Prediction of California bearing ratio (CBR) for coarse- and fine-grained soils using the GMDH-model

被引:4
|
作者
Kim, Mintae [1 ]
Ordu, Seyma [2 ]
Arslan, Ozkan [3 ]
Ko, Junyoung [4 ]
机构
[1] Korea Univ, Sch Civil Environm & Architectural Engn, 145 Anam ro, Seoul 02841, South Korea
[2] Tekirdag Namik Kemal Univ, Dept Environm Engn, Namik Kemal Mahallesi Kampus Caddesi 1, TR-59030 Tekirdag, Turkiye
[3] Tekirdag Namik Kemal Univ, Dept Elect & Commun Engn, Namik Kemal Mahallesi Kampus Caddesi 1, TR-59030 Tekirda, Turkiye
[4] Chungnam Natl Univ, Dept Civil Engn, 99 Daehak ro, Daejeon 34134, South Korea
基金
新加坡国家研究基金会;
关键词
artificial intelligence technology; California bearing ratio (CBR); group method of data handling (GMDH); NEURAL-NETWORK; SHALLOW FOUNDATIONS; SETTLEMENT; REGRESSION; INDEX;
D O I
10.12989/gae.2023.33.2.183
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
This study presents the prediction of the California bearing ratio (CBR) of coarse-and fine-grained soils using artificial intelligence technology. The group method of data handling (GMDH) algorithm, an artificial neural network-based model, was used in the prediction of the CBR values. In the design of the prediction models, various combinations of independent input variables for both coarse-and fine-grained soils have been used. The results obtained from the designed GMDH-type neural networks (GMDH-type NN) were compared with other regression models, such as linear, support vector, and multilayer perception regression methods. The performance of models was evaluated with a regression coefficient (R2), root-mean-square error (RMSE), and mean absolute error (MAE). The results showed that GMDH-type NN algorithm had higher performance than other regression methods in the prediction of CBR value for coarse-and fine-grained soils. The GMDH model had an R2 of 0.938, RMSE of 1.87, and MAE of 1.48 for the input variables {G, S, and MDD} in coarse-grained soils. For fine-grained soils, it had an R2 of 0.829, RMSE of 3.02, and MAE of 2.40, when using the input variables {LL, PI, MDD, and OMC}. The performance evaluations revealed that the GMDH-type NN models were effective in predicting CBR values of both coarse-and fine-grained soils.
引用
收藏
页码:183 / 194
页数:12
相关论文
共 47 条
  • [41] FINE-GRAINED ACRONYM EXPANSION IDENTIFICATION USING LATENT-STATE NEURAL STRUCTURED PREDICTION MODEL
    Liu, Jie
    Liu, Caihua
    Hu, Qinghua
    Huang, Yalou
    [J]. PROCEEDINGS OF 2015 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS (ICMLC), VOL. 1, 2015, : 259 - 264
  • [42] Prediction of California Bearing Ratio from Index Properties of Soils Using Parametric and Non-parametric Models
    Gonzalez Farias, Isabel
    Araujo, William
    Ruiz, Gaby
    [J]. GEOTECHNICAL AND GEOLOGICAL ENGINEERING, 2018, 36 (06) : 3485 - 3498
  • [43] Effect of Deformation-Induced Suction in the Behavior of Unsaturated Fine-Grained Soils Using Simplified Finite-Element Model
    Ravichandran, Nadarajah
    Krishnapillai, Shada H.
    [J]. INTERNATIONAL JOURNAL OF GEOMECHANICS, 2013, 13 (05) : 483 - 495
  • [44] Fine-Grained Battery-Swap Order Prediction Using Spatio-Temporal Data Via GAT Model
    Pan, Xianrui
    Yang, Panlong
    Fan, Xiaochen
    Zhang, Guanghui
    Pan, Pengju
    Ye, Lei
    Wu, Yicheng
    Shu, Dailong
    [J]. 2022 IEEE 28TH INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS, ICPADS, 2022, : 387 - 394
  • [45] Prediction of California bearing ratio and modified proctor parameters using deep neural networks and multiple linear regression: A case study of granular soils
    Polo-Mendoza, Rodrigo
    Duque, Jose
    Masin, David
    [J]. CASE STUDIES IN CONSTRUCTION MATERIALS, 2024, 20
  • [46] Predictive strength model of cement-treated fine-grained soils using key parameters: Consideration of the total water/cement and soil/cement ratios
    Kang, Gyeong-o
    Kim, Young-sang
    Kang, Jung-goo
    [J]. CASE STUDIES IN CONSTRUCTION MATERIALS, 2023, 18
  • [47] Prediction of California bearing ratio using multi-layer perceptron model based on multiple meta-heuristic optimizers
    Chen, Jianhong
    [J]. MULTISCALE AND MULTIDISCIPLINARY MODELING EXPERIMENTS AND DESIGN, 2024, 7 (03) : 2489 - 2505