학술논문

Radar Aided Active Prediction Based On Deep Learning
Document Type
Conference
Source
2023 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB) Broadband Multimedia Systems and Broadcasting (BMSB), 2023 IEEE International Symposium on. :1-5 Jun, 2023
Subject
Communication, Networking and Broadcast Technologies
Radar measurements
Wireless networks
Millimeter wave measurements
Switches
Millimeter wave radar
Predictive models
Reliability
mmWave
sub-THz
blockage prediction
DL
CNN
Transformer
Language
ISSN
2155-5052
Abstract
This paper proposes an application model of radar assisted active prediction in the Internet of Vehicles. A large-scale real world data set was obtained using the DeepSense framework to accurately evaluate the proposed solution. The data set collected more than 10000 data points and radar and millimeter wave communication measurement data of the coexistence of various blocking objects (vehicles, bicycles, humans, etc.). The simulations validate the effectiveness of the proposed scheme.