symposium on Dependable Computing.

[6]  J. Kingman A FIRST COURSE IN STOCHASTIC PROCESSES , 1967 .

[7]  Nachiketa Tarasia,et al.  A distributed connected dominating set using adjustable sensing range , 2014, 2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies.

[8]  Oliver Obst,et al.  Spatiotemporal Anomaly Detection in Gas Monitoring Sensor Networks , 2008, EWSN.

[9]  Ole J. Mengshoel,et al.  Computing Probabilistic Optical Flow Using Markov Random Fields , 2014, CompIMAGE.

[10]  Jie Wu,et al.  An extended localized algorithm for connected dominating set formation in ad hoc wireless networks , 2004, IEEE Transactions on Parallel and Distributed Systems.

[11]  Irfana Memon,et al.  Event Detection Using Wireless Sensor Networks , 2015 .

[12]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[13]  Milica Stojanovic,et al.  Underwater sensor networks: applications, advances and challenges , 2012, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.