English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we propose an intelligent analog beam selection strategy in aterahertz (THz) band beamspace multiple-input multiple-output (MIMO) system.First inspired by transfer learning, we fine-tune the pre-trained off-the-shelfGoogleNet classifier, to learn analog beam selection as a multi-class mappingproblem. Simulation results show 83% accuracy for the analog beam selection,which subsequently results in 12% spectral efficiency (SE) gain, upon theexisting counterparts. Towards a more accurate classifier, we replace theconventional rectified linear unit (ReLU) activation function of the GoogleNetwith the recently proposed Swish and retrain the fine-tuned GoogleNet to learnanalog beam selection. It is numerically indicated that the fine-tunedSwish-driven GoogleNet achieves 86% accuracy, as well as 18% improvement inachievable SE, upon the similar schemes. Eventually, a strong ensembledclassifier is developed to learn analog beam selection by sequentially trainingmultiple fine-tuned Swish-driven GoogleNet classifiers. According to thesimulations, the strong ensembled model is 90% accurate and yields 27% gain inachievable SE, in comparison with prior methods.

Swish-Driven GoogleNet for Intelligent Analog Beam Selection in Terahertz Beamspace MIMO