|
|
|
If you are an ASABE member or if your employer has arranged for access to the full-text, click the underlined title below to view. Don't have access to the full text? Click here for options. Detection and Identification of Stored-Grain Insects with RF/Microwave and Neural Network TechnologyPublished by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org Citation: Transactions of the ASABE. 52(6): 2105-2114. @2009Authors: F. Ding, C. L. Jones, P. Weckler Keywords: Detection, Identification and classification, Neural network, Radio frequency and microwave, Sensing, Stored-grain insects Eight different species of stored-grain insects were investigated in the radio frequency (RF) and microwave frequency range of 0.3 to 1200 MHz with a free-space device using a vector network analyzer. Detection and identification analysis were performed using neural network techniques. One-, two- and three-waveband sets were optimized in the frequency range to maximize the detection and identification recognition rate. The total recognition rate of identification for the insects was 73%, while the recognition rate of the detection of the empty device was 76% using the frequencies of 180.3, 1020, and 1032 MHz. |