Orange juice classification with a biologically based neural network

• Published in: Computers & chemistry Vol. 20; no. 2; pp. 261 - 266
• Main Authors: Dettmar, H.P., Barbour, G.S., Blackwell, K.T., Vogl, T.P., Alkon, D.L., Fry, F.S., Totah, J.E., Chambers, T.L.
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01-06-1996
• Subjects: Algorithms; Beverages - adverse effects; Beverages - analysis; Beverages - classification; Chromatography, High Pressure Liquid; Citrus - chemistry; Evaluation Studies as Topic; Flavonoids - analysis; Food Contamination - analysis; Neural Networks (Computer); Trace Elements - analysis
• ISSN: 0097-8485
• DOI: 10.1016/0097-8485(95)00015-1

Dystal, an artificial neural network, was used to classify orange juice products. Nine varieties of oranges collected from six geographical regions were processed into single-strength, reconstituted or frozen concentrated orange juice. The data set represented 240 authentic and 173 adulterated samples of juices; 16 variables [8 flavone and flavanone glycoside concentrations measured by high-performance liquid chromatography (HPLC) and 8 trace element concentrations measured by inductively coupled plasma spectroscopy] were selected to characterize each juice and were used as input to Dystal. Dystal correctly classified 89.8% of the juices as authentic or adulterated. Classification performance increased monotonically as the percentage of pulpwash in the sample increased. Dystal correctly identified 92.5% of the juices by variety (Valencia vs non-Valencia).