A hyper parameterized artificial neural network approach for prediction of the factor of safety against liquefaction
Erişim
info:eu-repo/semantics/openAccessTarih
2023Yazar
Kurnaz, Talas FikretErden, Caner
Kökçam, Abdullah Hulusi
Dağdeviren, Uğur
Demir, Alparslan Serhat
Üst veri
Tüm öğe kaydını gösterKünye
Kurnaz, T. F., Erden, C., Kökçam, A. H., Dağdeviren, U., & Demir, A. S. (2023). A hyper parameterized artificial neural network approach for prediction of the factor of safety against liquefaction. Engineering Geology, 319 doi:10.1016/j.enggeo.2023.107109Özet
Soil liquefaction during earthquakes is a complex geotechnical engineering problem. Although various analytical approaches exist for predicting liquefaction risk, their limitations have led researchers to explore using artificial intelligence and machine learning methods. Machine learning has the potential to significantly improve the ability to predict soil liquefaction and mitigate the associated risks. This study proposes a hyper parameterized artificial neural network architecture using random search, grid search, and Bayesian optimization algorithms to predict the factor of safety against liquefaction. The performances of hyper parameterized machine learning algorithms, including artificial neural networks (ANN), decision trees (DT), random forest (RF), and support vector regression (SVR), were compared. Statistical tests show that the proposed ANN outperformed the others with a determination coefficient of 0.99 at a 95% significance level. Hyperparameter optimization significantly improved learning performance with up to a 48% reduction in RMSE scores. The proposed method was compared with previous studies, and performance results confirmed its effectiveness and generalization ability. In conclusion, this study highlights the potential of machine learning algorithms for predicting soil liquefaction and emphasizes the importance of hyperparameter optimization for improving model performance. The findings of this study have practical implications for improving liquefaction risk assessment and mitigating the associated hazards. © 2023 Elsevier B.V.
WoS Q Kategorisi
Q1Kaynak
Engineering GeologyCilt
319Koleksiyonlar
İlgili Öğeler
Başlık, yazar, küratör ve konuya göre gösterilen ilgili öğeler.
-
Comparison of EEG- Based Deep Neural Network Classifiers for Emotion Recognition using Selected Electrodes
Gul, Ayse Nur Ay; Altuntas, Abdullah (Institute of Electrical and Electronics Engineers Inc., 2023)In this study, SVM and DNN models were employed to classify participants' emotional states using the publicly available SEED dataset, achieving impressive accuracy rates of 79.8% for DNN and 79.4% for SVM, surpassing the ... -
Makine öğrenmesi yöntemleri ile tiroit hastalığının teşhisi
Yıldız, Abdulbaki (Sakarya Uygulamalı Bilimler Üniversitesi, 2019)[Abstract Not Available] -
Detection of Grinding Burn Fault in Bearings by Squeeze Net
Ceylan N.; Kacar S.; Guney E.; Bayilmis C. (Institute of Electrical and Electronics Engineers Inc., 2022)Grinding burn is a significant problem encountered in the bearing manufacturing process. In the case of burns in the grinding bearing material, the surface quality deteriorates, and the material's internal structure and ...