An Algorithm of mmWave MIMO Antenna Exposure Based on Unsupervised Deep Learning
Conference: ISCTT 2022 - 7th International Conference on Information Science, Computer Technology and Transportation
05/27/2022 - 05/29/2022 at Xishuangbanna, China
Proceedings: ISCTT 2022
Pages: 4Language: englishTyp: PDF
Authors:
Xu, Yang; Fu, Haitao; Liu, Yawen; Hui, Xiong (Hubei Medical Devices Quality Supervision and Test Institute, NMPA Key Lab. of Ultrasonic Surgical Equipment, Wuhan, China)
Abstract:
Millimeter wave Multiple-Input Multiple-Output (MIMO) antenna has been used in 5th generation mobile communication technology to provide a high-qualified service, which also brings new challenges to traditional radiation safety evaluation, especially for numerical radiation simulation. An unsupervised deep learning method is proposed to determine the limit of millimeter wave MIMO terminal antennas radiation accurately and efficiently, providing a new alternative of rapid radiation safety evaluation. We firstly prove the practicality of the proposed method, and then take an example of simulating exposure of different antenna arrays with working frequency 28 GHz in the target plane. In addition, the reliability of the proposed algorithm is compared with Monte Carlo method as a reference. The results show that the error of the maximum and mean power density distribution can be limited up to 0.07% between the two methods.