Sequential backward feature selection for optimizing permanent strain model of unbound aggregates
Source abstract
Abstract
This study proposes a novel framework for identifying the optimal feature set required to predict the permanent strain of unbound aggregates. An experimental database consisting of 16 input features is preprocessed and the performance of 10 machine learning models is evaluated. The best-performing model is then paired with a sequential backward selection algorithm to determine the optimal feature set for predicting the permanent strain. Finally, the selected features are used to predict the permanent strain, and the performance is compared with those obtained from the principal components analysis. Six features are selected as the optimal feature set. Furthermore, the selected features accurately predict permanent strain with a root mean square error value of 0.014, which is smaller than those obtained from principal components analysis. Thus, the feature selection approach for machine learning models effectively predicts the permanent strain of unbound aggregates using a limited set of input features.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Geotechnical Engineering and Underground Structures · Infrastructure Maintenance and Monitoring · Asphalt Pavement Performance Evaluation
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (49)
Show source-provided references
1. Feature selection approach for failure mode detection of reinforced concrete bridge columns
2. Neural network application in forecasting maximum wall deflection in homogenous clay10.1186/s40703-021-00158-z ↗
3. Neural network-based model for prediction of permanent deformation of unbound granular materials10.1016/j.jrmge.2019.03.005 ↗
4. Evaluating the relevance of eggshell and glass powder for cement-based materials using machine learning and SHapley Additive exPlanations (SHAP) analysis
5. GEP tree-based computational AI approach to evaluate unconfined compression strength characteristics of Fly ash treated alkali contaminated soils
6. Cross-Validation
7. Aggregate properties affecting shear strength and permanent deformation characteristics of unbound–base course materials10.1061/(ASCE)MT.1943-5533.0003000 ↗
8. Feature selection in machine learning: a new perspective10.1016/j.neucom.2017.11.077 ↗
9. Rapid extraction of pavement aggregate gradation based on point clouds using deep learning networks10.1016/j.autcon.2023.105023 ↗
10. Framework for development of an improved unbound aggregate base rutting model for mechanistic-empirical pavement design10.3141/2401-02 ↗
11. Effect of inclusion of natural pozzolan and silica fume in cement - based mortars on the compressive strength utilizing artificial neural networks and support vector machine
12. An investigation of feature selection methods for soil liquefaction prediction based on tree-based ensemble algorithms using AdaBoost, gradient boosting, and XGBoost10.1007/s00521-022-07856-4 ↗
13. Liquefaction prediction with robust machine learning algorithms (SVM, RF, and XGBoost) supported by genetic algorithm-based feature selection and parameter optimization from the perspective of data processing10.1007/s12665-022-10578-4 ↗
14. Predicting occurrence of liquefaction-induced lateral spreading using gradient boosting algorithms integrated with particle swarm optimization: PSO-XGBoost, PSO-LightGBM, and PSO-CatBoost10.1007/s11440-022-01777-1 ↗
15. Automatic damage segmentation in pavement videos by fusing similar feature extraction siamese network (SFE-SNet) and pavement damage segmentation capsule network (PDS-CapsNet)10.1016/j.autcon.2022.104537 ↗
16. Data cleaning and feature selection for gravelly soil liquefaction10.1016/j.soildyn.2021.106711 ↗
17. Machine learning-based model for recognizing the failure modes of FRP-strengthened RC beams in flexure
18. Determination of Unbound Granular Material Resilient Modulus with MARS, PLSR, KNN and SVM10.1007/s42947-021-00054-w ↗
19. James, G., Witten, D., Hastie, T., Tibshirani, R., 2021. An Introduction to Statistical Learning.10.1007/978-1-0716-1418-1 ↗
20. Identifying outliers of non-Gaussian groundwater state data based on ensemble estimation for long-term trends10.1016/j.jhydrol.2017.02.058 ↗
21. Application of ensemble learning in predicting shallow foundation settlement in cohesionless soil10.1080/19386362.2023.2212996 ↗
22. Principal component analysis: a review and recent developments
23. Machine learning for developing a pavement condition index10.1016/j.autcon.2022.104296 ↗
24. Forecasting of pile plugging using machine learning10.1007/s11440-023-01797-5 ↗
25. A procedure for anomaly detection and analysis10.1016/j.engappai.2022.105503 ↗
26. Košir, A., Odić, A., Tkalčič, M., 2013. How to improve the statistical power of the 10-fold cross validation scheme in recommender systems. ACM International Conference Proceeding Series, 3–6.10.1145/2532508.2532510 ↗
27. State of the art. II: permanent strain response of unbound aggregates10.1061/(ASCE)0733-947X(2000)126:1(76) ↗
28. Application of improved grid search algorithm on SVM for classification of tumor gene10.14257/ijmue.2014.9.11.18 ↗
29. Automated asphalt pavement damage rate detection based on optimized GA-CNN10.1016/j.autcon.2022.104180 ↗
30. Liashchynskyi, P.B., Liashchynskyi, P., 2019. Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS. ArXiv.
31. Joint shear strength prediction of beam-column connections using machine learning via experimental results
32. Machine learning feature selection methods for landslide susceptibility mapping10.1007/s11004-013-9511-0 ↗
33. Application of multivariate adaptive regression splines (MARS) approach in prediction of compressive strength of eco-friendly concrete
34. Scikit-learn: machine learning in python
35. Implementation framework of the UIUC aggregate base rutting model10.1080/10298436.2019.1683178 ↗
36. Rahman, M.S., Erlingsson, S., Ahmed, A., 2022. Modelling the permanent deformation of unbound granular materials in pavements.10.1080/14680629.2022.2108883 ↗
37. Reliability analysis of reinforced soil slope stability using GA-ANFIS, RFC, and GMDH soft computing techniques
38. Sensitivity analysis of k-fold cross validation in prediction error estimation10.1109/TPAMI.2009.187 ↗
39. The use of PCA and signal processing techniques for processing time-based construction settlement data of road embankments10.1016/j.aei.2020.101181 ↗
40. Convolutional neural networks prediction of the factor of safety of random layered slopes by the strength reduction method
41. A comparative study on the development of hybrid SSA-RF and PSO-RF models for predicting the uniaxial compressive strength of rocks
42. Rapid pavement aggregate gradation estimation based on 3D data using a multi-feature fusion network10.1016/j.autcon.2021.104050 ↗
43. Predicting permanent strain accumulation of unbound aggregates using machine learning algorithms10.1016/j.trgeo.2023.101060 ↗
44. Performance evaluations of unbound aggregate permanent deformation models for various aggregate physical properties10.3141/2525-03 ↗
45. Characterizing the as-encountered ground condition with tunnel boring machine data using semi-supervised learning10.1016/j.compgeo.2022.105159 ↗
46. A novel feature selection method based on global sensitivity analysis with application in machine learning-based prediction model
47. CPT-based fully probabilistic seismic liquefaction potential assessment to reduce uncertainty: integrating XGBoost algorithm with Bayesian theorem10.1016/j.compgeo.2022.104868 ↗
48. Comprehensive review of machine learning in geotechnical reliability analysis: Algorithms, applications and further challenges10.1016/j.asoc.2023.110066 ↗
49. Deep Learning and Applications