Double Branch Model Based on Discrete Wavelet Transform for Spatiotemporal Prediction

Yingjie Cui; Zhenyu Lu; Le Sun; Byeungwoo Jeon

doi:10.1109/ICCSS58421.2023.10270114

Double Branch Model Based on Discrete Wavelet Transform for Spatiotemporal Prediction

Yingjie Cui
, Zhenyu Lu
, Le Sun
, Byeungwoo Jeon

Department of Electronic and Electrical Engineering

Nanjing University of Information Science & Technology

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

1 Scopus citations

Abstract

In recent years, spatiotemporal sequence prediction has received increasing attention from researchers and has a wide range of promising applications in the fields of meteorology, traffic flow prediction, and autonomous driving. However, existing spatiotemporal sequence prediction models have some problems, such as slow convergence, training difficulties, and loss of image structural and detail information. We propose a novel end-To-end two-branch spatiotemporal sequence prediction model, which has been improved on these issues. We have compared our model with current advanced models using two datasets and found that our model reached or exceeded the level of the other advanced models in several metrics.

Original language	English
Title of host publication	2023 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	105-110
Number of pages	6
ISBN (Electronic)	9798350342239
DOIs	https://doi.org/10.1109/ICCSS58421.2023.10270114
State	Published - 2023
Event	9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023 - Nanjing, China Duration: 2 Jul 2023 → 4 Jul 2023

Publication series

Name	2023 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023

Conference

Conference	9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023
Country/Territory	China
City	Nanjing
Period	2/07/23 → 4/07/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 11 Sustainable Cities and Communities

Keywords

Attentional mechanisms
Discrete wavelet transform
Spatiotemporal sequence prediction

Access to Document

10.1109/ICCSS58421.2023.10270114

Cite this

Cui, Y., Lu, Z., Sun, L., & Jeon, B. (2023). Double Branch Model Based on Discrete Wavelet Transform for Spatiotemporal Prediction. In 2023 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023 (pp. 105-110). (2023 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCSS58421.2023.10270114

Cui, Yingjie ; Lu, Zhenyu ; Sun, Le et al. / Double Branch Model Based on Discrete Wavelet Transform for Spatiotemporal Prediction. 2023 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 105-110 (2023 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023).

@inproceedings{9fc075bc89de4ae7895c2ae92f740167,

title = "Double Branch Model Based on Discrete Wavelet Transform for Spatiotemporal Prediction",

abstract = "In recent years, spatiotemporal sequence prediction has received increasing attention from researchers and has a wide range of promising applications in the fields of meteorology, traffic flow prediction, and autonomous driving. However, existing spatiotemporal sequence prediction models have some problems, such as slow convergence, training difficulties, and loss of image structural and detail information. We propose a novel end-To-end two-branch spatiotemporal sequence prediction model, which has been improved on these issues. We have compared our model with current advanced models using two datasets and found that our model reached or exceeded the level of the other advanced models in several metrics.",

keywords = "Attentional mechanisms, Discrete wavelet transform, Spatiotemporal sequence prediction",

author = "Yingjie Cui and Zhenyu Lu and Le Sun and Byeungwoo Jeon",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023 ; Conference date: 02-07-2023 Through 04-07-2023",

year = "2023",

doi = "10.1109/ICCSS58421.2023.10270114",

language = "English",

series = "2023 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "105--110",

booktitle = "2023 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023",

}

Cui, Y, Lu, Z, Sun, L & Jeon, B 2023, Double Branch Model Based on Discrete Wavelet Transform for Spatiotemporal Prediction. in 2023 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023. 2023 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023, Institute of Electrical and Electronics Engineers Inc., pp. 105-110, 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023, Nanjing, China, 2/07/23. https://doi.org/10.1109/ICCSS58421.2023.10270114

Double Branch Model Based on Discrete Wavelet Transform for Spatiotemporal Prediction. / Cui, Yingjie; Lu, Zhenyu; Sun, Le et al.
2023 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 105-110 (2023 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023).

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

TY - GEN

T1 - Double Branch Model Based on Discrete Wavelet Transform for Spatiotemporal Prediction

AU - Cui, Yingjie

AU - Lu, Zhenyu

AU - Sun, Le

AU - Jeon, Byeungwoo

PY - 2023

Y1 - 2023

N2 - In recent years, spatiotemporal sequence prediction has received increasing attention from researchers and has a wide range of promising applications in the fields of meteorology, traffic flow prediction, and autonomous driving. However, existing spatiotemporal sequence prediction models have some problems, such as slow convergence, training difficulties, and loss of image structural and detail information. We propose a novel end-To-end two-branch spatiotemporal sequence prediction model, which has been improved on these issues. We have compared our model with current advanced models using two datasets and found that our model reached or exceeded the level of the other advanced models in several metrics.

AB - In recent years, spatiotemporal sequence prediction has received increasing attention from researchers and has a wide range of promising applications in the fields of meteorology, traffic flow prediction, and autonomous driving. However, existing spatiotemporal sequence prediction models have some problems, such as slow convergence, training difficulties, and loss of image structural and detail information. We propose a novel end-To-end two-branch spatiotemporal sequence prediction model, which has been improved on these issues. We have compared our model with current advanced models using two datasets and found that our model reached or exceeded the level of the other advanced models in several metrics.

KW - Attentional mechanisms

KW - Discrete wavelet transform

KW - Spatiotemporal sequence prediction

UR - https://www.scopus.com/pages/publications/85175403393

U2 - 10.1109/ICCSS58421.2023.10270114

DO - 10.1109/ICCSS58421.2023.10270114

M3 - Conference contribution

AN - SCOPUS:85175403393

T3 - 2023 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023

SP - 105

EP - 110

BT - 2023 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023

Y2 - 2 July 2023 through 4 July 2023

ER -

Cui Y, Lu Z, Sun L, Jeon B. Double Branch Model Based on Discrete Wavelet Transform for Spatiotemporal Prediction. In 2023 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 105-110. (2023 9th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2023). doi: 10.1109/ICCSS58421.2023.10270114

Double Branch Model Based on Discrete Wavelet Transform for Spatiotemporal Prediction

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this