TY - GEN
T1 - Deep Learning-based Management for Wastewater Treatment Plants under Blockchain Environment
AU - Wan, Keyi
AU - Guo, Zhiwei
AU - Wang, Jianhui
AU - Zeng, Wenru
AU - Gao, Xu
AU - Shen, Yu
AU - Yu, Keping
N1 - Funding Information:
ACKNOWLEDGMENT This work was supported by the Chongqing basic research and frontier exploration project of China under Grant cstc2018jcyjAX0638, State Language Commission Research Program of China under Grant YB135-121, and Scientific Program of Chongqing Technology and Business University under Grant ZDPTTD201917, Grant KFJJ2018071, and Grant 1952027.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/8
Y1 - 2020/8
N2 - Smart management for sewage treatment plants has always been a hot issue. It is generally implemented on the basis of a data scheduling platform, in which intelligent algorithms can be embedded. The most essential problem for such management is to predict daily business volumes, including amount and quality of wastewater. To achieve a comprehensive perspective, the generation of wastewater is viewed as collaborative effect of multiple factors in social system. This paper proposes a deep learning-based management for sewage treatment plants. Specially, it combines two classical neural network models to construct a hybrid model for precise prediction of business volumes. At last, a set of experiments are carried out to assess the proposed management mechanism. Results reveal that it performs better than general baselines.
AB - Smart management for sewage treatment plants has always been a hot issue. It is generally implemented on the basis of a data scheduling platform, in which intelligent algorithms can be embedded. The most essential problem for such management is to predict daily business volumes, including amount and quality of wastewater. To achieve a comprehensive perspective, the generation of wastewater is viewed as collaborative effect of multiple factors in social system. This paper proposes a deep learning-based management for sewage treatment plants. Specially, it combines two classical neural network models to construct a hybrid model for precise prediction of business volumes. At last, a set of experiments are carried out to assess the proposed management mechanism. Results reveal that it performs better than general baselines.
KW - blockchain
KW - conventional neural network
KW - deep learning
KW - long short-term memory
KW - prediction
UR - http://www.scopus.com/inward/record.url?scp=85093923527&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85093923527&partnerID=8YFLogxK
U2 - 10.1109/ICCCWorkshops49972.2020.9209927
DO - 10.1109/ICCCWorkshops49972.2020.9209927
M3 - Conference contribution
AN - SCOPUS:85093923527
T3 - 2020 IEEE/CIC International Conference on Communications in China, ICCC Workshops 2020
SP - 106
EP - 110
BT - 2020 IEEE/CIC International Conference on Communications in China, ICCC Workshops 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE/CIC International Conference on Communications in China, ICCC Workshops 2020
Y2 - 9 August 2020 through 11 August 2020
ER -