Machine Learning Applications in Civil Engineering

By Kundan Meshram

Discusses machine learning and deep learning models for different civil engineering applications. These models work for stochastic methods, wherein internal processing is done using randomized prototypes, due to which indulgence of researchers for internal model design is not needed. Moreover, efficiency of these models is also very high when compared with linear models, due to which they must be deployed for various scenarios. Inspired by these observations, this book provides an insight to various Civil Engineering components, and discusses their design via deep learning models, which will assist readers to gain an edge against others in terms of practical design opportunities in Traffic Engineering, Transportation Engineering, Construction Materials, Geotechnical Engineering, Structural Engineering, Water Resources Engineering, Environmental Engineering, Remote sensing, GIS, Construction techniques and Management, thereby assisting them in exploration of suitable business avenues. As this book explains, various machine learning model designs, which will assist researchers to design multi domain systems with maximum efficiency, readers will also get a detailed review about different lacunas & challenges in current Civil Engineering based research components. These can be explored for designing customized components for an optimum system deployment. This book will initially cover introduction to Machine Learning, and its applications to different Civil Engineering tasks. This includes, Basic Machine Learning Models for data pre-processing, models for data representation, classification models for Civil Engineering Applications, Bioinspired Computing models for Civil Engineering, and their case studies. Using this book, Civil Engineering students & researchers can deep dive into Machine Learning, and identify various solutions to practical Civil Engineering tasks.

• Format: Paperback
• Language: English
• ISBN: 0443153647
• ISBN13: 9780443153648
• Release Date: October 2023
• Publisher: Elsevier
• Length: 218 Pages