IEICE TRANSACTIONS on Information
Research on a Prediction Method for Carbon Dioxide Concentration Based on an Optimized LSTM Network of Spatio-Temporal Data Fusion
Summary :
In view of the different spatial and temporal resolutions of observed multi-source heterogeneous carbon dioxide data and the uncertain quality of observations, a data fusion prediction model for observed multi-scale carbon dioxide concentration data is studied. First, a wireless carbon sensor network is created, the gross error data in the original dataset are eliminated, and remaining valid data are combined with kriging method to generate a series of continuous surfaces for expressing specific features and providing unified spatio-temporally normalized data for subsequent prediction models. Then, the long short-term memory network is used to process these continuous time- and space-normalized data to obtain the carbon dioxide concentration prediction model at any scales. Finally, the experimental results illustrate that the proposed method with spatio-temporal features is more accurate than the single sensor monitoring method without spatio-temporal features.
- Publication
- IEICE TRANSACTIONS on Information Vol.E104-D No.10 pp.1753-1757
- Publication Date
- 2021/10/01
- Publicized
- 2021/07/08
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2021EDL8020
- Type of Manuscript
- LETTER
- Category
- Data Engineering, Web Information Systems
Authors
Jun MENG
Beijing Institute of Technology
Gangyi DING
Beijing Institute of Technology
Laiyang LIU
Beijing Institute of Technology
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Jun MENG, Gangyi DING, Laiyang LIU, "Research on a Prediction Method for Carbon Dioxide Concentration Based on an Optimized LSTM Network of Spatio-Temporal Data Fusion" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 10, pp. 1753-1757, October 2021, doi: 10.1587/transinf.2021EDL8020.
Abstract: In view of the different spatial and temporal resolutions of observed multi-source heterogeneous carbon dioxide data and the uncertain quality of observations, a data fusion prediction model for observed multi-scale carbon dioxide concentration data is studied. First, a wireless carbon sensor network is created, the gross error data in the original dataset are eliminated, and remaining valid data are combined with kriging method to generate a series of continuous surfaces for expressing specific features and providing unified spatio-temporally normalized data for subsequent prediction models. Then, the long short-term memory network is used to process these continuous time- and space-normalized data to obtain the carbon dioxide concentration prediction model at any scales. Finally, the experimental results illustrate that the proposed method with spatio-temporal features is more accurate than the single sensor monitoring method without spatio-temporal features.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDL8020/_p
Copy
@ARTICLE{e104-d_10_1753,
author={Jun MENG, Gangyi DING, Laiyang LIU, },
journal={IEICE TRANSACTIONS on Information},
title={Research on a Prediction Method for Carbon Dioxide Concentration Based on an Optimized LSTM Network of Spatio-Temporal Data Fusion},
year={2021},
volume={E104-D},
number={10},
pages={1753-1757},
abstract={In view of the different spatial and temporal resolutions of observed multi-source heterogeneous carbon dioxide data and the uncertain quality of observations, a data fusion prediction model for observed multi-scale carbon dioxide concentration data is studied. First, a wireless carbon sensor network is created, the gross error data in the original dataset are eliminated, and remaining valid data are combined with kriging method to generate a series of continuous surfaces for expressing specific features and providing unified spatio-temporally normalized data for subsequent prediction models. Then, the long short-term memory network is used to process these continuous time- and space-normalized data to obtain the carbon dioxide concentration prediction model at any scales. Finally, the experimental results illustrate that the proposed method with spatio-temporal features is more accurate than the single sensor monitoring method without spatio-temporal features.},
keywords={},
doi={10.1587/transinf.2021EDL8020},
ISSN={1745-1361},
month={October},}
Copy
TY - JOUR
TI - Research on a Prediction Method for Carbon Dioxide Concentration Based on an Optimized LSTM Network of Spatio-Temporal Data Fusion
T2 - IEICE TRANSACTIONS on Information
SP - 1753
EP - 1757
AU - Jun MENG
AU - Gangyi DING
AU - Laiyang LIU
PY - 2021
DO - 10.1587/transinf.2021EDL8020
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2021
AB - In view of the different spatial and temporal resolutions of observed multi-source heterogeneous carbon dioxide data and the uncertain quality of observations, a data fusion prediction model for observed multi-scale carbon dioxide concentration data is studied. First, a wireless carbon sensor network is created, the gross error data in the original dataset are eliminated, and remaining valid data are combined with kriging method to generate a series of continuous surfaces for expressing specific features and providing unified spatio-temporally normalized data for subsequent prediction models. Then, the long short-term memory network is used to process these continuous time- and space-normalized data to obtain the carbon dioxide concentration prediction model at any scales. Finally, the experimental results illustrate that the proposed method with spatio-temporal features is more accurate than the single sensor monitoring method without spatio-temporal features.
ER -
English
