Classification of food vegetable oils by fluorimetry and artificial neural networks

There is a large variety and trademarks of vegetable oils in Brazil. Vegetable oils have characteristics quite similar to each other and often cannot be distinguished by only observing the color, odor or taste. Methods for classification of these oils are often costly and time consuming and they usually take advantage of techniques from analytical chemistry and mathematical methods such as PCA (Principal Component Analysis), PCR (Principal Components Regression) or PLS (Properties of Partial Least Squares) and ANN (Artificial Neural Networks) to increase their efficiency. Due to the wide variety of products, more efficient methods are needed to qualify, characterize and classify these substances, because the final price should reflect the excellence of the product that reaches the consumer. This paper proposes a methodology to classify vegetable oils like: Canola, Sunflower, Corn and Soybean from different manufacturers. The method used is characterized by a simple mathematical treatment, a light emission diode and CCD array sensor to capture the spectra of the induced fluorescence in diluted oil samples. An ANN that has three layers, each one with 4 neurons is responsible to perform the spectra classifications. The methodology is capable of classifying vegetable oil and allows fast network training using very few mathematical manipulations in the spectra data with 72% a rate of success.