Yazar "Topi, Ardiana" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • [ X ]
    Öğe
    Machine Learning-Based Classification of Albanian Wines by Grape Variety, Using Phenolic Compound Dataset
    (MDPI, 2025) Topi, Ardiana; Kasaj, Agim; Hudhra, Daniel; Kelebek, Hasim; Guclu, Gamze; Selli, Serkan; Topi, Dritan
    Wine phenolics serve as robust chemical signatures correlated to grape variety, processing, and regional identity. This study explores the potential of machine learning algorithms, combined with the phenolic profiles of Albanian wines, to classify them according to grape variety. Geographic origin analysis was conducted as a preliminary exploration. The dataset of phenolic compounds included white and red wines, spanning the 2017 to 2021 vintages. Using five supervised algorithms-Support Vector Machine (SVM), Random Forest, XGBoost, Logistic Regression, and K-Nearest Neighbors-a high classification accuracy was achieved, with SVM reaching 100% under Leave-One-Out Cross-Validation (LOOCV). To address class imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) and stratified cross-validation were applied. Random Forest feature importance consistently highlighted trans-Fertaric acid and Procyanidin B3 as dominant discriminants. Parallel coordinates plots demonstrated clear varietal patterns driven by phenolic differences, while PCA and hierarchical clustering confirmed unsupervised grouping consistent with wine type and maceration level. Permutation testing (1000 iterations) confirmed the non-randomness of model performance. These findings show that a small set of phenolic markers can offer high classification accuracy, supporting chemically based wine authentication. Although the dataset is relatively small, thorough cross-validation, non-redundant modeling, and chemical interpretability provide a solid foundation for scalable methods. Future work will expand the dataset and explore sensor-based phenolic measurement to enable rapid authentication in wine.
  • [ X ]
    Öğe
    Targeted analysis for the detection of phenolics and authentication of Albanian wines using LC-DAD/ESI-MS/MS combined with chemometric tools
    (Cell Press, 2024) Topi, Dritan; Topi, Ardiana; Güçlü, Gamze; Selli, Serkan; Uzlasir, Turkan; Kelebek, Haşim
    In recent years, Albania has seen a significant increase in wine production, which can be attributed to the growing interest in the diversity of native grape varieties. Among the most popular grape varieties are Kallmet, Shesh i zi (ShiZ), Shesh i bardhe (ShiB), and Cerruje, which are known for their distinctive wines as well as the planted area. A study was conducted to investigate the influence of the territory and vintage on phenolic compounds of single-variety wines from these grape varieties. Liquid chromatography identified and quantified thirty-one phenolic compounds, sub-grouped into flavonoids and non-flavonoids, with diode-array detection coupled to electrospray ionization tandem mass spectrometry (LC-DAD-ESI/MSn). Within the red wines group, the ShiZ variety wine presented the highest phenolic content (1037 mg/L), followed by Kallmet cv. (539 mg/L); conversely, in the white wine group, the ShiB wines (699 mg/L) were distinguished from the Cerruje variety. Gallic acid was the main phenolic compound, followed by procyanidin B3. ShiB and ShiZ had the highest levels, at 215 and 136 mg/L, respectively. Among flavanols, (+)-catechin was found in the highest levels, with the maximum in Kallmet cv. red wine (58.9 mg/L), followed by (-)-epicatechin (29.1 mg/L). The ShiB wine had the highest content of flavonols, with quercetin-3-O-glucuronide and quercetin-3-O-glucoside as the main contributors. The highest quantity of stilbenoids belonged to Kallmet red wine (1.59 mg/L). Applying Principal Component Analysis (PCA) in red and white wine groups made a good separation possible according to variety and region. However, a separation according to vintage year was not successful.