Implementing Chaotic and Synchronization Properties of Logistic Maps Using Artificial Neural Networks for Code Generation

Logistic maps, usually preferred for chaotic sequence generation, provide certain challenges while implementing for real applications. Specifically, while considered for applications as a coder or spread factor generators in wireless communication, certain modular and simplified approaches are necessary to mitigate effects of complex designs. The chaotic nature of logistic maps has been exploited for code generation and has been preferred for spread factor generation as part of spread spectrum modulation (SSM). In this paper, we describe an approach of using certain modular designs for reducing the complexities of a logic map coder and spread factor generator, specially the computational load, while implemented using artificial neural networks (ANNs). The learning ability of the ANN is used to track the chaotic and synchronization properties of logistic map and used as an aid to SSM in a wireless setup.