Title :
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
fDate :
2/1/1998 12:00:00 AM
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;
Journal_Title :
Instrumentation and Measurement, IEEE Transactions on
