Computational & Technology Resources
an online resource for computational,
engineering & technology publications
PROCEEDINGS OF THE THIRD INTERNATIONAL CONFERENCE ON PARALLEL, DISTRIBUTED, GRID AND CLOUD COMPUTING FOR ENGINEERING
Scalable Event Detection in Wireless Sensor Networks using a Novel Content-Based Pattern Recognition Scheme
A.H. Basirat and A.I. Khan
Clayton School of IT, Monash University, Melbourne, Australia
A.H. Basirat, A.I. Khan, "Scalable Event Detection in Wireless Sensor Networks using a Novel Content-Based Pattern Recognition Scheme", in , (Editors), "Proceedings of the Third International Conference on Parallel, Distributed, Grid and Cloud Computing for Engineering", Civil-Comp Press, Stirlingshire, UK, Paper 53, 2013. doi:10.4203/ccp.101.53
Keywords: wireless sensor networks, associative computing, pattern recognition, single-cycle learning, neural network.
Event detection within wireless sensor networks would be a key technology for resource conservation and bolstering national security. This technology is also vital for pre-emptive measures against extreme events such as bushfires, flooding, and tornado activity. The associative-based event detection approach presented in this paper outlines a new type of wireless sensor network (WSN) by developing a level of computability within the network whereby sensor readings can be instantly translated into event patterns and then locally analysed by the network. This approach will entail two-fold benefit. On one hand it will enhance event detection e.g. surveillance, and target location capabilities but on the other hand it will aid in the development of advanced threat detection systems for WSN, e.g. networks that can function like our biological immune system. The challenge which is addressed here is to evolve an approach, which can successfully detect complex real life patterns arising from heterogeneous data sets (generated by different types of sensors) in real-time. For this matter, a one-shot content-based pattern matching model is developed to detect macroscopic events by collating diverse sensor data, locally and in real-time, into meaningful patterns while reducing complexity of the WSN infrastructure to increase its potential for wide-spread use. With this in mind, the aim of this research is to explore new ways in providing distributed event detection in WSNs by introducing a light-weight distributed pattern recognition scheme which provides single-cycle learning and entails a large number of loosely coupled parallel operations. The strength of this scheme lies in the processing of non-uniform data patterns as it implements a finely distributable framework at the smallest (atomic) logical sub-pattern level. The results are easily obtained by summation at the overall pattern level. Hence, the algorithm is able to provide a type of divide and distribute filtering process throughout the network in a fine grained manner for minimizing the energy use.
In order to achieve a scalable distributed event detection framework, a novel level of computability within the WSN is developed whereby sensor readings are instantly translated into patterns and then rapidly analysed by the network (locally). For this purpose, events of interest are correlated to specific pattern classes of our definition. Furthermore the asymptotic limits of the approach are carefully examined through developing a professionally-designed simulation environment to test the accuracy and effectiveness of the model when deployed in a dynamic WSN. Last but not least, the proposed approach in this paper not only enjoys from conserving the limited power resources of resource-constrained sensor nodes, but also can be scaled effectively to address scalability issues which are of primary concern in wireless sensor networks.
purchase the full-text of this paper (price £20)