TDOA-based localization via stochastic gradient descent variants

L.F. Abanto Leon, Arie G.C. Koppelaar, S.M. Heemstra de Groot

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

Uittreksel

Source localization is of pivotal importance in several areas such as wireless sensor networks and Internet of Things (IoT), where the location information can be used for a variety of purposes, e.g. surveillance, monitoring, tracking, etc. Time Difference of Arrival (TDOA) is one of the well-known localization approaches where the source broadcasts a signal and a number of receivers record the arriving time of the transmitted signal. By means of computing the time difference from various receivers, the source location can be estimated. On the other hand, in the recent few years novel optimization algorithms have appeared in the literature for $(i)$ processing big data and for $(ii)$ training deep neural networks. Most of these techniques are enhanced variants of the classical stochastic gradient descent (SGD) but with additional features that promote faster convergence. In this paper, we compare the performance of the classical SGD with the novel techniques mentioned above. In addition, we propose an optimization procedure called RMSProp+AF, which is based on RMSProp algorithm but with the advantage of incorporating adaptation of the decaying factor. We show through simulations that all of these techniques---which are commonly used in the machine learning domain---can also be successfully applied to signal processing problems and are capable of attaining improved convergence and stability. Finally, it is also shown through simulations that the proposed method can outperform other competing approaches as both its convergence and stability are superior.
TaalEngels
TitelIEEE 88th Vehicular Technology Conference
SubtitelVTC 2018-Fall
Plaats van productiePiscataway
UitgeverijInstitute of Electrical and Electronics Engineers (IEEE)
Aantal pagina's11
ISBN van elektronische versie9781538663585
DOI's
StatusGepubliceerd - 15 apr 2019
Evenement88th IEEE Vehicular Technology Conference, VTC-Fall 2018 - Chicago, Verenigde Staten van Amerika
Duur: 27 aug 201830 aug 2018
Congresnummer: 88
http://www.ieeevtc.org/vtc2018fall/

Congres

Congres88th IEEE Vehicular Technology Conference, VTC-Fall 2018
Verkorte titelVTC2018-Fall
LandVerenigde Staten van Amerika
StadChicago
Periode27/08/1830/08/18
Internet adres

Vingerafdruk

Learning systems
Wireless sensor networks
Signal processing
Monitoring
Processing
Time difference of arrival
Deep neural networks
Internet of things
Big data

Citeer dit

Abanto Leon, L. F., Koppelaar, A. G. C., & Heemstra de Groot, S. M. (2019). TDOA-based localization via stochastic gradient descent variants. In IEEE 88th Vehicular Technology Conference: VTC 2018-Fall [8690742] Piscataway: Institute of Electrical and Electronics Engineers (IEEE). DOI: 10.1109/VTCFall.2018.8690742
Abanto Leon, L.F. ; Koppelaar, Arie G.C. ; Heemstra de Groot, S.M./ TDOA-based localization via stochastic gradient descent variants. IEEE 88th Vehicular Technology Conference: VTC 2018-Fall. Piscataway : Institute of Electrical and Electronics Engineers (IEEE), 2019.
@inproceedings{01d1ba75e6cc4218b64402409cb3d857,
title = "TDOA-based localization via stochastic gradient descent variants",
abstract = "Source localization is of pivotal importance in several areas such as wireless sensor networks and Internet of Things (IoT), where the location information can be used for a variety of purposes, e.g. surveillance, monitoring, tracking, etc. Time Difference of Arrival (TDOA) is one of the well-known localization approaches where the source broadcasts a signal and a number of receivers record the arriving time of the transmitted signal. By means of computing the time difference from various receivers, the source location can be estimated. On the other hand, in the recent few years novel optimization algorithms have appeared in the literature for $(i)$ processing big data and for $(ii)$ training deep neural networks. Most of these techniques are enhanced variants of the classical stochastic gradient descent (SGD) but with additional features that promote faster convergence. In this paper, we compare the performance of the classical SGD with the novel techniques mentioned above. In addition, we propose an optimization procedure called RMSProp+AF, which is based on RMSProp algorithm but with the advantage of incorporating adaptation of the decaying factor. We show through simulations that all of these techniques---which are commonly used in the machine learning domain---can also be successfully applied to signal processing problems and are capable of attaining improved convergence and stability. Finally, it is also shown through simulations that the proposed method can outperform other competing approaches as both its convergence and stability are superior.",
author = "{Abanto Leon}, L.F. and Koppelaar, {Arie G.C.} and {Heemstra de Groot}, S.M.",
year = "2019",
month = "4",
day = "15",
doi = "10.1109/VTCFall.2018.8690742",
language = "English",
booktitle = "IEEE 88th Vehicular Technology Conference",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",
address = "United States",

}

Abanto Leon, LF, Koppelaar, AGC & Heemstra de Groot, SM 2019, TDOA-based localization via stochastic gradient descent variants. in IEEE 88th Vehicular Technology Conference: VTC 2018-Fall., 8690742, Institute of Electrical and Electronics Engineers (IEEE), Piscataway, Chicago, Verenigde Staten van Amerika, 27/08/18. DOI: 10.1109/VTCFall.2018.8690742

TDOA-based localization via stochastic gradient descent variants. / Abanto Leon, L.F.; Koppelaar, Arie G.C.; Heemstra de Groot, S.M.

IEEE 88th Vehicular Technology Conference: VTC 2018-Fall. Piscataway : Institute of Electrical and Electronics Engineers (IEEE), 2019. 8690742.

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

TY - GEN

T1 - TDOA-based localization via stochastic gradient descent variants

AU - Abanto Leon,L.F.

AU - Koppelaar,Arie G.C.

AU - Heemstra de Groot,S.M.

PY - 2019/4/15

Y1 - 2019/4/15

N2 - Source localization is of pivotal importance in several areas such as wireless sensor networks and Internet of Things (IoT), where the location information can be used for a variety of purposes, e.g. surveillance, monitoring, tracking, etc. Time Difference of Arrival (TDOA) is one of the well-known localization approaches where the source broadcasts a signal and a number of receivers record the arriving time of the transmitted signal. By means of computing the time difference from various receivers, the source location can be estimated. On the other hand, in the recent few years novel optimization algorithms have appeared in the literature for $(i)$ processing big data and for $(ii)$ training deep neural networks. Most of these techniques are enhanced variants of the classical stochastic gradient descent (SGD) but with additional features that promote faster convergence. In this paper, we compare the performance of the classical SGD with the novel techniques mentioned above. In addition, we propose an optimization procedure called RMSProp+AF, which is based on RMSProp algorithm but with the advantage of incorporating adaptation of the decaying factor. We show through simulations that all of these techniques---which are commonly used in the machine learning domain---can also be successfully applied to signal processing problems and are capable of attaining improved convergence and stability. Finally, it is also shown through simulations that the proposed method can outperform other competing approaches as both its convergence and stability are superior.

AB - Source localization is of pivotal importance in several areas such as wireless sensor networks and Internet of Things (IoT), where the location information can be used for a variety of purposes, e.g. surveillance, monitoring, tracking, etc. Time Difference of Arrival (TDOA) is one of the well-known localization approaches where the source broadcasts a signal and a number of receivers record the arriving time of the transmitted signal. By means of computing the time difference from various receivers, the source location can be estimated. On the other hand, in the recent few years novel optimization algorithms have appeared in the literature for $(i)$ processing big data and for $(ii)$ training deep neural networks. Most of these techniques are enhanced variants of the classical stochastic gradient descent (SGD) but with additional features that promote faster convergence. In this paper, we compare the performance of the classical SGD with the novel techniques mentioned above. In addition, we propose an optimization procedure called RMSProp+AF, which is based on RMSProp algorithm but with the advantage of incorporating adaptation of the decaying factor. We show through simulations that all of these techniques---which are commonly used in the machine learning domain---can also be successfully applied to signal processing problems and are capable of attaining improved convergence and stability. Finally, it is also shown through simulations that the proposed method can outperform other competing approaches as both its convergence and stability are superior.

UR - http://www.scopus.com/inward/record.url?scp=85064910908&partnerID=8YFLogxK

U2 - 10.1109/VTCFall.2018.8690742

DO - 10.1109/VTCFall.2018.8690742

M3 - Conference contribution

BT - IEEE 88th Vehicular Technology Conference

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway

ER -

Abanto Leon LF, Koppelaar AGC, Heemstra de Groot SM. TDOA-based localization via stochastic gradient descent variants. In IEEE 88th Vehicular Technology Conference: VTC 2018-Fall. Piscataway: Institute of Electrical and Electronics Engineers (IEEE). 2019. 8690742. Beschikbaar vanaf, DOI: 10.1109/VTCFall.2018.8690742