Automatic Modulation Classification for Terahertz Communication

Abstract

The Terahertz band of frequencies offers a new frontier for research in wireless communication. With the availability of huge bandwidth, it offers the possibility of realizing the promised potential of 6G communication. An important capability the modern communication receivers are expected to possess is automatic modulation classification (AMC). In addition to its security and military applications, AMC improves spectral efficiency. It is also important in the context of cognitive radio. In this paper, a deep learning based approach is developed for the task of AMC in the Terahertz regime. Its performance is evaluated under different SNR conditions. The simulations demonstrate that the model developed provides excellent performance over the Terahertz channel.