Cooperative Relay and Jammer Node Selection Strategies Based on Feed-Forward Neural Network

Citation

Salem, Mohammed Ahmed and Abd. Aziz, Azlan and Al-Selwi, Hatem Fahd and Alias, Mohamad Yusoff (2020) Cooperative Relay and Jammer Node Selection Strategies Based on Feed-Forward Neural Network. In: 2020 International Conference on Computing and Information Technology, 9-10 Sept. 2020, Saudi Arabia, Tabuk, Saudi Arabia.

[img] Text
100.pdf
Restricted to Repository staff only

Download (4MB)

Abstract

Cooperative non-orthogonal multi-access networking is a promising model for future wireless networks, due to its benefits in terms of energy efficiency, broader coverage and reducing interference. In this paper, under the presence of an eavesdropper node, we are researching the secrecy efficiency of a downlink cooperative non-orthogonal multi access (NOMA) communication system. This paper proposes a cooperative node based on deep learning feed forward neural network. The selected cooperative relay node is employed to enhance the channel capacity of the legal users, where the selected cooperative jammer is employed to degrade the capacity of the wiretapped channel. Simulations of the secrecy performance metric namely the secrecy capacity (Cs) are presented and compared with the conventional technique based on fuzzy logic node selection technique. Based on our simulations and discussions the proposed technique outperforms the existing technique in terms of the secrecy performance.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Neural networks (Computer science), Cooperative relay transmission, cooperative jammer transmission, feed forward neural networks (FFNN), secrecy capacity.
Subjects: Q Science > Q Science (General)
Divisions: Faculty of Engineering (FOE)
Faculty of Engineering and Technology (FET)
Depositing User: Ms Rosnani Abd Wahab
Date Deposited: 10 Sep 2021 14:49
Last Modified: 10 Sep 2021 14:50
URII: http://shdl.mmu.edu.my/id/eprint/8515

Downloads

Downloads per month over past year

View ItemEdit (login required)