ICTACT Journal on Soft Computing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Prediction of Compaction Parameters of Soil Using GA and PSO Optimized Relevance Vector Machine (RVM)


Affiliations
1 Department of Civil Engineering, Rajasthan Technical University, India
     

   Subscribe/Renew Journal


The present research introduces the best architectural relevance vector machine (RVM) model for predicting the compaction parameters of soil. The two types of RVM models, i.e., single kernel function-based (SRVM) and dual kernels (parallel) function-based (DRVM), have been constructed in this study. However, the RVM is a kernel function-based approach. Therefore, linear, gaussian, laplacian, and polynomial kernel functions have been implemented in these models. Each model has been optimized by each Genetic algorithm (GA) and particle swarm optimization (PSO) algorithm. For this purpose, 59 soil samples have been collected from the literature. The root mean square error (RMSE), mean absolute error (MAE), and correlation coefficient (R) statistical tools have been used to measure the performance and accuracy of models. From the overall analysis, models MC10 and MD12 have predicted OMC (RMSE = 0.8194%, R = 0.9956, MAE = 0.7920%) and MDD (RMSE = 0.1310g/cc, R = 0.9941, MAE =0.0008g/cc) better than other RVM models. It has also been observed that the DRVM model predicts the compaction parameters better than the SRVM models. The GA algorithm is robust in predicting OMC prediction, and the PSO algorithm is robust in MDD prediction. The score analysis also confirms the robustness of the dual kernel function based DRVM models for predicting OMC and MDD of soil. The sensitivity analysis demonstrates that compaction parameter prediction is strongly influenced by the specific gravity, liquid limit, and plasticity index of soil.

Keywords

Compaction Parameters, Hybrid Approach, Genetic Algorithm, Particle Swarm Optimization Algorithm, Relevance Vector Machine
Subscription Login to verify subscription
User
Notifications
Font Size

  • V Hohn, A. Leme and A.G.R. Llanque, “Empirical Models to Predict Compaction Parameters for Soils in the State of Ceara, Northeastern Brazil”, Ingenieria e Investigacion, Vol. 42, No. 1, pp. 1-13, 2022.

  • K. Pentos, G. Niedbała and T. Wojciechowski, “Evaluation of Multiple Linear Regression and Machine Learning Approaches to Predict Soil Compaction and Shear Stress based on Electrical Parameters”, Applied Sciences, Vol. 12, No. 17, pp.8791-8795, 2022.

  • A.A. Yousif and I.A. Mohamed, “Prediction of Compaction Parameters from Soil Index Properties Case Study: Dam Complex of Upper Atbara Project”, American Journal of Pure and Applied Biosciences, Vol. 4, No. 1, pp. 1-9, 2022.

  • G. Verma and B. Kumar, “Multi-Layer Perceptron (MLP) Neural Network for Predicting the Modified Compaction Parameters of Coarse-Grained and Fine-Grained Soils”, Innovative Infrastructure Solutions, Vol. 7, No. 1, pp.1-13, 2022.

  • K. Othman, “Deep Neural Network Models for the Prediction of the Aggregate Base Course Compaction Parameters”, Designs, Vol. 5, No. 4, pp. 78-89, 2021.

  • K. Othman and H. Abdelwahab, “Prediction of the Soil Compaction Parameters using Deep Neural Networks”, Transportation Infrastructure Geotechnology, Vol. 12, pp. 1-18, 2021.

  • F.E. Jalal and M.F. Javed, “Predicting the Compaction Characteristics of Expansive Soils using Two Genetic Programming-based Algorithms”, Transportation Geotechnics, Vol. 30, pp. 100608-100617, 2021.

  • M.A. Benbouras and L. Lefilef, “Progressive Machine Learning Approaches for Predicting the Soil Compaction Parameters”, Transportation Infrastructure Geotechnology, Vol. 45, pp.1-28, 2021.

  • H.L. Wang and Z.Y. Yin, “High Performance Prediction of Soil Compaction Parameters using Multi Expression Programming”, Engineering Geology, Vol. 276, pp. 105758-105765, 2020.

  • A. Ozbeyaz and M. Soylemez, “Modeling Compaction Parameters using Support Vector and Decision Tree Regression Algorithms”, Turkish Journal of Electrical Engineering and Computer Sciences, Vol. 28, No. 5, pp. 3079-3093, 2020.

  • T.F. Kurnaz and Y. Kaya, “The Performance Comparison of the Soft Computing Methods on the Prediction of Soil Compaction Parameters”, Arabian Journal of Geosciences, Vol. 13, No. 4, pp.1-13, 2020.

  • U.V. Ratnam and K.N. Prasad, “Prediction of Compaction and Compressibility Characteristics of Compacted Soils”, International Journal of Applied Engineering Research, Vol. 14, No. 3, pp.621-632, 2019.

  • A. Hasnat and M.A. Alim, “Prediction of Compaction Parameters of Soil using Support Vector Regression”, Current Trends in Civil and Structural Engineering, Vol. 4, No. 1, pp.1-7, 2019.

  • S.A. Bunyamin and K.J. Osinubi, “Artificial Neural Networks Prediction of Compaction Characteristics of Black Cotton Soil Stabilized with Cement Kiln Dust”, Journal of Soft Computing in Civil Engineering, Vol. 2, No. 3, pp.50-71, 2018.

  • U. Khalid, “Evaluation of Compaction Parameters of Fine-Grained Soils using Standard and Modified Efforts”, International Journal of Geo-Engineering, Vol. 9, No. 1, pp. 1-17, 2018.

  • M. Karimpour-Fard, S.L. Machado and P. Tizpa, “Prediction of Compaction Characteristics of Soils from Index Test’s Results”, Iranian Journal of Science and Technology, Transactions of Civil Engineering, Vol. 43, No. 1, pp.231-248, 2019.

  • A. Ardakani and A. Kordnaeij, “Soil Compaction Parameters Prediction using GMDH-Type Neural Network and Genetic Algorithm”, European Journal of Environmental and Civil Engineering, Vol. 23, No. 4, pp. 449-462, 2019.

  • P. Vinod and G. Sreelekshmy Pillai, “Toughness Limit: A Useful Index Property for Prediction of Compaction Parameters of Fine Grained Soils at any Rational Compactive Effort”, Indian Geotechnical Journal, Vol. 47, No. 1, pp. 107-114, 2017.

  • G.A. Sreelekshmy Pillai and P.P. Vinod, “Re-Examination of Compaction Parameters of Fine-Grained Soils”, Proceedings of the Institution of Civil Engineers-Ground Improvement, Vol. 169, No. 3, pp.157-166, 2016.

  • E. Ozgan and I. Vural, “Multi-Faceted Investigation and Modeling of Compaction Parameters for Road Construction”, Journal of Terramechanics, Vol. 60, pp.33-42, 2015.

  • K.H. Jyothirmayi and K. Suresh, “Prediction of Compaction Characteristics of Soil using Plastic Limit”, International journal of Research in Engineering and Technology, Vol. 4, No. 6, pp. 253-256, 2015.

  • Y. Gurtug and A. Sridharan, “Prediction of Compaction Behaviour of Soils at Different Energy Levels”, International Journal of Engineering Research and Development, Vol. 7, No. 3, pp. 15-18, 2015.

  • K. Farooq, U. Khalid and H. Mujtaba, “Prediction of Compaction Characteristics of Fine-Grained Soils using Consistency Limits”, Arabian Journal for Science and Engineering, Vol. 41, No. 4, pp. 1319-1328, 2016.

  • A.H. Oren, “Estimating Compaction Parameters of Clayey Soils from Sediment Volume Test”, Applied Clay Science, Vol. 101, pp. 68-72, 2014.

  • S. Khuntia and B.M. Das, “Prediction of Compaction Parameters of Coarse Grained Soil using Multivariate Adaptive Regression Splines (MARS)”, International Journal of Geotechnical Engineering, Vol. 9, No. 1, pp.79-88, 2015.

  • O. Sivrikaya and E. Cecen, “Prediction of the Compaction Parameters for Coarse-Grained Soils with Fines Content by MLA and GEP”, Acta Geotechnica Slovenica, Vol. 10, No. 2, pp. 29-41, 2013.

  • R. Al Saffar and S. Khattab, “Prediction of Soil's Compaction Parameter using Artificial Neural Network”,

  • Al-Rafidain Engineering Journal, Vol. 21, No. 3, pp.15-27, 2013.

  • H. Mujtaba, N. Sivakugan and B.M. Das, “Correlation Between Gradational Parameters and Compaction Characteristics of Sandy Soils”, International Journal of Geotechnical Engineering, Vol. 7, No. 4, pp. 395-401, 2013.

  • F. Isik and G. Ozden, “Estimating Compaction Parameters of Fine-and Coarse-Grained Soils by Means of Artificial Neural Networks”, Environmental Earth Sciences, Vol. 69, No. 7, pp. 2287-2297, 2013.

  • O. Sivrikaya and T.Y. Soycan, “Estimation of Compaction Parameters of Fine‐Grained Soils in Terms of Compaction Energy using Artificial Neural Networks”, International Journal for Numerical and Analytical Methods in Geomechanics, Vol. 35, No. 17, pp.1830-1841, 2011.

  • O.J.E.G. Gunaydın, “Estimation of Soil Compaction Parameters by using Statistical Analyses and Artificial Neural Networks”, Environmental Geology, Vol. 57, No. 1, pp. 203-215, 2009.

  • Y. Gurtug and A. Sridharan, “Prediction of Compaction Characteristics of Fine-Grained Soils”, Geotechnique, Vol. 52, No. 10, pp. 761-763, 2002.

  • Y.M. Najjar and W.A. Naouss, “On the Identification of Compaction Characteristics by Neuronets”, Computers and Geotechnics, Vol. 18, No. 3, pp. 167-187, 1996.

  • C.H. Benson and X. Wang, “Estimating Hydraulic Conductivity of Compacted Clay Liners”, Journal of Geotechnical Engineering, Vol. 120, No. 2, pp. 366-387, 1994.

  • C.H. Benson and J.M. Trast, “Hydraulic Conductivity of Thirteen Compacted Clays”, Clays and Clay Minerals, Vol. 43, No. 6, pp. 669-681, 1995.

  • H.B. Nagaraj and M.R. Suresh, “Correlation of Compaction Characteristics of Natural Soils with Modified Plastic Limit”, Transportation Geotechnics, Vol. 2, pp. 65-77, 2015.

  • Y.M. Chew, “Estimating Maximum Dry Density and Optimum Moisture Content of Compacted Soils”, Proceedings of International Conference on Advances in Civil and Environmental Engineering, pp. 1-5, 2015.

  • J. Hair, M.C. Wolfnibarger and R.P. Bush, “Essentials of Marketing”, Mc Graw Hill, 2013.

  • M.E. Tipping, “Sparse Bayesian Learning and the Relevance Vector Machine”, Journal of Machine Learning Research, Vol. 1, No. 1, pp. 211-244, 2001.

  • J.Q. Candela, “Learning with Uncertainty-Gaussian Processes and Relevance Vector Machines”, Master Thesis, Department of Computer Science, Technical University of Denmark, pp. 1-152, 2004.

  • H. Tagimalek and M. Azargoman, “A Hybrid SVM-RVM Algorithm to Mechanical Properties in the Friction Stir Welding Process”, Journal of Applied and Computational Mechanics, Vol. 34, No. 1, pp. 1-12, 2019.

  • E. Rainarli and K.E. Dewi, “Relevance Vector Machine for Summarization”, IOP Publishing, 2018.

  • F. Liu and Z. Yu, “Hybrid RVM Algorithm Based on the Prediction Variance”, Proceedings of International Conference on Neural Information Processing, pp. 53-63, 2017.

  • P. Samui and D. Kim, “Determination of Electrical Resistivity of Soil based on Thermal Resistivity using RVM and MPMR”, Periodica Polytechnica Civil Engineering, Vol. 60, No. 4, pp. 511-515, 2016.

  • P. Samui and J. Karthikeyan, “The Use of a Relevance Vector Machine in Predicting Liquefaction Potential”, Indian Geotechnical Journal, Vol. 44, No. 4, pp. 458-467, 2014.

  • P. Samui, “Application of Relevance Vector Machine for Prediction of Ultimate Capacity of Driven Piles in Cohesionless Soils”, Geotechnical and Geological Engineering, Vol. 30, No. 5, pp. 1261-1270, 2012.

  • S.K. Das, “Prediction of Swelling Pressure of Soil using Artificial Intelligence Techniques”, Environmental Earth Sciences, Vol. 61, No. 2, pp. 393-403, 2010.

  • M. Mitchell, “An Introduction to Genetic Algorithms”, MIT Press, 1998.

  • M. Vijayanand and M.V. Kulkarni, “Regression-BPNN Modelling of Surfactant Concentration Effects in Electroless NiB Coating and Optimization using Genetic Algorithm”, Surface and Coatings Technology, Vol. 409, pp. 126878-126895, 2021.

  • J. Pereira and J.R. Paulo, “A Review of Genetic Algorithm Approaches for Wildfire Spread Prediction Calibration”, Mathematics, Vol. 10, No. 3, pp. 300-314, 2022.

  • X. Dong and L. Chen, “Parameter Identification of 3D Elastic-Plastic Model for Tunnel Engineering Based on Improved Genetic Algorithm”, Mathematical Problems in Engineering, Vol. 2022, pp. 1-16, 2022.

  • F. Dodigovic, J. Jug and K. Agnezovic, “Multi-Objective Optimization of Retaining Wall using Genetic Algorithm”, Environmental Engineering-Inzenjerstvo Okolisa, Vol. 8, No. 1-2, pp.58-65, 2021.

  • S. Katoch and V. Kumar, “A Review on Genetic Algorithm: Past, Present, and Future”, Multimedia Tools and Applications, Vol. 80, No. 5, pp. 8091-8126, 2021.

  • A.G. Gad, “Particle Swarm Optimization Algorithm and Its Applications: A Systematic Review”, Computational Methods in Engineering, Vol. 2022, pp.1-31, 2022.

  • A.R. Kashani, S. Mirjalili and A.H. Gandomi, “Particle Swarm Optimization Variants for Solving Geotechnical Problems: Review and Comparative Analysis”, Archives of

  • Computational Methods in Engineering, Vol. 28, No. 3, pp. 1871-1927, 2021.

  • F. Li, A. Jiang and S. Zheng, “Anchoring Parameters Optimization of Tunnel Surrounding Rock based on Particle Swarm Optimization”, Geotechnical and Geological Engineering, Vol. 39, No. 6, pp. 4533-4543, 2021.

  • F. Yin, T. Xiao, Y. Shao and M. Yuan, “The Prediction of Pile Foundation Buried Depth Based on BP Neural Network Optimized by Quantum Particle Swarm Optimization”, Advances in Civil Engineering, Vol. 2021, pp. 1-15, 2021.

  • R. Ray and W. Zhang, “Application of Soft Computing Techniques for Shallow Foundation Reliability in Geotechnical Engineering”, Geoscience Frontiers, Vol. 12, No. 1, pp. 375-383, 2021.

  • A. Bardhan and A.H. Gandomi, “Novel Integration of Extreme Learning Machine and Improved Harris Hawks Optimization with Particle Swarm Optimization-based Mutation for Predicting Soil Consolidation Parameter”, Journal of Rock Mechanics and Geotechnical Engineering, Vol. 20, No. 3, pp. 1-17, 2022.

  • T.A. Pham, V.Q. Tran and H.L.T. Vu, “Evolution of Deep Neural Network Architecture using Particle Swarm Optimization to Improve the Performance in Determining the Friction Angle of Soil”, Mathematical Problems in Engineering, Vol. 2021, pp. 1-13, 2021.

  • R. Shirani Faradonbeh and H.M. Wong, “Prediction of Ground Vibration due to Quarry Blasting based on Gene Expression Programming: A New Model for Peak Particle Velocity Prediction”, International Journal of Environmental Science and Technology, Vol. 13, No. 6, pp. 1453-1464, 2016.

  • M. Ahmad, M. Safdar and P. Rai, “Prediction of Ultimate Bearing Capacity of Shallow Foundations on Cohesionless Soils: A Gaussian Process Regression Approach”, Applied Sciences, Vol. 11, No. 21, pp. 10317-10322, 2021.

  • M.N.A. Raja and M.U.A. Khan, “An Intelligent Approach for Predicting the Strength of Geosynthetic-Reinforced Subgrade Soil”, International Journal of Pavement Engineering, Vol. 23, No. 10, pp. 3505-3521, 2022.

  • W. Chen and M.M. Tahir, “A New Design of Evolutionary Hybrid Optimization of SVR Model in Predicting the Blast-Induced Ground Vibration”, Engineering with Computers, Vol. 37, No. 2, pp. 1455-1471, 2021.


Abstract Views: 113

PDF Views: 2




  • Prediction of Compaction Parameters of Soil Using GA and PSO Optimized Relevance Vector Machine (RVM)

Abstract Views: 113  |  PDF Views: 2

Authors

Jitendra Khatti
Department of Civil Engineering, Rajasthan Technical University, India
Kamaldeep Singh Grover
Department of Civil Engineering, Rajasthan Technical University, India

Abstract


The present research introduces the best architectural relevance vector machine (RVM) model for predicting the compaction parameters of soil. The two types of RVM models, i.e., single kernel function-based (SRVM) and dual kernels (parallel) function-based (DRVM), have been constructed in this study. However, the RVM is a kernel function-based approach. Therefore, linear, gaussian, laplacian, and polynomial kernel functions have been implemented in these models. Each model has been optimized by each Genetic algorithm (GA) and particle swarm optimization (PSO) algorithm. For this purpose, 59 soil samples have been collected from the literature. The root mean square error (RMSE), mean absolute error (MAE), and correlation coefficient (R) statistical tools have been used to measure the performance and accuracy of models. From the overall analysis, models MC10 and MD12 have predicted OMC (RMSE = 0.8194%, R = 0.9956, MAE = 0.7920%) and MDD (RMSE = 0.1310g/cc, R = 0.9941, MAE =0.0008g/cc) better than other RVM models. It has also been observed that the DRVM model predicts the compaction parameters better than the SRVM models. The GA algorithm is robust in predicting OMC prediction, and the PSO algorithm is robust in MDD prediction. The score analysis also confirms the robustness of the dual kernel function based DRVM models for predicting OMC and MDD of soil. The sensitivity analysis demonstrates that compaction parameter prediction is strongly influenced by the specific gravity, liquid limit, and plasticity index of soil.

Keywords


Compaction Parameters, Hybrid Approach, Genetic Algorithm, Particle Swarm Optimization Algorithm, Relevance Vector Machine

References