Аутори:
1. Milica Karadžić, University of Novi Sad, Faculty of Technology, Serbia, Serbia
2. Sanja Podunavac Kuzmanović, University of Novi Sad, Faculty of Technology, Serbia, Serbia
3. Lidija Jevrić, University of Novi Sad, Faculty of Technology, Serbia, Serbia
4. Strahinja Kovačević, University of Novi Sad, Faculty of Technology, Serbia, Serbia
5. Aleksandra Tepić Horecki, University of Novi Sad, Faculty of Technology, Serbia, Serbia
6. Zdravko Šumić, University of Novi Sad, Faculty of Technology, Serbia, Serbia
7. Senka Vidović, University of Novi Sad, Faculty of Technology, Serbia, Serbia
8. Žarko Ilin, Faculty of Agriculture, University of Novi Sad, Novi Sad, Serbia, Serbia

Апстракт:
The present paper deals the influence of the contents of six different phytochemical (phenols, carotenoids, chlorophyll a, chlorophyll b, chlorophyll a + b and vitamin C) on antioxidant potential of Kitare and Carmesi lettuce varieties. The data set used for modeling contained 31 lettuce samples. Chemometric classification and regression analysis were conducted in order to select the phytochemicals that best describe the antioxidant activity. Principal component analysis (PCA) and hierarchical cluster analysis (HCA) grouped lettuce samples according to their phytochemical content. Established artificial neural networks (ANNs) models were statistically evaluated. As the best phytochemicals for the antioxidant potential prediction, chlorophyll a, chlorophyll a + b and total phenols content stand out. Predictive ability of the obtained ANNs can be used for antioxidant potential estimations.

Кључне речи:
antioxidant activity, artificial neural networks, classification, lettuce

Тематска област:
Прехрамбене технологије

Датум пријаве сажетка:
19.10.2016.

Конференцијa:
XI Savjetovanje hemičara, tehnologa i ekologa Republike Srpske

Сажетак рада