SPIS: Signal Processing for Integrated Sensing Technologies Using 6G Networks with Machine Learning Algorithms

Abstract

The proliferation of integrated sensing techniques in Sixth Generation (6G) networks is an increasingly significant aspect in facilitating efficient end-to-end communication for all users. The suggested methodology employs a digital signal processed with terahertz bandwidth to assess the impact of 6G networks. The primary focus lies in the design of 6G networks, emphasizing key parameters such interference, loss, signal strength, signal-to-noise ratio, and dual band channels. The aforementioned factors are combined with two machine learning algorithms in order to determine the extent of spectrum sharing among all available resources. Thus suggested approach for detecting signals in the terahertz communication spectrum is evaluated using 10 devices across four situations, which involve interference, signal loss, strength, and time margins for integrated sensing. Also the assumptions are based on signal processing devices operating within millimeter waves ranging from 5 to 10 terahertz. Interference and losses in the specified spectrum are seen to be less than 1%, but the time margin for integrated sensing with 99% maximized signal intensity remains at 85%.