Spatial Signal Design for Positioning via End-to-End Learning

被引：1

作者：

Rivetti, Steven ^{[1
]}

Miguel Mateos-Ramos, Jose ^{[1
]}

Wu, Yibo ^{[1
,2
]}

Song, Jinxiang ^{[1
]}

Keskin, Musa Furkan ^{[1
]}

Yajnanarayana, Vijaya ^{[3
]}

Hager, Christian ^{[1
]}

Wymeersch, Henk ^{[1
]}

机构：

[1] Chalmers Univ Technol, Dept Elect Engn, S-41258 Gothenburg, Sweden

[2] Ericsson Res, Ericsson AB, S-41756 Stockholm, Sweden

[3] Ericsson Res, Bengaluru 560048, India

来源：

IEEE WIRELESS COMMUNICATIONS LETTERS | 2023年 / 12卷 / 03期

基金：

瑞典研究理事会;

关键词：

Estimation; Artificial neural networks; Signal design; MISO communication; Benchmark testing; Wireless communication; Uncertainty; mmWave positioning; precoder optimization; end-to-end learning; WAVE-FORM;

D O I：

10.1109/LWC.2022.3233475

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This letter considers the problem of end-to-end (E2E) learning for joint optimization of transmitter precoding and receiver processing for mmWave downlink positioning. Considering a multiple-input single-output (MISO) scenario, we propose a novel autoencoder (AE) architecture to estimate user equipment (UE) position with multiple base stations (BSs) and demonstrate that E2E learning can match model-based design, both for angle-of-departure (AoD) and position estimation, under ideal conditions without model deficits and outperform it in the presence of hardware impairments.

引用

页码：525 / 529

页数：5

共 50 条

[41] Amharic OCR: An End-to-End Learning
Belay, Birhanu
Habtegebrial, Tewodros
Meshesha, Million
Liwicki, Marcus
Belay, Gebeyehu
Stricker, Didier
[J]. APPLIED SCIENCES-BASEL, 2020, 10 (03):
[42] END-TO-END LEARNING OF COMPRESSIBLE FEATURES
Singh, Saurabh
Abu-El-Haija, Sami
Johnston, Nick
Balle, Johannes
Shrivastava, Abhinav
Toderici, George
[J]. 2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2020, : 3349 - 3353
[43] End-to-end design of ingestible electronics
Angsagan Abdigazy
Mohammed Arfan
Gianluca Lazzi
Constantine Sideris
Alex Abramson
Yasser Khan
[J]. Nature Electronics, 2024, 7 : 102 - 118
[44] End-to-end design of wearable sensors
Ates, H. Ceren
Nguyen, Peter Q.
Gonzalez-Macia, Laura
Morales-Narvaez, Eden
Guder, Firat
Collins, James J.
Dincer, Can
[J]. NATURE REVIEWS MATERIALS, 2022, 7 (11) : 887 - 907
[45] End-to-end design of ingestible electronics
Abdigazy, Angsagan
Arfan, Mohammed
Lazzi, Gianluca
Sideris, Constantine
Abramson, Alex
Khan, Yasser
[J]. NATURE ELECTRONICS, 2024, 7 (02) : 102 - 118
[46] End-to-end integration testing design
Tsai, WT
Bai, XY
Paul, R
Shao, WG
Agarwal, V
[J]. 25TH ANNUAL INTERNATIONAL COMPUTER SOFTWARE & APPLICATIONS CONFERENCE, 2001, : 166 - 171
[47] End-to-end design of wearable sensors
H. Ceren Ates
Peter Q. Nguyen
Laura Gonzalez-Macia
Eden Morales-Narváez
Firat Güder
James J. Collins
Can Dincer
[J]. Nature Reviews Materials, 2022, 7 : 887 - 907
[48] End-to-end Drive Design and Simulation
Brecher, C.
Oezdemir, D.
Herfs, W.
[J]. AUTOMATION 2011, 2011, 213 : 79 - 82
[49] Bias Reduction via End-to-End Shift Learning: Application to Citizen Science
Chen, Di
Gomes, Carla P.
[J]. THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 493 - 500
[50] END-TO-END CROWD COUNTING VIA JOINT LEARNING LOCAL AND GLOBAL COUNT
Shang, Chong
Ai, Haizhou
Bai, Bo
[J]. 2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2016, : 1215 - 1219

← 1 2 3 4 5 →