Long short-term memory network-based wastewater quality prediction model with sparrow search algorithm

被引:11
作者
Li, Guobin [1 ]
Cui, Qingzhe [1 ]
Wei, Shengnan [1 ]
Wang, Xiaofeng [1 ]
Xu, Lixiang [1 ]
He, Lixin [1 ]
Kwong, Timothy C. H. [2 ]
Tang, Yuanyan [3 ]
机构
[1] Hefei Univ, Sch Artificial Intelligence & Big Data, Hefei, Peoples R China
[2] Tung Wah Coll, Hong Kong, Peoples R China
[3] FST Univ Macau, Zhuhai UM Sci & Technol Res Inst, Macau, Peoples R China
关键词
Water quality prediction; attention mechanism; principal component analysis; long short-term memory networks; sparrows search algorithm;
D O I
10.1142/S0219691323500194
中图分类号
TP31 [计算机软件];
学科分类号
081205 [计算机软件];
摘要
The wastewater treatment process is characterized by uncertainty, non-linearity, time delay and complexity, and is susceptible to many dynamic factors. Since some key water quality parameters are not available in real time, a Long Short-Term Memory (LSTM) network water quality prediction model based on sparrow search algorithm (SSA-LSTM) and attention mechanism is proposed to solve the problem. In this model, we take historical data as input, constructs models to learn the feature of internal dynamic changes, introduces the attention mechanism, assigns different weights to the hidden state of the LSTM network by mapping weightings with the learning parameter matrix, and uses the SSA to select the optimal hyperparameters for prediction. As high-latitude feature vectors are subject to the curse of dimension, a PCA-LSTM model is further proposed to apply the Principal Component Analysis (PCA) method to the SSA-LSTM model to reduce the dimensionality of the original data. The SSA-LSTM model without the PCA method (NPCA-LSTM) and the PCA-LSTM model are applied to predict wastewater quality and the PCA-LSTM model shows higher predictive ability.
引用
收藏
页数:20
相关论文
共 24 条
[1]
New texture-based pansharpening method using wavelet packet transform and PCA [J].
Abdolahpoor, Asma ;
Kabiri, Peyman .
INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING, 2020, 18 (04)
[2]
Chen JJ, 2017, 2017 IEEE INTERNATIONAL CONFERENCE ON SMART COMPUTING (SMARTCOMP), P211
[3]
Drozdov I. Y., 2021, IOP C SER MAT SCI EN, V1047
[4]
Graves A, 2012, STUD COMPUT INTELL, V385, P1, DOI [10.1162/neco.1997.9.1.1, 10.1007/978-3-642-24797-2]
[5]
RNN Models for Dynamic Matrix Inversion: A Control-Theoretical Perspective [J].
Jin, Long ;
Li, Shuai ;
Hu, Bin .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2018, 14 (01) :189-199
[6]
Adaptive optimization-based Deep Convolutional Long Short-Term Memory for Bank NIFTY index prediction [J].
Kelotra, Amit ;
Pandey, Prateek .
INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING, 2021, 19 (03)
[7]
T2F-LSTM Method for Long-Term Traffic Volume Prediction [J].
Li, Runmei ;
Hu, Yongchao ;
Liang, Qiuhong .
IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2020, 28 (12) :3256-3264
[8]
Research on Sewage Monitoring and Water Quality Prediction Based on Wireless Sensors and Support Vector Machines [J].
Liu, Cong ;
Li, Hongji ;
Zhang, Qinkun .
WIRELESS COMMUNICATIONS & MOBILE COMPUTING, 2020, 2020
[9]
TD-LSTM: Temporal Dependence-Based LSTM Networks for Marine Temperature Prediction [J].
Liu, Jun ;
Zhang, Tong ;
Han, Guangjie ;
Gou, Yu .
SENSORS, 2018, 18 (11)
[10]
A hybrid model based on convolutional neural networks and long short-term memory for ozone concentration prediction [J].
Pak, Unjin ;
Kim, Chungsong ;
Ryu, Unsok ;
Sok, Kyongjin ;
Pak, Sungnam .
AIR QUALITY ATMOSPHERE AND HEALTH, 2018, 11 (08) :883-895