Title :
Non-destructive measurement of sugar content in apples using millimeter wave reflectometry and artificial neural networks for calibration
Author :
Oda, Makoto ; Mase, Atsushi ; Uchino, Kiichiro
Author_Institution :
Miyazaki Prefecture Ind. Technol. Center, Miyazaki, Japan
Abstract :
A millimeter wave reflectometer has been developed for non-destructive measurement of sugar content in fruits. The intensity of reflected wave varies not only by sugar content but also by temperature of fruits. Therefore, a calibration curve to calculate sugar content by binary measurements is necessary. We report here a method for making a calibration curve by using a feed forward artificial neural network (ANN). An ANN containing three layers of nodes was trained. Sigmoidal and linear transfer functions were used in the hidden and output layers, respectively. The proposed method was applied satisfactorily to measure sugar content in apples.
Keywords :
agricultural products; calibration; computerised instrumentation; feedforward neural nets; microwave reflectometry; millimetre wave measurement; nondestructive testing; sugar; transfer functions; apple sugar content; artificial neural networks; binary measurements; calibration curve; feedforward artificial neural network; fruit temperature; linear transfer functions; millimeter wave reflectometry; nondestructive measurement; reflected wave intensity; sigmoidal transfer functions; Antenna measurements; Artificial neural networks; Calibration; Millimeter wave measurements; Sugar; Sugar industry; Temperature measurement; Artificial neural networks; Millimeter Wave; Nondestructive testing; Reflectometry; Sugar;
Conference_Titel :
Microwave Conference Proceedings (APMC), 2011 Asia-Pacific
Conference_Location :
Melbourne, VIC
Print_ISBN :
978-1-4577-2034-5
