Priority Sensitive Event Detection in Hybrid Wireless Sensor Networks

Traditionally, event centric Wireless Sensor Network (WSN) applications treat all events with equal importance, implicitly assuming that all events have same priority. However, in real world applications events may have different level of severity and sensitivity based on their cost of potential damage, occurrence location and frequency. Such applications demand that a detection scheme adopt differentiated treatment of events considering above criteria. Recent works proposed multi-modal sensor nodes for detection of different types of event in a single sensor network and mobile nodes for on-demand attendance of events. When a multi- modal WSN is deployed to monitor events of varied priority, major challenges lies to allocate resources and mobilize mobile nodes in an optimized way to maximize detection performance. We introduce the concept of varied priority and cost of mis-detection of events, and propose a detection scheme for multiple simultaneous events in a hybrid sensor network. Mobile nodes are mobilized through formulation of an optimization problem that maximizes the prioritized accuracy while minimizing detection delay. Theoretical and simulation results demonstrate that our scheme significantly outperforms other scheme that treats all events equally.

[1]  Manuela M. Veloso,et al.  Mobile robot task allocation in hybrid wireless sensor networks , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  Sajal K. Das,et al.  Mission-Oriented k-Coverage in Mobile Wireless Sensor Networks , 2010, ICDCN.

[3]  Dharma P. Agrawal,et al.  Fault tolerant multiple event detection in a wireless sensor network , 2008, J. Parallel Distributed Comput..

[4]  Dyi-Rong Duh,et al.  Fault-tolerant decision fusion via collaborative sensor fault detection in wireless sensor networks , 2008, IEEE Transactions on Wireless Communications.

[5]  Parameswaran Ramanathan,et al.  Fault tolerance in collaborative sensor networks for target detection , 2004, IEEE Transactions on Computers.

[6]  Mounir Ghogho,et al.  A probabilistic model of k-coverage in minimum cost wireless sensor networks , 2008, CoNEXT '08.

[7]  Kevin Yoon,et al.  ScoutNode: A Multimodal Sensor Node for Wide Area Sensor Networks , 2009, 2009 Proceedings of 18th International Conference on Computer Communications and Networks.

[8]  Dragos D. Margineantu,et al.  Class Probability Estimation and Cost-Sensitive Classification Decisions , 2002, ECML.

[9]  G.E. Whitehouse,et al.  Meta-RaPS approach for solving the resource allocation problem , 2002, Proceedings of the 5th Biannual World Automation Congress.

[10]  Guanghui Lan,et al.  An effective and simple heuristic for the set covering problem , 2007, Eur. J. Oper. Res..

[11]  Harald Haas,et al.  The Distribution of Path Losses for Uniformly Distributed Nodes in a Circle , 2008, J. Electr. Comput. Eng..

[12]  Christian Bettstetter,et al.  An inhomogeneous spatial node distribution and its stochastic properties , 2007, MSWiM '07.

[13]  Youxian Sun,et al.  Wireless sensor networks solutions for real time monitoring of nuclear power plant , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

[14]  Yue Jiang,et al.  Misclassification cost-sensitive fault prediction models , 2009, PROMISE '09.

[15]  Donald F. Towsley,et al.  Mobility improves coverage of sensor networks , 2005, MobiHoc '05.

[16]  Pramod K. Varshney,et al.  Distributed Detection and Data Fusion , 1996 .

[17]  H. Thompson Distribution of Distance to Nth Neighbour in a Population of Randomly Distributed Individuals , 1956 .

[18]  Joarder Kamruzzaman,et al.  QoS Support in Event Detection in WSN through Optimal k-Coverage , 2011, ICCS.