Author(s): Shikha Namdeo, Dr. Sadhna K. Mishra, Dr. Vineet Richhariya
Published in: International Journal of Engineering Research & Technology
License: This work is licensed under a Creative Commons Attribution 4.0 International License.
Volume/Issue: Vol. 3 - Issue 6 (June - 2014)
Security threat and routing holes in wireless scenario are more frequent than other networks. Lack of infrastructure and centralized monitoring using limited battery power are the crucial point. Attackers can easily launch an attack to consumed resources of wireless network such as battery power packet dropping attack in sensor network. In such exploiting condition an antagonist node may launch various attacks to disturb the communication in WSN. Amidst of such attacks packet dropping and modifier are the most prevailing attacks. In packet dropping attack compromising nods starts dropping each and every packet pass from him (node) or modify the packet before forwarding in a later attack. In wireless sensor network, there are so many challenges and issues as already been discussed and proposed. The main challenges are how to provide maximum lifetime to network and how to provide robustness to network. In sensor network, the energy is mainly consumed for three purposes: data transmission, signal processing, and hardware operation. In this article we have Propose a machine learning based mechanism to identify the routing holes on wireless sensor network. The concept lies on social behavior of the human society in which individual’s behavior is the benchmark to decide his authenticity in the network. Proposed system works on the concept of the anomaly detection due to unlabeled information produce by the sensor nodes. The overall objective of this research article is to identify packet dropper and modifier in wireless sensor network against the set of qualitative performance metrics.
Number of Citations for this article: Data not Available
7 Paper(s) Found related to your topic:
Publish your Ph.D/Master's Thesis Online