Performance of SVM technique for DoA Estimation in 5G mm-Wave band

  • Youmni Ziade Electrical and Computer Engineering, Beirut Arab University, Tripoli, Lebanon.
  • Wissam Obeid Department of Telecommunication, CentraleSupelec, Paris Saclay University, Gif-Sur-Yvette, France.
DOI: https://doi.org/10.36909/jer.12013

Abstract

     Machine learning has been widely used in binary and multiclass problems for various applications. Application of ML algorithms in wireless communication has shown increasing interest, due to the increase of demand on capacity, the increase of the number of users, and equipment sharing the limited frequency spectrum resources. Also, the need for a reduction in power consumption at base stations and the optimization of radio coverage make ML an attractive and promising technique. Methods aiming to an intelligent and optimized use of the limited resources are necessary to fill these needs. In this paper, we investigate the usage of artificial intelligence, and in particular the Support Vector Machine (SVM) technique for DoA estimation in the millimeter-wave band. The objective, in the context of this paper, is to predict the location of a user in a given area by analyzing the received signals at an array of antennas, using an SVM-based model. The first phase of this technique consists of the training phase that aims to identify the characteristics of each class, and that is based on a set of training samples. The second phase consists of testing the trained model using a set of samples/users. We have carried out a set of simulations based on the developed model. We have considered different configurations where we have varied the training samples set, the antennas array, the width of the zone of the user location. The results are promising in terms of the accuracy of determining the DoA, taking into consideration a channel with noise and multipath. Also, the use of an antenna array with an inter-element spacing of around half-wavelength gives better performance, and the increase in the number of elements of the array enhances the prediction accuracy of the system.

Author Biographies

Youmni Ziade, Electrical and Computer Engineering, Beirut Arab University, Tripoli, Lebanon.

Youmni Ziadé was born in Tripoli, Lebanon, in 1980. He received a Diploma in Computer and
Communications Engineering from the Lebanese University, Tripoli, Lebanon, in 2002, an M.S.
(DEA) degree in Communications and Radar from the University of Rennes 1, Rennes, France,
in 2003, and a Ph.D. degree from the University of Paris 6, Paris, France, in 2006. From 2003 to
2006, he was a research assistant in the “Laboratoire des Signaux et Systèmes” at SUPELEC
France and worked on the modeling of electromagnetic propagation in complex media for radar
applications. Between March 2007 and August 2008, he worked as a postdoctoral fellow at
Orange Labs, Paris, France on the application of time reversal technique in communications
systems. Between 2008 and 2012, he was an R&D engineer at MobiNetS – Lebanon and was
working on the design, optimization, and development of mobile networks planning tools for
different worldwide telecom operators. Since 2012, he has been an assistant professor at the
Electrical and Computer Engineering Department at Beirut Arab University. His research
interest includes the modeling of electromagnetic propagation in complex media with
applications from radar and targets detection and localization, to radio coverage calculation and
optimization and the study of the performance of wireless networks. Dr. Ziade is an IEEE
member and he is the treasurer of the IEEE Lebanon Section since September 2019 and the
counselor of the Beirut Arab University IEEE Student Branch.

Wissam Obeid, Department of Telecommunication, CentraleSupelec, Paris Saclay University, Gif-Sur-Yvette, France.

Wissam Obeid was born in Ain El Tina, Lebanon, in 1998. He received a Bachelor of Engineering degree in
Communications and Electronics Engineering from Beirut Arab University, Lebanon, in June 2020, and a
Master’s degree in Advanced Wireless Communication Systems from CentraleSupélec - Paris-Saclay
University, Gif-Sur-Yvette, France, in November 2021. From April 2021 to August 2021, he followed a
research internship at Nokia Bell Labs, Nozay, France., where he worked on the application of deep learning
and machine learning for the physical layer in beyond 5G communication systems. Between June 2019 and
August 2019, he followed two professional internships. The first one was in the IT and networking
department at Middle East Airlines, Lebanon. The second one was in the radio access network at TOUCH,
one of the leading mobile operators in Lebanon. His research of interest is in the domain of machine learning
and its applications in the enhancement of wireless and cellular communication systems. Mr. Obeid is an
IEEE member since 2018 and he was the chairperson of the IEEE student branch at Beirut Arab University-
Tripoli campus from July 2018 to February 2020. He won the third prize in Theemar Business Idea
Competition in June 2018. Also, he won the most active ambassador award in the Students and Young
Professional Lebanese Congress 19 (SYPLC’19) in March 2019.

Published
2021-12-22
Issue
Online First Articles
Section
Computer Engineering