Please use this identifier to cite or link to this item:
https://hdl.handle.net/11499/52026
Title: | Machine Learning Supported Nano-Router Localization in Wnsns | Authors: | Gulec, O. | Keywords: | Iont Machine Learning Nano-Router Localization Wireless Nano-Sensor Networks |
Publisher: | Sakarya University | Abstract: | Sensing data from the environment is a basic process for the nano-sensors on the network. This sensitive data need to be transmitted to the base station for data processing. In Wireless Nano-Sensor Networks (WNSNs), nano-routers undertake the task of gathering data from the nanosensors and transmitting it to the nano-gateways. When the number of nano-routers is not enough on the network, the data need to be transmitted by multi-hop routing. Therefore, there should be more nano-routers placed on the network for efficient direct data transmission to avoid multi-hop routing problems such as high energy consumption and network traffic. In this paper, a machine learning-supported nano-router localization algorithm for WNSNs is proposed. The algorithm aims to predict the number of required nano-routers depending on the network size for the maximum node coverage in order to ensure direct data transmission by estimating the best virtual coordinates of these nano-routers. According to the results, the proposed algorithm successfully places required nano-routers to the best virtual coordinates on the network which increases the node coverage by up to 98.03% on average and provides high accuracy for efficient direct data transmission. © 2023, Sakarya University. All rights reserved. | URI: | https://doi.org/10.16984/saufenbilder.1246617 | ISSN: | 1301-4048 |
Appears in Collections: | İktisadi ve İdari Bilimler Fakültesi Koleksiyonu Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection TR Dizin İndeksli Yayınlar Koleksiyonu / TR Dizin Indexed Publications Collection |
Files in This Item:
File | Size | Format | |
---|---|---|---|
document (43).pdf | 2.04 MB | Adobe PDF | View/Open |
CORE Recommender
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.