A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Plasticity-Based Liquefaction Prediction Using Support Vector Machine and Adaptive Neuro-Fuzzy Inference System
This paper proposes computational methods mainly based on plasticity of fine-grained soils for evaluating its liquefaction potential. The proposed ANFIS and SVM models are formulated from the datasets collected from the literature. The SVM is firmly founded on statistical learning theory and uses classification techniques, whereas the ANFIS model is a hybrid of an ANN and a fuzzy inference system (FIS). Several soil properties were employed as input parameters for the models, including the SPT-N value (N1)60, liquid limit (LL), and plasticity index (PI) and few seismic parameters like peak ground acceleration (PGA) and magnitude of earthquake (Mw). The seismic vulnerability of high seismic region of Bihar, India, is evaluated using these developed models, and its performance was evaluated by means of statistical performance tools. The results revealed that SVM and ANFIS model considering plasticity of the fine-grained soil deposit are favourable methods for evaluation of liquefaction susceptibility and capable of becoming a practical approach for geotechnical engineers in the assessment of soil liquefaction response with minimize cost. It was also observed that as PI value increases, liquefaction susceptibility of soil decreases. This dependency of liquefaction on soil’s plasticity provides a new insight to researchers and geotechnical engineers about liquefaction response of plastic soils for economical design of structure.
Plasticity-Based Liquefaction Prediction Using Support Vector Machine and Adaptive Neuro-Fuzzy Inference System
This paper proposes computational methods mainly based on plasticity of fine-grained soils for evaluating its liquefaction potential. The proposed ANFIS and SVM models are formulated from the datasets collected from the literature. The SVM is firmly founded on statistical learning theory and uses classification techniques, whereas the ANFIS model is a hybrid of an ANN and a fuzzy inference system (FIS). Several soil properties were employed as input parameters for the models, including the SPT-N value (N1)60, liquid limit (LL), and plasticity index (PI) and few seismic parameters like peak ground acceleration (PGA) and magnitude of earthquake (Mw). The seismic vulnerability of high seismic region of Bihar, India, is evaluated using these developed models, and its performance was evaluated by means of statistical performance tools. The results revealed that SVM and ANFIS model considering plasticity of the fine-grained soil deposit are favourable methods for evaluation of liquefaction susceptibility and capable of becoming a practical approach for geotechnical engineers in the assessment of soil liquefaction response with minimize cost. It was also observed that as PI value increases, liquefaction susceptibility of soil decreases. This dependency of liquefaction on soil’s plasticity provides a new insight to researchers and geotechnical engineers about liquefaction response of plastic soils for economical design of structure.
Plasticity-Based Liquefaction Prediction Using Support Vector Machine and Adaptive Neuro-Fuzzy Inference System
Lecture Notes in Civil Engineering
Muthukkumaran, Kasinathan (editor) / Ayothiraman, R. (editor) / Kolathayar, Sreevalsa (editor) / Ghani, Sufyan (author) / Kumari, Sunita (author)
Indian Geotechnical Conference ; 2021 ; Trichy, India
Soil Dynamics, Earthquake and Computational Geotechnical Engineering ; Chapter: 44 ; 515-527
2023-01-01
13 pages
Article/Chapter (Book)
Electronic Resource
English
| British Library Online Contents | 2009
Neuro - fuzzy modeling for liquefaction prediction -
| British Library Conference Proceedings | 2004
Prediction of concrete elastic modulus using adaptive neuro-fuzzy inference system
| Online Contents | 2006
Prediction of concrete elastic modulus using adaptive neuro-fuzzy inference system
| British Library Online Contents | 2006