TY - JOUR
T1 - Data-driven Diversity Antenna Selection for MIMO Communication using Machine Learning
AU - Wu, Chien Hsiang
AU - Lai, Chin Feng
N1 - Funding Information:
This study is conducted under the ?New generation transport deep learning intelligent system Project? of the Institute for Information Industry which is subsidized by the Ministry of Economic Affairs of the Republic of China.
Publisher Copyright:
© 2022 Taiwan Academic Network Management Committee. All rights reserved.
PY - 2022
Y1 - 2022
N2 - With the popularity of wireless application environments, smart antenna technology has completely changed the communication system. In order to improve the quality of wireless transmission, smart antennas have been widely used in wireless devices. Wireless signal modeling and prediction machine learning gradually replaced the traditional smart antenna selection method in the antenna selection solution. This article utilizes mobile devices to adjust the diversity antenna pattern for test verification in a MIMO wireless communication environment. The proposed method manipulates signal parameters through error vector magnitude (EVM) and adds data-driven training data. The results show that the SVM and NN methods proposed in this paper are 10.5% and 14% higher than the traditional EVM calculation methods, respectively. Thereby, realize precise antenna adjustment of mobile devices and improving wireless transmission quality.
AB - With the popularity of wireless application environments, smart antenna technology has completely changed the communication system. In order to improve the quality of wireless transmission, smart antennas have been widely used in wireless devices. Wireless signal modeling and prediction machine learning gradually replaced the traditional smart antenna selection method in the antenna selection solution. This article utilizes mobile devices to adjust the diversity antenna pattern for test verification in a MIMO wireless communication environment. The proposed method manipulates signal parameters through error vector magnitude (EVM) and adds data-driven training data. The results show that the SVM and NN methods proposed in this paper are 10.5% and 14% higher than the traditional EVM calculation methods, respectively. Thereby, realize precise antenna adjustment of mobile devices and improving wireless transmission quality.
UR - http://www.scopus.com/inward/record.url?scp=85125834674&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85125834674&partnerID=8YFLogxK
M3 - Article
AN - SCOPUS:85125834674
VL - 23
SP - 1
EP - 9
JO - Journal of Internet Technology
JF - Journal of Internet Technology
SN - 1607-9264
IS - 1
ER -