Ouassila Bahloul, Zohra Tebbi Fatima, Laid Lekouara, Hizia Bekhouche
LGCROI. Civil Laboratory Risks and Structures Interactions, Faculty of Technology, University of Mostepha Ben Batna 2, Fesdis, Algeria.
LRNAT Laboratory, Earth Sciences and Universe Institute, University of Mostepha Ben Boulaid Batna 2, Fesdis, Algeria.
Heliyon. 2023 Jul 26;9(8):e18673. doi: 10.1016/j.heliyon.2023.e18673. eCollection 2023 Aug.
The swelling pressure (SP) of expansive soils is crucial for both geotechnical studies as well as practitioners. Multiple attempts have been made to correlate the SP with the properties of soil due to the difficulty of determining it in the laboratory. However, the large number of environmental and physical governing parameters makes accurate SP predictions difficult. In this paper, Artificial Neural Networks (ANNs) are used to assess accurate prediction of SP of soil. Dimension reduction techniques are intensely required for ANNs inputs. Feature extraction (FE) based dimension reduction (DR) methods map original multidimensional space into a space of reduced dimensionality. This paper presents a comparative study of linear FE using Principal Component Analysis (PCA) and nonlinear FE using ISOmetric MAPping (ISOMAP) for feed forward neural models to predict SP. Results showed that FE technique improves ANNs models compared to multiple linear regression (MLR) and ANNs model without DR. Moreover, nonlinear ISOMAP based DR technique has proven its effectiveness regarding performance metrics for five dimensions inputs (Dims), Determination coefficient (R = 0.923), Mean absolute percentage error (MAPE = 0.072), and Root mean square error (RMSE = 54.937) and Root relative squared error (RRSE = 0.383). Therefore, ISOMAP-ANN models can be adopted to solve geotechnical problems specially those of expansive soils which have a very complex and nonlinear structure.
膨胀土的膨胀压力（SP）对于岩土工程研究和从业者而言都至关重要。由于在实验室中确定SP存在困难，人们已多次尝试将其与土壤性质相关联。然而，大量的环境和物理控制参数使得准确预测SP变得困难。本文采用人工神经网络（ANN）来评估土壤SP的准确预测。ANN输入强烈需要降维技术。基于特征提取（FE）的降维（DR）方法将原始多维空间映射到低维空间。本文对用于前馈神经模型以预测SP的使用主成分分析（PCA）的线性FE和使用等距映射（ISOMAP）的非线性FE进行了比较研究。结果表明，与多元线性回归（MLR）和无DR的ANN模型相比，FE技术改进了ANN模型。此外，基于非线性ISOMAP的DR技术在五个维度输入（Dims）的性能指标方面已证明其有效性，决定系数（R = 0.923）、平均绝对百分比误差（MAPE = 0.072）、均方根误差（RMSE = 54.937）和根相对平方误差（RRSE = 0.383）。因此，ISOMAP-ANN模型可用于解决岩土工程问题，特别是那些具有非常复杂和非线性结构的膨胀土问题。
