Today’s Electronic Warfare (EW) receivers need advanced technology to achieve real-time surveillance operations. Dynamic and intelligent systems are required for UAVs and other airborne applications. The airborne Electronic Warfare systems must be knowledge-based systems, learning from the threat scenario with highly integrated capabilities to detect, react, and adapt to radar threats in real-time. Artificial intelligence is a machine-dependent process, by adapting certain rules and logic supported by human intelligence, AI can be used for cognitive processing. Cognitive signal processing is required for making the system autonomous and dynamic in nature. Military action on radar signatures requires a set of commands to be executed dynamically with the help of the proposed EW system. It is proposed to design and develop a cognitive EW architecture and simulation of machine learning that combines neural network architecture with the help of sine and square waves as input. This paper presents the Cognitive signal processing for EW systems with Neural Network, Recurrent Neural Network (RNN), Machine learning (ML), and Deep learning (DL) techniques with their simulation with sine and square waves.
Read full abstract