Data processing: artificial intelligence – Neural network
Reexamination Certificate
1998-12-11
2001-11-27
Powell, Mark R. (Department: 2122)
Data processing: artificial intelligence
Neural network
C706S016000, C382S110000, C356S073000
Reexamination Certificate
active
06324531
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates to systems and methods for analyzing a fresh commodity, and, more particularly, to such systems and methods for identifying the geographic origin thereof.
2. Description of Related Art
Fresh produce is often labeled with its geographical origin when that origin is believed to confer a beneficial attribute. Such indicators include “Vidalia onions,” “Idaho potatoes,” and “Florida citrus.” Federal and state laws have been enacted to ban mislabeling of fresh produce, and cases of alleged misrepresentation have been investigated by the U.S. Department. of Agriculture, state governments, and grower groups.
One detection method involves the analysis of vitamin or other organic molecules. Such compounds are, however, subject to variability owing to degradation over time and to storage conditions.
Another way that has been used is to test for the concentration of certain elements in a product, which can be affected by such things as the soil in which the product is grown. The soil-plant system is highly specific for different elements, plant species, and environmental conditions. Under most conditions, a trace element present in the commodity must have existed in the rooting zone of the plant, generally in highly soluble form. A trace element must also pass through at least one cellular membrane in its movement from soil to plant. The selectivity of these processes of mineral accumulation within the commodity varies with different trace elements, with different plants, and the unique environment in which the commodity is grown.
An example of geographic origin variability is the higher barium levels typically found in Brazilian than in Florida oranges;, which can thus be used as an indicator of adulteration. The use of trace metals to define geographical origin of orange juice has been described using inductively coupled plasma—atomic emission spectrometry (ICP-AES) data subjected to a multivariate pattern recognition algorithm and artificial neural networks (Nikdel et al., in Nagy et al.,
Adulteration of Fruit Juice Beverages
, Marciel Dekker, New York, 1988; Nikdel, in Nagy et al.,
Methods to Detect Adulteration of Fruit Juice Beverages
, Vol. I, Agscience, Inc., Auburndale, Fla., 1995).
SUMMARY OF THE INVENTION
It is therefore an object of the present invention to provide a system and method for detecting a geographical origin of a fresh commodity.
It is a further object to provide such a system and method that utilize elemental analysis.
It is another object to provide such a system and method that utilize statistical computational and neural network methods to analyze the elemental data.
It is an additional object to provide such a system and method for detecting adulteration of a commodity.
It is yet a further object to provide such a system and method for detecting a mislabeling of a commodity.
It is yet another object to provide such a system and method for determining the geographic origin of a potato.
These and other objects are achieved by the present invention, a system and method for detecting a geographical origin of a fresh commodity. The method comprises a series of steps, including generating a plurality of neural network models. Each model has as a training set a data set from a plurality of samples of a commodity of known origins. Each sample has been analyzed for a plurality of elemental concentrations.
Each neural network model is presented for classification a test data set from a plurality of samples of a commodity of unknown origins. As with the training set, the samples have been analyzed for the same plurality of elemental concentrations.
Next a bootstrap aggregating strategy is employed to combine the results of the classifications for each sample in the test data set made by each neural network model. Finally, a determination is made from the bootstrap aggregating strategy as to a final classification of each sample in the test data set. This final classification is indicative of the geographical origin of the commodity.
The system of the present invention includes means for performing the above-recited steps, comprising software means for generating the neural network models and a software routine for performing the bootstrap aggregating strategy.
The features that characterize the invention, both as to organization and method of operation, together with further objects and advantages thereof, will be better understood from the is following description used in conjunction with the accompanying drawing. It is to be expressly understood that the drawing is for the purpose of illustration and description and is not intended as a definition of the limits of the invention. These and other objects attained, and advantages offered, by the present invention will become more fully apparent as the description that now follows is read in conjunction with the accompanying drawing.
REFERENCES:
patent: 4550082 (1985-10-01), Martin et al.
patent: 5659624 (1997-08-01), Fazzari et al.
patent: 5761070 (1998-06-01), Conners et al.
patent: 5917927 (1999-06-01), Satake et al.
patent: 6122042 (2000-09-01), Wunderman et al.
Hahn, F.; Muir, A.Y., Neural networks for crop/weed discrimination in different cabbage trials, Signal Processing, 1996., 3rd International Conference on, vol.: 2, Oct. 14-18, 1996, pp.: 1445-1448 vol. 2.*
Stark, E.; Eltoft, T.; Braathen, B., Performance of vegetation classification methods using synthetic multispectral satellite data, Geoscience and Remote Sensing Symposium, 1995. IGARSS '95. 'Quantitative Remote Sensing for Science and Applications', Inte, Jul. 1995.*
A. K. Jain, M. N. Murty and P. J. Flynn; Data clustering: a review; ACM Comput. Surv. 31, 3 (Sep. 1999), pp. 264-323., Oct. 1996.*
Seifollah Nikel Et Al., Trace Metals: Defining Geographical Origin and Detecting Adulteration of Orange Juice, Adulteration of Fruit Juice Beverages, Marcel Dekker, Inc., 1988, pp. 81-105.
Judy Curlee, To Sell The Truth, Food Quality, Apr. 1998, pp. 32-35.
Jo Rita Jordan, Detecting the Geographical Origins of Foods, Inside Laboratory Management, May 1998, pp. 10-12.
Anderson Kim A.
Magnuson Bernadene
Smith Brian
Allen Dyer Doppelt Milbrath & Gilchrist, P.A.
Florida Department of Citrus
Powell Mark R.
Starks, Jr. Wilbert L.
LandOfFree
System and method for identifying the geographic origin of a... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for identifying the geographic origin of a..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for identifying the geographic origin of a... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2571475