Machine Learning-Assisted Detection for BPSK-modulated Ambient Backscatter Communication Systems

Xiyu Wang; Ruifeng Duan; Yusein Yigitler; Estifanos Menta; Riku Jäntti

doi:10.1109/GLOBECOM38437.2019.9013284

Machine Learning-Assisted Detection for BPSK-modulated Ambient Backscatter Communication Systems

Xiyu Wang, Ruifeng Duan, Yusein Yigitler, Estifanos Menta, Riku Jäntti

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

23 Downloads (Pure)

Abstract

Ambient backscatter communication (AmBC), a green communication technology, is hampered by the continuously and extremely fast varying, strong and unknown ambient radio frequency (RF) signals. This paper presents a machine learning-assisted method for extracting the information of the AmBC device. The information is modulated on top of the unknown Gaussian-distributed ambient RF signals. The proposed approach can decode the binary phase shift keying backscatter signals encoded using Hadamard codes. This method extracts the learnable features for the tag signal by first eliminating the
direct path signal and then correlating the residual signal with the coarse estimate of ambient signal. Thereafter, the tag signals are recovered by using the k-nearest neighbors classification algorithm. The recovered signals are decoded by a Hadamard decoder to retrieve the original information bits. We validate the performance using simulations to corroborate the proposed
approach.

Original language	English
Title of host publication	IEEE Global Communications Conference
Publisher	IEEE
Number of pages	6
ISBN (Electronic)	9781728109626
DOIs	https://doi.org/10.1109/GLOBECOM38437.2019.9013284
Publication status	Published - 2019
MoE publication type	A4 Article in a conference publication
Event	IEEE Global Communications Conference - Waikoloa, United States Duration: 9 Dec 2019 → 13 Dec 2019

Publication series

Name	IEEE Global Communications Conference
ISSN (Print)	2334-0983

Conference

Conference	IEEE Global Communications Conference
Abbreviated title	GLOBECOM
Country	United States
City	Waikoloa
Period	09/12/2019 → 13/12/2019

Keywords

Ambient backscatter
classification algorithm
green communication
machine learning
signal detection

Access to Document

10.1109/GLOBECOM38437.2019.9013284

ELEC_Wang_Machine_learning_GlobeComAccepted author manuscript, 481 KB

Fingerprint Dive into the research topics of 'Machine Learning-Assisted Detection for BPSK-modulated Ambient Backscatter Communication Systems'. Together they form a unique fingerprint.

Projects

1 Finished
1 Active

Adaptive ambient backscatter Communications for ultra-low power Systems

Menta, E., Jäntti, R., Badihi Olyaei, B., Wang, X., Sheikh, M. & Liljemark, A.

01/09/2018 → 31/08/2021

Project: Academy of Finland: Other research funding

AIMHIS: Collaborative Research: Ambient Re-Scatter inspired Machine Type Communications for Heterogeneous IoT Systems

Duan, R. & Jäntti, R.

12/04/2017 → 24/01/2020

Project: Academy of Finland: Other research funding

Cite this

Wang, X., Duan, R., Yigitler, Y., Menta, E., & Jäntti, R. (2019). Machine Learning-Assisted Detection for BPSK-modulated Ambient Backscatter Communication Systems. In IEEE Global Communications Conference [9013284] (IEEE Global Communications Conference). IEEE. https://doi.org/10.1109/GLOBECOM38437.2019.9013284

@inproceedings{9aea44e8791448d2ab40c9ab84d1e109,

title = "Machine Learning-Assisted Detection for BPSK-modulated Ambient Backscatter Communication Systems",

abstract = "Ambient backscatter communication (AmBC), a green communication technology, is hampered by the continuously and extremely fast varying, strong and unknown ambient radio frequency (RF) signals. This paper presents a machine learning-assisted method for extracting the information of the AmBC device. The information is modulated on top of the unknown Gaussian-distributed ambient RF signals. The proposed approach can decode the binary phase shift keying backscatter signals encoded using Hadamard codes. This method extracts the learnable features for the tag signal by first eliminating thedirect path signal and then correlating the residual signal with the coarse estimate of ambient signal. Thereafter, the tag signals are recovered by using the k-nearest neighbors classification algorithm. The recovered signals are decoded by a Hadamard decoder to retrieve the original information bits. We validate the performance using simulations to corroborate the proposedapproach.",

keywords = "Ambient backscatter, classification algorithm, green communication, machine learning, signal detection",

author = "Xiyu Wang and Ruifeng Duan and Yusein Yigitler and Estifanos Menta and Riku J{\"a}ntti",

year = "2019",

doi = "10.1109/GLOBECOM38437.2019.9013284",

language = "English",

series = "IEEE Global Communications Conference",

publisher = "IEEE",

booktitle = "IEEE Global Communications Conference",

address = "United States",

note = "IEEE Global Communications Conference, GLOBECOM ; Conference date: 09-12-2019 Through 13-12-2019",

}

Wang, X , Duan, R , Yigitler, Y , Menta, E & Jäntti, R 2019, Machine Learning-Assisted Detection for BPSK-modulated Ambient Backscatter Communication Systems. in IEEE Global Communications Conference., 9013284, IEEE Global Communications Conference, IEEE, IEEE Global Communications Conference, Waikoloa, United States, 09/12/2019. https://doi.org/10.1109/GLOBECOM38437.2019.9013284

Machine Learning-Assisted Detection for BPSK-modulated Ambient Backscatter Communication Systems. / Wang, Xiyu ; Duan, Ruifeng ; Yigitler, Yusein ; Menta, Estifanos ; Jäntti, Riku.

IEEE Global Communications Conference. IEEE, 2019. 9013284 (IEEE Global Communications Conference).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Machine Learning-Assisted Detection for BPSK-modulated Ambient Backscatter Communication Systems

AU - Wang, Xiyu

AU - Duan, Ruifeng

AU - Yigitler, Yusein

AU - Menta, Estifanos

AU - Jäntti, Riku

PY - 2019

Y1 - 2019

N2 - Ambient backscatter communication (AmBC), a green communication technology, is hampered by the continuously and extremely fast varying, strong and unknown ambient radio frequency (RF) signals. This paper presents a machine learning-assisted method for extracting the information of the AmBC device. The information is modulated on top of the unknown Gaussian-distributed ambient RF signals. The proposed approach can decode the binary phase shift keying backscatter signals encoded using Hadamard codes. This method extracts the learnable features for the tag signal by first eliminating thedirect path signal and then correlating the residual signal with the coarse estimate of ambient signal. Thereafter, the tag signals are recovered by using the k-nearest neighbors classification algorithm. The recovered signals are decoded by a Hadamard decoder to retrieve the original information bits. We validate the performance using simulations to corroborate the proposedapproach.

AB - Ambient backscatter communication (AmBC), a green communication technology, is hampered by the continuously and extremely fast varying, strong and unknown ambient radio frequency (RF) signals. This paper presents a machine learning-assisted method for extracting the information of the AmBC device. The information is modulated on top of the unknown Gaussian-distributed ambient RF signals. The proposed approach can decode the binary phase shift keying backscatter signals encoded using Hadamard codes. This method extracts the learnable features for the tag signal by first eliminating thedirect path signal and then correlating the residual signal with the coarse estimate of ambient signal. Thereafter, the tag signals are recovered by using the k-nearest neighbors classification algorithm. The recovered signals are decoded by a Hadamard decoder to retrieve the original information bits. We validate the performance using simulations to corroborate the proposedapproach.

KW - Ambient backscatter

KW - classification algorithm

KW - green communication

KW - machine learning

KW - signal detection

U2 - 10.1109/GLOBECOM38437.2019.9013284

DO - 10.1109/GLOBECOM38437.2019.9013284

M3 - Conference contribution

T3 - IEEE Global Communications Conference

BT - IEEE Global Communications Conference

PB - IEEE

T2 - IEEE Global Communications Conference

Y2 - 9 December 2019 through 13 December 2019

ER -