Autorentext

Prof. Zong Woo Geem works for the Department of Smart City at Gachon University in South Korea. He has obtained B.Eng. from Chung-Ang University, M.Eng. and Ph.D. from Korea University, and M.Sc. from Johns Hopkins University, and researched at Virginia Tech, University of Maryland - College Park, and Johns Hopkins University. He invented a music-inspired optimization algorithm, Harmony Search (HS), which has been applied to various scientific and engineering problems as well as social and cultural problems. His research interest includes theoretical background (e.g. novel human-experience-based derivative of HS rather than existing analytic-calculus-based derivative) and problem-specific development (e.g. problem-specific operator of HS) of phenomenon-mimicking algorithm and its applications to sustainability & culture issues.

Gebrail Bekda, Professor, is researcher in Mechanics at Istanbul University - Cerrahpaa. He obtained his DPhil in Structural Engineering from Istanbul University with a thesis subject of design of cylindrical walls. He was one of the guest editors in 2017 special issue of KSCE Journal of Civil Engineering. He co-chaired 6th International Conference on Harmony Search, Soft Computing and Applications (ICHSA 2020). He has authored about 500 papers for journals and scientific events.

Sinan Melih Nigdeli, Professor, is researcher in Mechanics at Istanbul University - Cerrahpaa. He obtained his DPhil in Structural Engineering from Istanbul Technical University with a thesis subject of active control. He was one of the guest editors in 2017 special issue of KSCE Journal of Civil Engineering. He co-chaired 6th International Conference on Harmony Search, Soft Computing and Applications (ICHSA 2020). He has authored about 500 papers for journals and scientific events.

Yaren Aydn is research assistant in Mechanics at Istanbul University - Cerrahpaa. Yaren Aydn is studying at stanbul University-Cerrahpaa, Institute of Postgraduate Education, Department of Civil Engineering, PhD program on the subject of Artificial Intelligence-Machine Learning. In her master thesis, Ms. Yaren AYDIN applied important technical knowledge: computer programming, optimization and analysis of various types of structures. In today's world, most engineering problems are based on maximum efficiency with limited resources, leading to optimization processes that involve civil engineering knowledge and computer programming. She has also carried out various studies on artificial intelligence and machine learning in her articles and papers. There are also studies that combine optimization and artificial intelligence. She has participated in many conferences on optimization and machine learning.

Ümit Ikda is currently working as a Professor of Construction Informatics at the Department of Architecture in Mimar Sinan Fine Arts University. He has a PhD in Construction Informatics from the University of Salford, U.K.His current research interests are in Machine and Deep Learning, Internet of Things, 3D GIS, BIM and Structural Equation Modeling. He has started teaching in 1999 and since then he has worked full and part time at (chronological order:) Ege University, Beykent University, Istanbul Kultur University, Istanbul University, Istanbul Esenyurt University, Bogazici University, Istanbul Technical University. In addition, he has worked as a senior researcher at Coventry University (2004), and the University of Central Lancashire (2013).

Prof. Tae-Hyung Kim has been serving as a Professor in the Department of Civil Engineering at the National Korea Maritime and Ocean University in South Korea since 2004. He obtained his B.Eng. and M.Eng. from Chung-Ang University in South Korea, and his Ph.D. from the University of Colorado at Boulder, CO. After completing his Ph.D., he conducted research at Lehigh University. He also worked as an engineer for Hyundai Construction. Additionally, he has served as a visiting professor at Oregon State University. He holds a professional engineer license issued by the State of Washington, USA. His main research interests forensic geotechnical engineering, such as the characterization of deep soft soil behavior, and the behavior of seabed and coastal structures due to interactions among waves, seabed, and structures.

Klappentext
Introduction and Applications of Machine Learning in Geotechnics offers a comprehensive exploration of machine learning methodologies and their diverse applications in geotechnical engineering. The book begins with a detailed review of machine learning methods tailored for geotechnical applications, setting the foundation for subsequent chapters. Regression models are utilized to predict shear wave velocities while optimization-based approaches are employed to determine the optimal dimensions of reinforced concrete (RC) retaining walls. The book further explores the identification of gravelly soil through optimized machine learning models and predicts stress-strain responses using data from simple shear tests.

Additionally, it outlines the forecasting of liquefaction events triggered by seismic activities and estimates the uniaxial compressive strength of soil using machine learning techniques. The prediction of vertical effective stress and specific penetration resistance is examined to enhance soil characterization and geotechnical analyses. The authors' provide valuable insights for geotechnical engineers and researchers seeking to leverage advanced computational tools for enhanced geotechnical assessments and design processes.

Inhalt

1. A review of machine learning (ML) methods for geotechnical engineering
2. Regression models for shear wave velocity prediction
3. Optimization based approaches to predict optimal dimensions of RC retaining walls
4. Gravelly soil identification based on the optimized ML models
5. Prediction of the Stress-strain responses by simple shear tests
6. Predicting the liquefaction from seismic events
7. Estimation of uniaxial compressive strength of soil
8. Prediction of vertical effective stress ( 'v) and specific penetration resistance (ps)
9. Slope stability prediction using ML models