ASABE Technical Library - Abstract
Member and Access Notice
Data Fusion in Yield Maps to Reduce Errors Using Distinctive Types of Sensors
Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org
Citation: Paper number 031035, 2003 ASAE Annual Meeting . (doi: 10.13031/2013.15387)Authors: Seung You Na,Won Suk Lee, Dae Jung Shin, Myung Kook Ahn
Keywords: Precision agriculture, Yield map, Data integration/fusion, Sensor-data processing
Due to various types of errors added to yield data, proper methods to reduce measurement errors
are required to produce reliable yield maps. To deal with parasitic types of errors in yield systems, information
provided by the various sensors was utilized and combined in such a way to reduce the measurement errors of
load cells. In addition to four load cells from an experimental model trailer, an accelerometer was used to
obtain information to compensate error induced from vertical movement of the vehicle due to the variation of
ground smoothness.
An array of photo-interrupter circuit was added to provide distinctive information other than weight data that
helped reinforce the process to determine the error sources and types. Also a unit of temperature sensor circuit
provided compensation for sensor characteristics deviation during operation. Data were acquired at 250 Hz
using a TI MSP430 microprocessor from multiple types of the sensors. This sampling rate was considered fast
enough for real yield data so that near white noise components could be cancelled out by moving-average.
Processed error magnitudes of less than 20g could be obtained for 10Kg experimental loads.