Mathematical models of CBSC over wireless channels and their analysis by using the LeNN-WOA-NM algorithm. (January 2022)

• Record Type: Journal Article
• Authors: Khan, Naveed Ahmad; Sulaiman, Muhammad; Aljohani, Abdulah Jeza; Bakar, Maharani A.; Miftahuddin,
• Is Part Of: Engineering applications of artificial intelligence. Volume 107(2022)
• Publication Date: 2022-01
• Subjects: Chaotic communications -- Wireless communication -- Chao's circuits -- Secure communication -- Chaotic synchronization -- System of ODE's -- Soft computing technique -- Mathematical modeling and analysis -- Optimization problems; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2021.104537
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: In recent studies, several chaos-based secure communication (CBSC) systems are developed and are assumed to be effective and promising tools for balancing communications in wireless applications. The reliability of a wireless communication system is dependent on the synchronization between receiving and transmitting nodes. Therefore, it is crucial to analyze the mathematical models for different enhancements through CBSC and avoid the difficulty in synchronization. We have designed a novel computational paradigm that uses weighted Legendre polynomials to construct series solutions for mathematical models of the Lorenz Chaotic Attractor (LCA) and Double Scroll Attractor (DSA) (with filter and without filter) by using Chua's circuits. We design fitness functions for each system of differential equations. Two optimization techniques, the Whale Optimization Algorithm (WOA) and the Nelder–Mead (NM) algorithm are adopted to optimize the objective functions and calculate the best set of unknown weights. We name our soft computing paradigm, the LeNN-WOA-NM algorithm. We have compared our results with state-of-the-art, and we establish that the LeNN-WOA-NM algorithm is fast, accurate, and reliable. We present graphical and statistical analysis to further elaborate on the performance of our algorithm.