Evolutionary polynomial regression improved by regularization methods

Evolutionary polynomial regression (EPR) is a data mining tool that has been widely used in solving various geotechnical engineering problems. The fitness function is the core of EPR. However, overfitting may still occur in EPR, and this issue may cause the testing dataset not to perform effectively. Improvement of the EPR fitness function through L1 and L2 regularization methods is critical to avoid overfitting and enhance good generalization. First, the appropriate values of the regularization parameter λ of the L1 regularization method (L1RM) and L2 regularization method (L2RM) are determined by comparing the test data sets. Then, the EPR with a classical fitness function is compared with that of L1 or L2 regularization methods to evaluate their abilities in developing regression and producing accurate predictions. The results show that the fitness function combined with the regularization method could improve the EPR. However, L1RM performs better in prediction than L2RM. Improvement of EPR using L1RM could solve problems associated with construction constitutive models or could be used for prediction in geotechnical engineering.

[1]  S. Babaie-Kafaki,et al.  Improved high-dimensional regression models with matrix approximations applied to the comparative case studies with support vector machines , 2022, Optim. Methods Softw..

[2]  Gian Paolo Cimellaro,et al.  Evolutionary Polynomial Regression Algorithm Enhanced with a Robust Formulation: Application to Shear Strength Prediction of RC Beams without Stirrups , 2021, J. Comput. Civ. Eng..

[3]  Jianhua Yin,et al.  A single-objective EPR based model for creep index of soft clays considering L2 regularization , 2019, Engineering Geology.

[4]  Wei Gao,et al.  A comprehensive review on identification of the geomaterial constitutive model using the computational intelligence method , 2018, Adv. Eng. Informatics.

[5]  Ronny Berndtsson,et al.  Evolutionary polynomial regression approach to predict longitudinal dispersion coefficient in rivers , 2018, Journal of Water Supply: Research and Technology - Aqua.

[6]  Ashish Mehta,et al.  Investigation on the Effect of L1 an L2 Regularization on Image Features Extracted Using Restricted Boltzmann Machine , 2018, 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS).

[7]  Chuang Yu,et al.  EPR-RCGA-based modelling of compression index and RMSE-AIC-BIC-based model selection for Chinese marine clays and their engineering application , 2018 .

[8]  Akbar A. Javadi,et al.  Developing constitutive models from EPR‐based self‐learning finite element analysis , 2018 .

[9]  Babak Ebrahimian,et al.  Application of an evolutionary-based approach in evaluating pile bearing capacity using CPT results , 2017 .

[10]  Hongwei Huang,et al.  Evolutionary polynomial regression based modelling of clay compressibility using an enhanced hybrid real-coded genetic algorithm , 2016 .

[11]  Ali Firat Cabalar,et al.  Modeling deformation modulus of a stratified sedimentary rock mass using neural network, fuzzy inference and genetic programming , 2016 .

[12]  V. R. Kohestani,et al.  Modeling the Mechanical Behavior of Carbonate Sands Using Artificial Neural Networks and Support Vector Machines , 2016 .

[13]  Meysam Ramezani,et al.  Prediction of soil saturated water content using evolutionary polynomial regression (EPR) , 2014 .

[14]  Akbar A. Javadi,et al.  Identification of coupling parameters between shear strength behaviour of compacted soils and chemical’s effects with an evolutionary-based data mining technique , 2013 .

[15]  Amir M. Alani,et al.  EPR-based material modelling of soils considering volume changes , 2012, Comput. Geosci..

[16]  Akbar A. Javadi,et al.  Modelling stress-strain and volume change behaviour of unsaturated soils using an evolutionary based data mining technique, an incremental approach , 2012, Eng. Appl. Artif. Intell..

[17]  Akbar A. Javadi,et al.  Modeling of permeability and compaction characteristics of soils using evolutionary polynomial regression , 2011, Comput. Geosci..

[18]  Akbar A. Javadi,et al.  An evolutionary based approach for assessment of earthquake-induced soil liquefaction and lateral displacement , 2011, Eng. Appl. Artif. Intell..

[19]  Akbar A. Javadi,et al.  A new approach for prediction of the stability of soil and rock slopes , 2010 .

[20]  Akbar A. Javadi,et al.  Intelligent finite element method: An evolutionary approach to constitutive modeling , 2009, Adv. Eng. Informatics.

[21]  R. K. Gupta,et al.  A GA based penalty function technique for solving constrained redundancy allocation problem of series system with interval valued reliability of components , 2009, J. Comput. Appl. Math..

[22]  Jiang Li,et al.  Modeling nonlinear elastic behavior of reinforced soil using artificial neural networks , 2009, Appl. Soft Comput..

[23]  Akbar A. Javadi,et al.  Applications of artificial intelligence and data mining techniques in soil modeling , 2009 .

[24]  D. Savić,et al.  A symbolic data-driven technique based on evolutionary polynomial regression , 2006 .

[25]  Hitoshi Iba,et al.  Regularization approach to inductive genetic programming , 2001, IEEE Trans. Evol. Comput..

[26]  Mahdi Roozbeh,et al.  Two penalized mixed–integer nonlinear programming approaches to tackle multicollinearity and outliers effects in linear regression models , 2020, Journal of Industrial & Management Optimization.

[27]  Angelo Doglioni,et al.  Predicting Landslide Displacements by Multi-objective Evolutionary Polynomial Regression , 2015 .

[28]  B. Ebrahimian,et al.  Evaluation of Axial Bearing Capacity of Piles in Sandy Soils by CPT Results , 2013 .

[29]  Orazio Giustolisi,et al.  Evaluation of liquefaction potential based on CPT results using evolutionary polynomial regression , 2010 .

[30]  John H. Holland,et al.  Genetic Algorithms and Adaptation , 1984 .