Hybrid optimized RF model of seismic resilience of buildings in mountainous region based on hyperparameter tuning and SMOTE

Wen, Haijia; Wu, Jinnan; Zhang, Chi; Zhou, Xinzhi; Liao, Mingyong; Xu, Jiahui

doi:10.1016/j.jobe.2023.106488

Cited by 3 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper utilizes the random forest algorithm to construct a comprehensive risk assessment model for pipelines based on existing pipeline classification data. The random forest model is a classification model that uses multiple decision trees as classifiers to train and predict samples. , The algorithm model is illustrated in Figure . This model combines the bagging algorithm, which operates on training samples, with the random subspace method, which operates on feature sets.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Integrated Risk Assessment of Mountainous Long-Distance Oil and Gas Pipelines Based on Multisource Spatial Data

Wang,

Li,

Zhu

et al. 2024

ACS Omega

View full text Add to dashboard Cite

Pipeline risk assessment is crucial for pipeline safety management and operation. The aim of this study is to develop a comprehensive assessment model that accurately evaluates pipeline risks and ensures the safe and reliable operation of the pipeline system. The model is based on multisource spatial data and is primarily applicable to long-distance oil and gas pipelines that traverse complex geological conditions in mountainous areas. The research is conducted using the example of the Jinliwen natural gas pipeline in Zhejiang Province, China. By analyzing the geological data of the study area and the potential risks that the pipeline may encounter, a comprehensive risk assessment indicator system for the pipeline was developed using slope units to divide pipeline sections. The pipeline risk levels are classified using the K-means clustering-entropy weighted-random forest algorithm. The model is evaluated using accuracy (Acc), precision (Pre), recall (R), F1-score, and the ROC curve. The results show that the model has an accuracy of 0.917, a precision of 0.92, a recall of 0.916, an F1-score of 0.914, and an AUC (Area Under Curve) of 0.93, indicating its strong predictive capability. The risk assessment results demonstrate a strong consistency when compared with actual incident events. This indicates that the constructed model effectively reflects the influencing factors of pipeline risk, providing a basis for pipeline risk assessment and disaster prevention and mitigation efforts in similar regions.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The random forest model is a classification model that uses multiple decision trees as classifiers to train and predict samples. 42 , 43 The algorithm model is illustrated in Figure 2 . This model combines the bagging algorithm, which operates on training samples, with the random subspace method, which operates on feature sets.…”

Section: Methodsmentioning

confidence: 99%

Integrated Risk Assessment of Mountainous Long-Distance Oil and Gas Pipelines Based on Multisource Spatial Data

Wang,

Li,

Zhu

et al. 2024

ACS Omega

View full text Add to dashboard Cite

show abstract

Different-Classification-Scheme-Based Machine Learning Model of Building Seismic Resilience Assessment in a Mountainous Region

et al. 2023

View full text Add to dashboard Cite

This study aims to develop different-classification-scheme-based building-seismic-resilience (BSR)-mapping models using random forest (RF) and a support vector machine (SVM). Based on a field survey of earthquake-damaged buildings in Shuanghe Town, the epicenter of the Changning M 5.8 earthquake that occurred on 17 June 2019, we selected 19 influencing factors for BSR assessment to establish a database. Based on three classification schemes for the description of BSR, we developed six machine learning assessment models for BSR mapping using RF and an SVM after optimizing the hyper-parameters. The validation indicators of model performance include precision, recall, accuracy, and F1-score as determined from the test sub-dataset. The results indicate that the RF- and SVM-based BSR models achieved prediction accuracies of approximately 0.64–0.94 for different classification schemes applied to the test sub-dataset. Additionally, the precision, recall, and F1-score indicators showed satisfactory values with respect to the BSR levels with relatively large sample sizes. The RF-based models had a lower tendency for overfitting compared to the SVM-based models. The performance of the BSR models was influenced by the quantity of total datasets, the classification schemes, and imbalanced data. Overall, the RF- and SVM-based BSR models can improve the evaluation efficiency of earthquake-damaged buildings in mountainous areas.

show abstract

Machine learning algorithms for safer construction sites: Critical review

Junjia,

Alias,

Haron

et al. 2024

Build. Eng.

View full text Add to dashboard Cite

Machine learning, a key thruster of Construction 4.0, has seen exponential publication growth in the last ten years. Many studies have identified ML as the future, but few have critically examined the applications and limitations of various algorithms in construction management. Therefore, this article comprehensively reviewed the top 100 articles from 2018 to 2023 about ML algorithms applied in construction risk management, provided their strengths and limitations, and identified areas for improvement. The study found that integrating various data sources, including historical project data, environmental factors, and stakeholder information, has become a common trend in construction risk. However, the challenges associated with the need for extensive and high-quality datasets, models’ interpretability, and construction projects’ dynamic nature pose significant barriers. The recommendations presented in this paper can facilitate interdisciplinary collaboration between traditional construction and machine learning, thereby enhancing the development of specialized algorithms for real-world projects.

show abstract

Hybrid optimized RF model of seismic resilience of buildings in mountainous region based on hyperparameter tuning and SMOTE

Cited by 3 publications

References 38 publications

Integrated Risk Assessment of Mountainous Long-Distance Oil and Gas Pipelines Based on Multisource Spatial Data

Integrated Risk Assessment of Mountainous Long-Distance Oil and Gas Pipelines Based on Multisource Spatial Data

Different-Classification-Scheme-Based Machine Learning Model of Building Seismic Resilience Assessment in a Mountainous Region

Machine learning algorithms for safer construction sites: Critical review

Contact Info

Product

Resources

About