Wireless Sensor Networks Fault Identification Using Data Association
T. Abirami Kongu, P. Thangaraj and P. Priakanth Kongu
DOI : 10.3844/jcssp.2012.1501.1505
Journal of Computer Science
Volume 8, Issue 9
Problem statement: Wireless Sensor Networks (WSN) are formed by thousands of lightweight nodes equipped with transducers for capturing information. The captured data are transmitted using multi hop routes to a base station, also called a sink. They can be extensively deployed during emergency response, medical monitoring and missiion critical applications requiring extensive data capture from sensors.Wireless sensor network applications include finding out patterns from what has been observed though advance knowledge of such patterns is usually unavailable. Sensor which collect data hand them over to the sink which is followed by offline data analyses to extract patterns. The existence of a large communication overhead affects sensor network performance negatively. Approach: This large overhead becomes a hurdle for the deployment of long term large scale sensor networks. Association mining to discover frequent patterns which form part of date mining and study of spatial and temporal properties is thus the subject of this study. As the association mining is applied in-network, Patterns and not the raw data streams are forwarded to the sink when association mining is applied to the network which thereby reduces communication overhead significantly. In this study, it is proposed to investigate the association of data received in the sink from various nodes across the network. Results and Conclusion: Simulations show associations based on the received traffic can be effectively used to identify mote failures and link failures.The proposed method at accuracy levels greater than 75% was able to identify all associations among the motes. The proposed method was able to find all associations among the deployed nodes.
© 2012 T. Abirami Kongu, P. Thangaraj and P. Priakanth Kongu. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.