Page Banner

United States Department of Agriculture

Agricultural Research Service

Research Project: Pesticide Application Technologies for Spray-drift Management, Maximizing In-field Deposition, and Targeted Spraying

Location: Crop Production Systems Research Unit

Title: Development of Soft Computing and Applications in Agricultural and Biological Engineering

Authors
item Huang, Yanbo
item Lan, Yubin
item Thomson, Steven
item Fang, Alex
item Hoffmann, Wesley
item Lacey, Ron

Submitted to: Computers and Electronics in Agriculture
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: January 24, 2010
Publication Date: March 23, 2010
Repository URL: http://hdl.handle.net/10113/41981
Citation: Huang, Y., Lan, Y., Thomson, S.J., Fang, A., Hoffmann, W.C., Lacey, R. 2010. Development of Soft Computing and Applications in Agricultural and Biological Engineering. Computers and Electronics in Agriculture. 71:107-127.

Interpretive Summary: Soft computing is a set of computing techniques that are relative to hard computing. Hard computing contains a huge set of conventional computing techniques such as stochastic and statistical methods that are used to solve problems that have a direct connection between the size of a problem and the amount of resources needed to solve the problem. The travelling salesman problem is a typical one solved by hard computing. However, some problems may be so large that, even at super computing speeds, it still would take the lifetime of the Universe to solve them. Soft computing was proposed to overcome the problems of hard computing by using inexact, intelligent methods to give useful but inexact answers to very complex problems. Soft computing mimics human intelligence. A number of important techniques are included in soft computing: fuzzy logic, model of human reasoning in imprecise environment (not simply yes or no), artificial neural networks, model of interconnecting neurons from human brain studies, and genetic algorithm, a problem solving scheme mimicking the processes in evolutionary biology. Soft computing has been widely used in engineering computing. In agricultural and biological engineering, fuzzy logic, artificial neural networks, genetic algorithms, decision trees, and support vector machines, new soft computing technique, have been developed in study of soil and water problems related to crop growth management, design, analysis and control food processing, and decision support in precision farming. With the state of the art, it is necessary to clarify the limitations of soft computing and project what is going on soft computing will be in the next decade or so for more research and applications, especially in agricultural and biological engineering.

Technical Abstract: Soft computing is a set of “inexact” computing techniques, which are able to model and analyze very complex problems. For these complex problems, more conventional methods have not been able to produce cost-effective, analytical, or complete solutions. Soft computing has been extensively studied and applied in the last three decades for scientific research and engineering computing. In agricultural and biological engineering, researchers and engineers have developed methods of fuzzy logic, artificial neural networks, genetic algorithms, decision trees, and support vector machines to study soil and water regimes related to crop growth, analyze the operation of food processing, and support decision-making in precision farming. This paper will review the development of soft computing techniques, and a number of advanced soft computing techniques will be introduced. With these concepts and methods, applications of soft computing in the field of agricultural and biological engineering will be presented, especially in the soil and water context for crop management and decision support for precision agriculture. The future of development and application of soft computing in agricultural and biological engineering will be discussed.

Last Modified: 10/24/2014