Dynamic Feature Extraction and Prediction for High Dimensional Time Series with Seasonality

Bingyuan Li; Yang Wang; Yang Zhao; Lishuai Li; Yining Dong

doi:10.1109/CASE59546.2024.10711621

Dynamic Feature Extraction and Prediction for High Dimensional Time Series with Seasonality

Bingyuan Li
, Yang Wang
, Yang Zhao
, Lishuai Li
, Yining Dong^*

^*Corresponding author for this work

Department of Data Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

1 Citation (Scopus)

Abstract

In this paper, a novel reduced-dimensional seasonal autoregressive modeling algorithm with a canonical correlation analysis objective (RDSAR-CCA) is developed for dynamic feature extraction and prediction in high-dimensional time series with seasonality. The proposed algorithm estimates a seasonal reduced-dimensional dynamic model for extracting and modeling the latent dynamics within the data. This approach facilitates dynamic latent variable (DLV) analysis in high-dimensional seasonal time series. The DLVs extracted by the proposed algorithm are orthogonal and ranked in descending order of predictability, which simplifies interpretation and enhances visualization. The effectiveness and superiority of the proposed RDSAR-CCA algorithm are evaluated on the passenger flow data from the Shenzhen metro system. © 2024 IEEE

Original language	English
Title of host publication	2024 IEEE 20th International Conference on Automation Science and Engineering (CASE)
Publisher	IEEE
Pages	368-373
ISBN (Electronic)	979-8-3503-5851-3
ISBN (Print)	979-8-3503-5852-0
DOIs	https://doi.org/10.1109/CASE59546.2024.10711621
Publication status	Published - 2024
Event	20th International Conference on Automation Science and Engineering (CASE 2024) - The Nicolaus Hotel, Bari, Italy Duration: 28 Aug 2024 → 1 Sept 2024 https://2024.ieeecase.org/

Publication series

Name
ISSN (Print)	2161-8070
ISSN (Electronic)	2161-8089

Conference

Conference	20th International Conference on Automation Science and Engineering (CASE 2024)
Place	Italy
City	Bari
Period	28/08/24 → 1/09/24
Internet address	https://2024.ieeecase.org/

Funding

This work was financially supported by National Key Research and Development Program of China (2021YFA1003504); National Natural Science Foundation of China (2322816); Shenzhen-Hong Kong-Macao Science and Technology Project Fund (SGDX20210823103403028); City University of Hong Kong Project (7005889). The work described in this paper was partially supported by InnoHK initiative, The Government of the HKSAR, and Laboratory for AI-Powered Financial Technologies.

UN SDGs

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

SDG 11 Sustainable Cities and Communities

Research Keywords

Big-Data and Data Mining

Access Output

10.1109/CASE59546.2024.10711621

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{f68e8b3329ea4899a99fe71656ec039f,

title = "Dynamic Feature Extraction and Prediction for High Dimensional Time Series with Seasonality",

abstract = "In this paper, a novel reduced-dimensional seasonal autoregressive modeling algorithm with a canonical correlation analysis objective (RDSAR-CCA) is developed for dynamic feature extraction and prediction in high-dimensional time series with seasonality. The proposed algorithm estimates a seasonal reduced-dimensional dynamic model for extracting and modeling the latent dynamics within the data. This approach facilitates dynamic latent variable (DLV) analysis in high-dimensional seasonal time series. The DLVs extracted by the proposed algorithm are orthogonal and ranked in descending order of predictability, which simplifies interpretation and enhances visualization. The effectiveness and superiority of the proposed RDSAR-CCA algorithm are evaluated on the passenger flow data from the Shenzhen metro system. {\textcopyright} 2024 IEEE",

keywords = "Big-Data and Data Mining",

author = "Bingyuan Li and Yang Wang and Yang Zhao and Lishuai Li and Yining Dong",

year = "2024",

doi = "10.1109/CASE59546.2024.10711621",

language = "English",

isbn = "979-8-3503-5852-0",

publisher = "IEEE",

pages = "368--373",

booktitle = "2024 IEEE 20th International Conference on Automation Science and Engineering (CASE)",

address = "United States",

note = "20th International Conference on Automation Science and Engineering (CASE 2024) ; Conference date: 28-08-2024 Through 01-09-2024",

url = "https://2024.ieeecase.org/",

}

Li, B, Wang, Y, Zhao, Y, Li, L & Dong, Y 2024, Dynamic Feature Extraction and Prediction for High Dimensional Time Series with Seasonality. in 2024 IEEE 20th International Conference on Automation Science and Engineering (CASE). IEEE, pp. 368-373, 20th International Conference on Automation Science and Engineering (CASE 2024), Bari, Italy, 28/08/24. https://doi.org/10.1109/CASE59546.2024.10711621

Dynamic Feature Extraction and Prediction for High Dimensional Time Series with Seasonality. / Li, Bingyuan; Wang, Yang; Zhao, Yang et al.
2024 IEEE 20th International Conference on Automation Science and Engineering (CASE). IEEE, 2024. p. 368-373.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Dynamic Feature Extraction and Prediction for High Dimensional Time Series with Seasonality

AU - Li, Bingyuan

AU - Wang, Yang

AU - Zhao, Yang

AU - Li, Lishuai

AU - Dong, Yining

PY - 2024

Y1 - 2024

N2 - In this paper, a novel reduced-dimensional seasonal autoregressive modeling algorithm with a canonical correlation analysis objective (RDSAR-CCA) is developed for dynamic feature extraction and prediction in high-dimensional time series with seasonality. The proposed algorithm estimates a seasonal reduced-dimensional dynamic model for extracting and modeling the latent dynamics within the data. This approach facilitates dynamic latent variable (DLV) analysis in high-dimensional seasonal time series. The DLVs extracted by the proposed algorithm are orthogonal and ranked in descending order of predictability, which simplifies interpretation and enhances visualization. The effectiveness and superiority of the proposed RDSAR-CCA algorithm are evaluated on the passenger flow data from the Shenzhen metro system. © 2024 IEEE

AB - In this paper, a novel reduced-dimensional seasonal autoregressive modeling algorithm with a canonical correlation analysis objective (RDSAR-CCA) is developed for dynamic feature extraction and prediction in high-dimensional time series with seasonality. The proposed algorithm estimates a seasonal reduced-dimensional dynamic model for extracting and modeling the latent dynamics within the data. This approach facilitates dynamic latent variable (DLV) analysis in high-dimensional seasonal time series. The DLVs extracted by the proposed algorithm are orthogonal and ranked in descending order of predictability, which simplifies interpretation and enhances visualization. The effectiveness and superiority of the proposed RDSAR-CCA algorithm are evaluated on the passenger flow data from the Shenzhen metro system. © 2024 IEEE

KW - Big-Data and Data Mining

U2 - 10.1109/CASE59546.2024.10711621

DO - 10.1109/CASE59546.2024.10711621

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 979-8-3503-5852-0

SP - 368

EP - 373

BT - 2024 IEEE 20th International Conference on Automation Science and Engineering (CASE)

PB - IEEE

T2 - 20th International Conference on Automation Science and Engineering (CASE 2024)

Y2 - 28 August 2024 through 1 September 2024

ER -

Dynamic Feature Extraction and Prediction for High Dimensional Time Series with Seasonality

Abstract

Publication series

Conference

Funding

UN SDGs

Research Keywords

Access Output

Other Access Options

Permanent Link

Fingerprint

Cite this