Pg. Bartley et al., DETERMINING MOISTURE-CONTENT OF WHEAT WITH AN ARTIFICIAL NEURAL-NETWORK FROM MICROWAVE TRANSMISSION MEASUREMENTS, IEEE transactions on instrumentation and measurement, 47(1), 1998, pp. 123-126
An artificial neural network (ANN) was used to determine the moisture
content of hard, red winter wheat. The ANN was trained to recognize mo
isture content in the range from 10.6% to 19.2% (wet basis) from trans
mission coefficient measurements on samples of wheat. The measurements
were made at 8 microwave frequencies (10 GHz to 18 GHz) on wheat samp
les of varying bulk densities (0.72 g/cm(3) to 0.88 g/cm(3)) at 24 deg
rees C. The trained network predicted moisture content (%) with a mean
absolute error of 0.135 (compared with oven-dried measurements).