Genetic programming in civil engineering: advent, applications and future trends
- PDF / 1,685,754 Bytes
- 23 Pages / 439.37 x 666.142 pts Page_size
- 90 Downloads / 293 Views
Genetic programming in civil engineering: advent, applications and future trends Qianyun Zhang1 · Kaveh Barri1 · Pengcheng Jiao2,3 · Hadi Salehi4 · Amir H. Alavi1,5
© Springer Nature B.V. 2020
Abstract Over the past two decades, machine learning has been gaining significant attention for solving complex engineering problems. Genetic programing (GP) is an advanced framework that can be used for a variety of machine learning tasks. GP searches a program space instead of a data space without a need to pre-defined models. This method generates transparent solutions that can be easily deployed for practical civil engineering applications. GP is establishing itself as a robust intelligent technique to solve complicated civil engineering problems. This paper provides a review of the GP technique and its applications in the civil engineering arena over the last decade. We discuss the features of GP and its variants followed by their potential for solving various civil engineering problems. We finally envision the potential research avenues and emerging trends for the application of GP in civil engineering. Keywords Civil engineering · Prediction · Classification · Genetic programming · Machine learning · Deep learning
* Amir H. Alavi [email protected] http://www.engineering.pitt.edu/AmirhosseinAlavi/ Pengcheng Jiao [email protected] 1
Department of Civil and Environmental Engineering, University of Pittsburgh, Pittsburgh, PA, USA
2
Institute of Port, Coastal and Offshore Engineering, Ocean College, Zhejiang University, Zhoushan 316021, Zhejiang, China
3
Engineering Research Center of Oceanic Sensing Technology and Equipment, Zhejiang University, Ministry of Education, Zhoushan 316021, China
4
Department of Aerospace Engineering, University of Michigan, Ann Arbor, MI, USA
5
Department of Computer Science and Information Engineering, Asia University, Taichung, Taiwan
13
Vol.:(0123456789)
Q. Zhang et al.
1 Introduction Artificial intelligence (AI) emulates the complex biological processes such as learning, reasoning and self-correction to explore solutions for engineering problems. Unlike traditional statistical methods, AI can provide solutions without prior knowledge of the nature of the relationship between the dependent and independent variables. Therefore, the AI techniques can provide alternative solutions to determine engineering design parameters. This can be particularly important when it is not possible to carry out laboratory or field testing. In general, AI can be classified into several sub-categories such as reasoning, programming, artificial life, belief revision, data mining, distributed AI, expert systems, evolutionary computation, systems, knowledge representation, machine learning, natural language understanding, neural networks, theorem proving, constraint satisfaction, and theory of computation (Kushchu 2002; Zhang and Rockett 2007). Figure 1 shows an illustration of the interrelation between AI and major data science techniques including machine learning (ML) and data mining (DM). The
Data Loading...
