Application of HKELM Model Based on Improved Seahorse Optimizer in Reservoir Dissolved Oxygen Prediction DOI Open Access

Lijin Guo,

Xiao Hu

Water, Journal Year: 2024, Volume and Issue: 16(16), P. 2232 - 2232

Published: Aug. 8, 2024

As an important part of environmental science and water resources management, quality prediction is great importance. In order to improve the efficiency accuracy predicting dissolved oxygen (DO) at outlet a reservoir, this paper proposes improved Seahorse Optimizer enhance hybrid kernel extreme learning machine model for prediction. Firstly, circle chaotic map used initialize hippocampus population diversity population, then sine cosine strategy replace predation behavior global search ability. Finally, lens imaging reverse expand range prevent it from falling into local optimal solution. By introducing two functions, function (Poly) (RBF), new formed by linearly combining these functions. The parameters HKELM are optimized with Optimizer, CZTSHO-HKELM constructed. simulation results show that operating better than those ELM, CZTSHO-ELM, CZTSHO-KELM, SHO-HKELM models, correlation coefficients increased 5.5%, 3.3%, 3.4%, 7.4%, respectively. curve close actual change, which can meet requirements reservoir above method be applied further accurately predict reservoir.

Language: Английский

Predicting water quality in municipal water management systems using a hybrid deep learning model DOI

Wenxian Luo,

Leijun Huang,

Jiabin Shu

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 133, P. 108420 - 108420

Published: April 23, 2024

Language: Английский

Citations

7
A novel sub-model selection algorithm considering model interactions in combination forecasting for carbon price forecasting DOI

Jingling Yang,

Liren Chen, Huayou Chen

et al.

Applied Intelligence, Journal Year: 2025, Volume and Issue: 55(6)

Published: Jan. 24, 2025

Language: Английский

Citations

0
Shapley value-driven superior subset selection algorithm for carbon price interval forecast combination DOI Creative Commons

Jingling Yang,

Liren Chen, Huayou Chen

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 27, 2025

Interval prediction requires not only accuracy but also the consideration of interval width and coverage, making model selection complex. However, research rarely addresses this challenge in combination forecasting. To address issue, study introduces a for forecast based on Shapley value (MSIFC–SV). This algorithm calculates values to measure each model's marginal contribution establishes redundancy criterion basis changes scores. If removal does decrease score, it is considered redundant excluded. The process starts with all models ranks them by their values. Models are then assessed retention or according criterion, which continues until remaining subset used generate combinations through Bayesian weighting. Empirical analysis carbon price shows that MSIFC–SV outperforms individual derived subsets across metrics such as coverage probability (PICP), mean (MPIW), (CWC), score (IS). Comparisons benchmark methods further demonstrate superiority MSIFC–SV. Furthermore, successfully extended public dataset-housing dataset, indicates its universality. In summary, provides reliable delivers high-quality forecasts.

Language: Английский

Citations

0
An efficient parallel runoff forecasting model for capturing global and local feature information DOI Creative Commons

Yang-hao Hong,

Dongmei Xu, Wenchuan Wang

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 11, 2025

Language: Английский

Citations

0
Feature extraction for acoustic leakage detection in water pipelines DOI
Tao An,

Liang Ma,

Dazhi Li

et al.

Automation in Construction, Journal Year: 2025, Volume and Issue: 176, P. 106248 - 106248

Published: May 9, 2025

Language: Английский

Citations

0
Algal bloom forecasting leveraging signal processing: a novel perspective from ensemble learning DOI
Caicai Xu, Yuzhou Huang,

Ruoxue Xin

et al.

Water Research, Journal Year: 2025, Volume and Issue: unknown, P. 123800 - 123800

Published: May 1, 2025

Language: Английский

Citations

0
DBFiLM: A novel dual-branch frequency improved legendre memory forecasting model for coagulant dosage determination DOI
Sibo Xia, Hongqiu Zhu,

Ning Zhang

et al.

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 254, P. 124488 - 124488

Published: June 12, 2024

Language: Английский

Citations

1
Application of HKELM Model Based on Improved Seahorse Optimizer in Reservoir Dissolved Oxygen Prediction DOI Open Access

Lijin Guo,

Xiao Hu

Water, Journal Year: 2024, Volume and Issue: 16(16), P. 2232 - 2232

Published: Aug. 8, 2024

As an important part of environmental science and water resources management, quality prediction is great importance. In order to improve the efficiency accuracy predicting dissolved oxygen (DO) at outlet a reservoir, this paper proposes improved Seahorse Optimizer enhance hybrid kernel extreme learning machine model for prediction. Firstly, circle chaotic map used initialize hippocampus population diversity population, then sine cosine strategy replace predation behavior global search ability. Finally, lens imaging reverse expand range prevent it from falling into local optimal solution. By introducing two functions, function (Poly) (RBF), new formed by linearly combining these functions. The parameters HKELM are optimized with Optimizer, CZTSHO-HKELM constructed. simulation results show that operating better than those ELM, CZTSHO-ELM, CZTSHO-KELM, SHO-HKELM models, correlation coefficients increased 5.5%, 3.3%, 3.4%, 7.4%, respectively. curve close actual change, which can meet requirements reservoir above method be applied further accurately predict reservoir.

Language: Английский

Citations

0