Deep Learning based Computer-vision for Enhanced Beamforming

Meeting the high data rate demands of modern applications necessitates the utilization of high-frequency spectrum bands, including millimeter-wave and sub-terahertz bands. However, these frequencies require precise alignment of narrow communication beams between transmitters and receivers, typically resulting in significant beam training overhead. This paper introduces a novel end-to-end vision-aided beamforming framework that utilizes images to predict optimal beams while considering geometric adjustments to reduce overhead. Our model demonstrates robust adaptability to dynamic environments without relying on additional training data where the experimental results indicate a top-5 beam prediction accuracy of 98.96%, significantly surpassing current state-of-the-art solutions in vision-aided beamforming.

Rician Channel Modelling for Super Wideband MIMO Communications

Recent developments in Multiple-Input-Multiple-Output (MIMO) technology include packing a large number of antenna elements in a compact array to access the bandwidth benefits provided by higher mutual coupling (MC). The resulting super-wideband (SW) systems require a circuit-theoretic framework to handle the MC and channel models which span extremely large bands. Hence, in this paper, we make two key contributions. First, we develop a physically-consistent Rician channel model for use with SW systems. Secondly, we express the circuit-theoretic models in terms of a standard MIMO model, so that insights into the effects of antenna layouts, MC, and bandwidth can be made using standard communication theory. For example, we show the bandwidth widening resulting from the new channel model. In addition, we show that MC distorts line-of-sight paths which has beamforming implications. We also highlight the interaction between spatial correlation and MC and show that tight coupling reduces spatial correlations at low frequencies.