Detecting Denial of Service Attack in Wireless Sensor Network Using Energy Efficient Extreme Learning Neural Network (EEELNN)
A. Venkatesh1, S. Asha2 

1A. Venkatesh, Department of School of Computing Science and Engineering, VIT University, Chennai, India.
2S. Asha, School of Department of Computing Science and Engineering, VIT University, Chennai, India.

Manuscript received on 11 March 2019 | Revised Manuscript received on 18 March 2019 | Manuscript published on 30 July 2019 | PP: 5913-5918 | Volume-8 Issue-2, July 2019 | Retrieval Number: B3533078219/19©BEIESP | DOI: 10.35940/ijrte.B3533.078219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: One of the effective communication technology is wireless sensor network technology which helps to monitor the surrounding information by sensed nodes. The effective utilization of sensed nodes is utilized in different applications such as military, health information, environmental monitoring, disaster relief and target analyze. The application requires the collection of information which may be collected from one location and transferred to the other location for making their process so easier. During the information transformation process, the network may affect by several intermediate attack, in which denial of service is one of the serious attack because it affects the entire network resources such as network energy, power, bandwidth. The unavailability of the resources reduces the entire sensor network performance. For managing the attack related issues, in this paper introduces the Energy Efficient Extreme Learning Neural Network (EEELNN) approach for overcoming the attack related issues. Initially the network transmitted zone is computed along with energy, power, bandwidth, neighboring node information and lifetime for eliminating the attack in sensor network. The computed information is processed and trained by extreme learning neural network that successfully predict the attack related data, node and network zone with effective manner that leads to improve the overall network performance. At last system efficiency is evaluated using simulation results such as detection rate, classification accuracy, false alarm rate and detection time.
Keywords: Wireless Sensor Network, Denial of Service, Energy Efficient Extreme Learning Neural Network (EEELNN) Approach, Detection Rate, Classification Accuracy, False Alarm Rate and Detection Time.

Scope of the Article: Classification