Determining moisture content of wheat with an artificial neural network from microwave transmission measurements

Author

Bartley, Philip G., Jr. ; Nelson, Stuart O. ; McClendon, Ronald W. ; Trabelsi, Samir

Author_Institution

Georgia Univ., Athens, GA, USA

Volume

47

Issue

1

fYear

1998

fDate

2/1/1998 12:00:00 AM

Firstpage

123

Lastpage

126

Abstract

An artificial neural network (ANN) was used to determine the moisture content of hard, red winter wheat. The ANN was trained to recognize moisture content in the range from 10.6% to 19.2% (wet basis) from transmission coefficient measurements on samples of wheat. The measurements were made at 8 microwave frequencies (10 GHz to 18 GHz) on wheat samples of varying bulk densities (0.72 g/cm³ to 0.88 g/cm³) at 24°C. The trained network predicted moisture content (%) with a mean absolute error of 0.135 (compared with oven-dried measurements)

Keywords

agriculture; computerised instrumentation; dielectric measurement; microwave measurement; moisture measurement; neural nets; 10 to 18 GHz; 24 C; absolute error; artificial neural network; bulk densities; dielectric measurement; microwave frequencies; microwave transmission measurements; moisture content; oven-dried measurement; permittivity; red winter wheat; samples; trained network; transmission coefficient measurement; Antenna measurements; Artificial neural networks; Density measurement; Dielectric measurements; Electrical resistance measurement; Frequency measurement; Microwave measurements; Microwave ovens; Moisture measurement; Permittivity measurement;

fLanguage

English

Journal_Title

Instrumentation and Measurement, IEEE Transactions on

Publisher

ieee

ISSN

0018-9456

Type

jour

DOI

10.1109/19.728803

Filename

728803