Journal article
Orange juice classification with a biologically based neural network
Computers & chemistry, Vol.20(2), pp.261-266
06/01/1996
DOI: 10.1016/0097-8485(95)00015-1
PMID: 8936424
Abstract
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).
Details
- Title: Subtitle
- Orange juice classification with a biologically based neural network
- Creators
- H.P. Dettmar - Environmental Research Institute of MichiganG.S. Barbour - Environmental Research Institute of MichiganK.T. Blackwell - Environmental Research Institute of MichiganT.P. Vogl - Environmental Research Institute of MichiganD.L. Alkon - National Institute of Neurological Disorders and StrokeF.S. Fry - Center for Food Safety and Applied NutritionJ.E. Totah - Center for Food Safety and Applied NutritionT.L. Chambers - Center for Food Safety and Applied Nutrition
- Resource Type
- Journal article
- Publication Details
- Computers & chemistry, Vol.20(2), pp.261-266
- DOI
- 10.1016/0097-8485(95)00015-1
- PMID
- 8936424
- NLM abbreviation
- Comput Chem
- ISSN
- 0097-8485
- Publisher
- Elsevier Ltd
- Language
- English
- Date published
- 06/01/1996
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Iowa Neuroscience Institute
- Record Identifier
- 9984446535802771
Metrics
10 Record Views