Research on HC-LSSVM Model for Soft Soil Settlement Prediction Based on Homotopy Continuation Method
Source abstract
Abstract
Prediction of soft soil settlement is an important research topic in the field of civil engineering, and the least square support vector machine is one of the commonly used prediction methods at present. Nonetheless, the existing LSSVM models have problems of low search efficiency in the search process and lack of global optimal solution in the search results. In order to solve this problem, based on the leave-one-out cross-validation method, the homotopy continuation method was used to optimize the LSSVM model parameters, and then the HC-LSSVM model was constructed with the goal of minimizing the sum of squares of the prediction error of the full sample retention one. Finally, the rationality and correctness of the model are verified by engineering application. The results show that the HC-LSSVM model constructed in this study can accurately predict the settlement of soft ground, which is superior to the common LSSVM model and solves the problem that the parameters of LSSVM model cannot be solved optimally. The research results provide a new method for prediction of soft soil settlement.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Geotechnical Engineering and Analysis · Infrastructure Maintenance and Monitoring · Landslides and related hazards
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Civil Engineering, Sun Yat-sen University, Zhuhai 519082, China
Guangdong Engineering Research Centre for Major Infrastructures Safety, Guangzhou 510275, China
Research Center for Geotechnical Engineering and Information Technology, Sun Yat-sen University, Guangzhou 510275, China
Funding
the National Natural Science Foundation of China · the National Key Research and Development Project · The National Key Research and Development Project · the Special Fund Key Project of Applied Science and Technology Research and Development in Guangdong
References (28)
Show source-provided references
1. Review of research on high-speed railway subgrade settlement in soft soil area10.1007/s40534-020-00214-x ↗
2. On the behavior of piles in non-cohesive soil under combined horizontal and vertical loading10.1007/s11440-010-0124-1 ↗
3. A Simple Approach for Evaluating the Bearing Capacity of Piles Subjected to Inclined Loads10.1061/(ASCE)GM.1943-5622.0002215 ↗
4. Observation and Evaluation of Subgrade’s Settlement
5. Wei, J.H., Song, Z.Z., Bai, Y.X., Liu, J., Kanungo, D.P., and Sun, S.R. (2018). Field Test and Numerical Simulation for Coordinated Deformation of New Subgrade and Old Embankment Adjacent to River. Appl. Sci., 8.10.3390/app8122334 ↗
6. Zhai, H.B., Ding, H.Y., Zhang, P.Y., and Le, C.H. (2019). Model Tests of Soil Reinforcement Inside the Bucket Foundation with Vacuum Electroosmosis Method. Appl. Sci., 9.10.3390/app9183778 ↗
7. Analysis of Monitoring and Settlement Prediction of Wenzhou Shoal Seawall
8. Prediction of soft soil foundation settlement in Guangxi granite area based on fuzzy neural network model
9. Zhu, M.C., Li, S.Q., Wei, X.L., and Wang, P. (2021). Prediction and Stability Assessment of Soft Foundation Settlement of the Fishbone-Shaped Dike Near the Estuary of the Yangtze River Using Machine Learning Methods. Sustainability, 13.10.3390/su13073744 ↗
10. Application of soft computing techniques for shallow foundation reliability in geotechnical engineering10.1016/j.gsf.2020.05.003 ↗
11. Prediction of ground settlement based on immune genetic algorithm10.4028/www.scientific.net/AMM.155-156.1056 ↗
12. An unbiased LSSVM model for classification and regression10.1007/s00500-009-0435-z ↗
13. Settlement of Shallow Foundations on Cohesionless Soils Based on SPT Value Using Multi-Objective Feature Selection10.1007/s10706-018-0549-0 ↗
14. Foundation pit displacement monitoring and prediction using least squares support vector machines based on multi-point measurement10.1177/1475921718767935 ↗
15. Intelligent Approach to Estimation of Tunnel-Induced Ground Settlement Using Wavelet Packet and Support Vector Machines10.1061/(ASCE)CP.1943-5487.0000621 ↗
16. Reliability Analysis of Settlement of Pile Group in Clay Using LSSVM, GMDH, GPR10.1007/s10706-020-01464-6 ↗
17. Least-square support vector machine applied to settlement of shallow foundations on cohesionless soils10.1002/nag.731 ↗
18. Individual and combined impacts of future climate and land use changes on the water balance10.1016/j.ecoleng.2017.04.061 ↗
19. Choosing Multiple Parameters for Support Vector Machines10.1023/A:1012450327387 ↗
20. PHoM—A Polyhedral Homotopy Continuation Method for Polynomial Systems10.1007/s00607-003-0032-4 ↗
21. An adaptive accelerated proximal gradient method and its homotopy continuation for sparse optimization10.1007/s10589-014-9694-4 ↗
22. Benchmarking Least Squares Support Vector Machine Classifiers10.1023/B:MACH.0000008082.80494.e0 ↗
23. Geophysical Study: Estimation of Deposit Depth Using Gravimetric Data and Euler Method (Jalalabad Iron Mine, Kerman Province of IRAN)
24. Newton correction methods for computing real eigenpairs of symmetric tensors10.1137/17M1133312 ↗
25. Wang, S. (2000). Research on the Design of Swelling Soil Subgrade of Lian-Xu Experssway, Master Southeast University.
26. Feng, W. (2005). Application of MATLAB-ANN System in Expressway Soft Ground Settlement Prediction. [Master’ Thesis, Chang’an University].
27. GB 50021-2001 (2009). Code for Investigation of Geotechnical Engineering.
28. Wang, X., and Yuan, H. (2001). Design and Construction Technology of Embankment on Soft Soil Foundation of High-Grade Highway, People’s Communications Press.