Loading

Node Localization using Naive Bayes Classifier and Trilateral Algorithm
K. Madhumathi1, T. Suresh.2, R. Maruti3

1Ms. K. Madhumathi, Assistant Professor, Department of BCA, Anna Adarsh College for Women, Chennai,
2Dr.T.Suresh,, Associate Professor, Department of Computer Science and Engineering, Annamalai University, TN, India.
3Dr. R. Maruti, Professor, Ponnaiyah Ramajayam Institute of Science and Technology, Chennai.
Manuscript received on January 26, 2020. | Revised Manuscript received on February 05, 2020. | Manuscript published on February 30, 2020. | PP: 2467-2470 | Volume-9 Issue-3, February 2020. | Retrieval Number: C5604029320/2020©BEIESP | DOI: 10.35940/ijeat.C5604.029320
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Node localization is an important problem considered among the researchers in the area of Wireless Sensor Networks (WSN). The WSN is formed by a group of sensor nodes having limited energy and other resources that transfers data among each other or to a base station in an ad-hoc fashion. The estimation of the geo location (co-ordinates in the two-dimensional space) of the sensor nodes is essential for ensuring the QoS within the network. The different applications of WSN require varied level of accuracy in the estimation of the location of the sensor nodes. Different localization schemes are adopted in the literature for better estimation of the node location and each of them has both merits and demerits. This paper focuses on analyzing the different node localization mechanism used in the WSN and to identify various issues and challenges in the estimation of the node location. This paper also proposes an optimal approach with less computational effort and high accuracy in prediction based on trilateration algorithm and the RSSI (Received Signal Strength Indicator) values extracted from the target nodes antennas. The network is segmented in to different blocks of unequal size and the block number in which the node is present will be identified using the naive bayes classifier.
Keywords: RSSI, naive bayes classifier, trilateration, node localization, wireless sensor network