Flowchart of MSHHOTSA. by Guangwei Liu (181992)

“…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. …”

Tension/compression spring design problem. by Guangwei Liu (181992)

“…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. …”

Speed reducer design problem. by Guangwei Liu (181992)

“…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. …”

Flowchart of TSA [43]. by Guangwei Liu (181992)

“…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. …”

Pressure vessel design problem. by Guangwei Liu (181992)

“…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. …”

Gear train design problem. by Guangwei Liu (181992)

“…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. …”

The proportion integral derivative controller. by Guangwei Liu (181992)

“…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. …”

Random parameter factor. by Guangwei Liu (181992)

“…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. …”

Eight commonly used benchmark functions. by Guangwei Liu (181992)

“…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. …”

Hyperbolic tangent row domain. by Guangwei Liu (181992)

“…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. …”

Parameter settings. by Guangwei Liu (181992)

“…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. …”

Nonlinear fast convergence factor. by Guangwei Liu (181992)

“…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. …”

CEC2019 benchmark functions. by Guangwei Liu (181992)

“…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. …”

Results of Comprehensive weighting. by Hao Yang (328526)

“…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. …”

The prediction error of each model. by Hao Yang (328526)

“…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. …”

VIF analysis results for hazard-causing factors. by Hao Yang (328526)

“…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. …”

Benchmark function information. by Hao Yang (328526)

“…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. …”

Geographical distribution of the study area. by Hao Yang (328526)

“…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. …”

Results for model hyperparameter values. by Hao Yang (328526)

“…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. …”

Flow chart of this study. by Hao Yang (328526)

“…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. …”