Search alternatives:
robust optimization » process optimization (Expand Search), robust estimation (Expand Search), joint optimization (Expand Search)
primary using » primary drying (Expand Search), primary amine (Expand Search), primary link (Expand Search)
robust optimization » process optimization (Expand Search), robust estimation (Expand Search), joint optimization (Expand Search)
primary using » primary drying (Expand Search), primary amine (Expand Search), primary link (Expand Search)
-
1
-
2
-
3
-
4
Robustness Analysis of each model.
Published 2025“…The model is developed and validated using data from 159 debris flow-prone gullies, integrating deep convolutional, recurrent, and attention-based architectures, with hyperparameters autonomously optimized by IKOA. …”
-
5
-
6
-
7
Eight commonly used benchmark functions.
Published 2023“…The primary objective of MSHHOTSA is to address the limitations of the tunicate swarm algorithm, which include slow optimization speed, low accuracy, and premature convergence when dealing with complex problems. …”
-
8
Curve of step response signal of 6 algorithms.
Published 2023“…The primary objective of MSHHOTSA is to address the limitations of the tunicate swarm algorithm, which include slow optimization speed, low accuracy, and premature convergence when dealing with complex problems. …”
-
9
Results of Comprehensive weighting.
Published 2025“…The model is developed and validated using data from 159 debris flow-prone gullies, integrating deep convolutional, recurrent, and attention-based architectures, with hyperparameters autonomously optimized by IKOA. …”
-
10
The prediction error of each model.
Published 2025“…The model is developed and validated using data from 159 debris flow-prone gullies, integrating deep convolutional, recurrent, and attention-based architectures, with hyperparameters autonomously optimized by IKOA. …”
-
11
VIF analysis results for hazard-causing factors.
Published 2025“…The model is developed and validated using data from 159 debris flow-prone gullies, integrating deep convolutional, recurrent, and attention-based architectures, with hyperparameters autonomously optimized by IKOA. …”
-
12
Benchmark function information.
Published 2025“…The model is developed and validated using data from 159 debris flow-prone gullies, integrating deep convolutional, recurrent, and attention-based architectures, with hyperparameters autonomously optimized by IKOA. …”
-
13
Geographical distribution of the study area.
Published 2025“…The model is developed and validated using data from 159 debris flow-prone gullies, integrating deep convolutional, recurrent, and attention-based architectures, with hyperparameters autonomously optimized by IKOA. …”
-
14
Results for model hyperparameter values.
Published 2025“…The model is developed and validated using data from 159 debris flow-prone gullies, integrating deep convolutional, recurrent, and attention-based architectures, with hyperparameters autonomously optimized by IKOA. …”
-
15
Flow chart of this study.
Published 2025“…The model is developed and validated using data from 159 debris flow-prone gullies, integrating deep convolutional, recurrent, and attention-based architectures, with hyperparameters autonomously optimized by IKOA. …”
-
16
Stability analysis of each model.
Published 2025“…The model is developed and validated using data from 159 debris flow-prone gullies, integrating deep convolutional, recurrent, and attention-based architectures, with hyperparameters autonomously optimized by IKOA. …”
-
17
Data used to drive the Double Layer Carbon Model in the Qinling Mountains.
Published 2024“…These compartments help accurately simulate the dynamics of SOC by considering both the fast-cycling and slow-cycling components of organic matter decomposition. The DLCM optimizes initial SOC stocks using extensive spatial simulations, ensuring accurate baseline carbon levels. …”
-
18
Wilcoxon’s rank sum test results.
Published 2023“…The primary objective of MSHHOTSA is to address the limitations of the tunicate swarm algorithm, which include slow optimization speed, low accuracy, and premature convergence when dealing with complex problems. …”
-
19
Flowchart of MSHHOTSA.
Published 2023“…The primary objective of MSHHOTSA is to address the limitations of the tunicate swarm algorithm, which include slow optimization speed, low accuracy, and premature convergence when dealing with complex problems. …”
-
20
S1 Data -
Published 2023“…The primary objective of MSHHOTSA is to address the limitations of the tunicate swarm algorithm, which include slow optimization speed, low accuracy, and premature convergence when dealing with complex problems. …”