Multi‐input fully CNN for joint pilot decontamination and symbol detection in 5G massive MIMO
Abstract This paper presents a multi‐input deep learning‐based joint pilot decontamination and symbol detection (SD) technique for 5G massive multiple‐input multiple‐output (MAMIMO) systems. It consists of a fully convolutional neural network (FCNN) that finds the 5G channel coefficients using pre‐k...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-10-01
|
| Series: | IET Communications |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cmu2.12670 |
| _version_ | 1797667657160327168 |
|---|---|
| author | Crallet M. Victor Alloys N. Mvuma Salehe I. Mrutu |
| author_facet | Crallet M. Victor Alloys N. Mvuma Salehe I. Mrutu |
| author_sort | Crallet M. Victor |
| collection | DOAJ |
| description | Abstract This paper presents a multi‐input deep learning‐based joint pilot decontamination and symbol detection (SD) technique for 5G massive multiple‐input multiple‐output (MAMIMO) systems. It consists of a fully convolutional neural network (FCNN) that finds the 5G channel coefficients using pre‐known sounding reference signals (SRSs) under pilot contamination and a symbol detector derived from projected gradient descent iterations. The study considers pilot contamination caused by inter‐cell interferences between SRSs during channel estimation (CE). The proposed scheme accepts entire 5G orthogonal frequency modulated (OFDM) data and least square estimates and produces the transmitted OFDM signal. Simulation experiments demonstrated that the proposed technique has better CE and SD performance with reduced trainable parameters. Moreover, it is faster due to the lowest elapsed time during end‐to‐end OFDM symbol detection. This paper proposes a joint pilot decontamination and signal detection for 5G MAMIMO systems. It achieves better detection performance with the lowest number of trainable parameters and memory requirements. It is applicable in 5G OFDM symbol detection and channel estimation under pilot contamination. |
| first_indexed | 2024-03-11T20:17:28Z |
| format | Article |
| id | doaj.art-9752059c9e3f4c9f89a35cf18a593700 |
| institution | Directory Open Access Journal |
| issn | 1751-8628 1751-8636 |
| language | English |
| last_indexed | 2024-03-11T20:17:28Z |
| publishDate | 2023-10-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Communications |
| spelling | doaj.art-9752059c9e3f4c9f89a35cf18a5937002023-10-03T10:55:37ZengWileyIET Communications1751-86281751-86362023-10-0117161899190610.1049/cmu2.12670Multi‐input fully CNN for joint pilot decontamination and symbol detection in 5G massive MIMOCrallet M. Victor0Alloys N. Mvuma1Salehe I. Mrutu2College of Informatics and Virtual EducationUniversity of DodomaDodomaTanzaniaCollege of Information and Communication TechnologyMbeya University of Science and TechnologyMbeyaTanzaniaCollege of Informatics and Virtual EducationUniversity of DodomaDodomaTanzaniaAbstract This paper presents a multi‐input deep learning‐based joint pilot decontamination and symbol detection (SD) technique for 5G massive multiple‐input multiple‐output (MAMIMO) systems. It consists of a fully convolutional neural network (FCNN) that finds the 5G channel coefficients using pre‐known sounding reference signals (SRSs) under pilot contamination and a symbol detector derived from projected gradient descent iterations. The study considers pilot contamination caused by inter‐cell interferences between SRSs during channel estimation (CE). The proposed scheme accepts entire 5G orthogonal frequency modulated (OFDM) data and least square estimates and produces the transmitted OFDM signal. Simulation experiments demonstrated that the proposed technique has better CE and SD performance with reduced trainable parameters. Moreover, it is faster due to the lowest elapsed time during end‐to‐end OFDM symbol detection. This paper proposes a joint pilot decontamination and signal detection for 5G MAMIMO systems. It achieves better detection performance with the lowest number of trainable parameters and memory requirements. It is applicable in 5G OFDM symbol detection and channel estimation under pilot contamination.https://doi.org/10.1049/cmu2.126705G massive MIMOchannel estimationfully convolutional neural networksmulti‐input deep neural networkspilot contaminationsymbol detection |
| spellingShingle | Crallet M. Victor Alloys N. Mvuma Salehe I. Mrutu Multi‐input fully CNN for joint pilot decontamination and symbol detection in 5G massive MIMO IET Communications 5G massive MIMO channel estimation fully convolutional neural networks multi‐input deep neural networks pilot contamination symbol detection |
| title | Multi‐input fully CNN for joint pilot decontamination and symbol detection in 5G massive MIMO |
| title_full | Multi‐input fully CNN for joint pilot decontamination and symbol detection in 5G massive MIMO |
| title_fullStr | Multi‐input fully CNN for joint pilot decontamination and symbol detection in 5G massive MIMO |
| title_full_unstemmed | Multi‐input fully CNN for joint pilot decontamination and symbol detection in 5G massive MIMO |
| title_short | Multi‐input fully CNN for joint pilot decontamination and symbol detection in 5G massive MIMO |
| title_sort | multi input fully cnn for joint pilot decontamination and symbol detection in 5g massive mimo |
| topic | 5G massive MIMO channel estimation fully convolutional neural networks multi‐input deep neural networks pilot contamination symbol detection |
| url | https://doi.org/10.1049/cmu2.12670 |
| work_keys_str_mv | AT cralletmvictor multiinputfullycnnforjointpilotdecontaminationandsymboldetectionin5gmassivemimo AT alloysnmvuma multiinputfullycnnforjointpilotdecontaminationandsymboldetectionin5gmassivemimo AT saleheimrutu multiinputfullycnnforjointpilotdecontaminationandsymboldetectionin5gmassivemimo |