notesum.ai

Published at December 4

Deep Learning based Computer-vision for Enhanced Beamforming

cs.IT

eess.SP

math.IT

Released Date: December 4, 2024

Authors: Sachira Karunasena¹, Erfan Khordad¹, Thomas Drummond¹, Rajitha Senanayake¹

Aff.: ¹University of Melbourne

Arxiv: http://arxiv.org/pdf/2412.03073v1

Refer to caption

	Methodology	TX Identification Accuracy
	Methodology	$M$ =1	$M$ =3	$M$ =5
Scenario 3	Charan et al. [13]	98.43%	99.00%	99.48%
	Ours: TX Identification Method 1	99.65%	100.00%	100.00%
	Ours: TX Identification Method 2	96.52%	100.00%	100.00%
	Ablation study 1: RGB input	99.10%	100.00%	100.00%
	Ablation study 2: All zero mmWave channel	24.92%	25.61%	26.82%
Scenario 4	Charan et al. [13]	97.16%	98.48%	98.60%
	Ours: TX Identification Method 1	97.46%	99.64%	99.64%
	Ours: TX Identification Method 2	94.20%	99.64%	99.64%
	Ablation study 1: RGB input	98.91%	99.64%	99.64%
	Ablation study 2: All zero mmWave channel	22.89%	23.72%	24.45%