Generalized adaptive smoothing based neural network architecture for traffic state estimation

Chuhan Yang; Ambadipudi Sai Venkata Ramana; Saif Eddin Jabari

doi:10.1016/j.ifacol.2023.10.1502

Generalized adaptive smoothing based neural network architecture for traffic state estimation

Chuhan Yang, Ambadipudi Sai Venkata Ramana, Saif Eddin Jabari

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The adaptive smoothing method (ASM) is a standard data-driven technique used in traffic state estimation. The ASM has free parameters which, in practice, are chosen to be some generally acceptable values based on intuition. However, we note that the heuristically chosen values often result in un-physical predictions by the ASM. In this work, we propose a neural network based on the ASM which tunes those parameters automatically by learning from sparse data from road sensors. We refer to it as the adaptive smoothing neural network (ASNN). We also propose a modified ASNN (MASNN), which makes it a strong learner by using ensemble averaging. The ASNN and MASNN are trained and tested with two real-world datasets. Our experiments reveal that the ASNN and the MASNN outperform the conventional ASM.

Original language	English (US)
Title of host publication	IFAC-PapersOnLine
Editors	Hideaki Ishii, Yoshio Ebihara, Jun-ichi Imura, Masaki Yamakita
Publisher	Elsevier B.V.
Pages	3483-3490
Number of pages	8
Edition	2
ISBN (Electronic)	9781713872344
DOIs	https://doi.org/10.1016/j.ifacol.2023.10.1502
State	Published - Jul 1 2023
Event	22nd IFAC World Congress - Yokohama, Japan Duration: Jul 9 2023 → Jul 14 2023

Publication series

Name	IFAC-PapersOnLine
Number	2
Volume	56
ISSN (Electronic)	2405-8963

Conference

Conference	22nd IFAC World Congress
Country/Territory	Japan
City	Yokohama
Period	7/9/23 → 7/14/23

Keywords

Adaptive
Adaptive smoothing method
Ensemble learning
Intelligent Autonomous Vehicles
Learning Systems
Neural networks
Transportation Systems

ASJC Scopus subject areas

Control and Systems Engineering

Access to Document

10.1016/j.ifacol.2023.10.1502

Cite this

Generalized adaptive smoothing based neural network architecture for traffic state estimation. / Yang, Chuhan; Ramana, Ambadipudi Sai Venkata; Jabari, Saif Eddin.
IFAC-PapersOnLine. ed. / Hideaki Ishii; Yoshio Ebihara; Jun-ichi Imura; Masaki Yamakita. 2. ed. Elsevier B.V., 2023. p. 3483-3490 (IFAC-PapersOnLine; Vol. 56, No. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Yang, C, Ramana, ASV & Jabari, SE 2023, Generalized adaptive smoothing based neural network architecture for traffic state estimation. in H Ishii, Y Ebihara, J Imura & M Yamakita (eds), IFAC-PapersOnLine. 2 edn, IFAC-PapersOnLine, no. 2, vol. 56, Elsevier B.V., pp. 3483-3490, 22nd IFAC World Congress, Yokohama, Japan, 7/9/23. https://doi.org/10.1016/j.ifacol.2023.10.1502

@inproceedings{a2ae7ac651b24e8a898cde3afa339794,

title = "Generalized adaptive smoothing based neural network architecture for traffic state estimation",

abstract = "The adaptive smoothing method (ASM) is a standard data-driven technique used in traffic state estimation. The ASM has free parameters which, in practice, are chosen to be some generally acceptable values based on intuition. However, we note that the heuristically chosen values often result in un-physical predictions by the ASM. In this work, we propose a neural network based on the ASM which tunes those parameters automatically by learning from sparse data from road sensors. We refer to it as the adaptive smoothing neural network (ASNN). We also propose a modified ASNN (MASNN), which makes it a strong learner by using ensemble averaging. The ASNN and MASNN are trained and tested with two real-world datasets. Our experiments reveal that the ASNN and the MASNN outperform the conventional ASM.",

keywords = "Adaptive, Adaptive smoothing method, Ensemble learning, Intelligent Autonomous Vehicles, Learning Systems, Neural networks, Transportation Systems",

author = "Chuhan Yang and Ramana, {Ambadipudi Sai Venkata} and Jabari, {Saif Eddin}",

note = "Publisher Copyright: Copyright {\textcopyright} 2023 The Authors. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/); 22nd IFAC World Congress ; Conference date: 09-07-2023 Through 14-07-2023",

year = "2023",

month = jul,

day = "1",

doi = "10.1016/j.ifacol.2023.10.1502",

language = "English (US)",

series = "IFAC-PapersOnLine",

publisher = "Elsevier B.V.",

number = "2",

pages = "3483--3490",

editor = "Hideaki Ishii and Yoshio Ebihara and Jun-ichi Imura and Masaki Yamakita",

booktitle = "IFAC-PapersOnLine",

edition = "2",

}

TY - GEN

T1 - Generalized adaptive smoothing based neural network architecture for traffic state estimation

AU - Yang, Chuhan

AU - Ramana, Ambadipudi Sai Venkata

AU - Jabari, Saif Eddin

PY - 2023/7/1

Y1 - 2023/7/1

N2 - The adaptive smoothing method (ASM) is a standard data-driven technique used in traffic state estimation. The ASM has free parameters which, in practice, are chosen to be some generally acceptable values based on intuition. However, we note that the heuristically chosen values often result in un-physical predictions by the ASM. In this work, we propose a neural network based on the ASM which tunes those parameters automatically by learning from sparse data from road sensors. We refer to it as the adaptive smoothing neural network (ASNN). We also propose a modified ASNN (MASNN), which makes it a strong learner by using ensemble averaging. The ASNN and MASNN are trained and tested with two real-world datasets. Our experiments reveal that the ASNN and the MASNN outperform the conventional ASM.

AB - The adaptive smoothing method (ASM) is a standard data-driven technique used in traffic state estimation. The ASM has free parameters which, in practice, are chosen to be some generally acceptable values based on intuition. However, we note that the heuristically chosen values often result in un-physical predictions by the ASM. In this work, we propose a neural network based on the ASM which tunes those parameters automatically by learning from sparse data from road sensors. We refer to it as the adaptive smoothing neural network (ASNN). We also propose a modified ASNN (MASNN), which makes it a strong learner by using ensemble averaging. The ASNN and MASNN are trained and tested with two real-world datasets. Our experiments reveal that the ASNN and the MASNN outperform the conventional ASM.

KW - Adaptive

KW - Adaptive smoothing method

KW - Ensemble learning

KW - Intelligent Autonomous Vehicles

KW - Learning Systems

KW - Neural networks

KW - Transportation Systems

UR - http://www.scopus.com/inward/record.url?scp=85182162539&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85182162539&partnerID=8YFLogxK

U2 - 10.1016/j.ifacol.2023.10.1502

DO - 10.1016/j.ifacol.2023.10.1502

M3 - Conference contribution

AN - SCOPUS:85182162539

T3 - IFAC-PapersOnLine

SP - 3483

EP - 3490

BT - IFAC-PapersOnLine

A2 - Ishii, Hideaki

A2 - Ebihara, Yoshio

A2 - Imura, Jun-ichi

A2 - Yamakita, Masaki

PB - Elsevier B.V.

T2 - 22nd IFAC World Congress

Y2 - 9 July 2023 through 14 July 2023

ER -

Generalized adaptive smoothing based neural network architecture for traffic state estimation

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this